MaltSci 麦伴科研

Appearance

Popular Reports / Clinical Medicine

This report is written by MaltSci based on the latest literature and research findings

How does AI assist in medical imaging? ​

Abstract ​

The integration of artificial intelligence (AI) into medical imaging is revolutionizing healthcare by addressing the growing complexity and volume of imaging data. Traditional image analysis methods often struggle to keep pace, highlighting the need for innovative solutions that enhance diagnostic accuracy and efficiency. AI technologies, particularly machine learning and deep learning, have emerged as powerful tools that automate and improve various stages of the imaging process, from acquisition to interpretation. This report explores the significance of AI in medical imaging, emphasizing its potential to improve patient outcomes and alleviate the burden on healthcare providers. Key advancements include AI's role in detecting abnormalities, optimizing imaging protocols, and integrating multimodal data to support personalized treatment plans. However, the integration of AI also presents challenges related to data privacy, algorithmic bias, and ethical considerations. The report concludes by outlining future directions for research and the need for comprehensive regulatory frameworks to ensure the safe implementation of AI technologies in clinical practice. By examining the intersection of AI and medical imaging, this report aims to provide a comprehensive understanding of how these technologies can transform diagnostic practices and inform future research in the biomedical field.

Outline ​

This report will discuss the following questions.

  • 1 Introduction
  • 2 Overview of Medical Imaging
    • 2.1 Types of Medical Imaging Techniques
    • 2.2 Importance of Imaging in Diagnosis and Treatment
  • 3 Role of AI in Medical Imaging
    • 3.1 Image Acquisition
    • 3.2 Image Analysis and Interpretation
    • 3.3 Workflow Optimization
  • 4 Current Applications of AI in Medical Imaging
    • 4.1 Radiology
    • 4.2 Pathology
    • 4.3 Cardiology
  • 5 Challenges and Ethical Considerations
    • 5.1 Data Privacy and Security
    • 5.2 Bias and Fairness in AI Algorithms
    • 5.3 Regulatory and Legal Issues
  • 6 Future Directions and Research Opportunities
    • 6.1 Innovations in AI Technologies
    • 6.2 Integration of AI with Other Technologies
    • 6.3 Enhancing Clinical Decision-Making
  • 7 Conclusion

1 Introduction ​

The integration of artificial intelligence (AI) into medical imaging is heralding a new era in healthcare, driven by the increasing complexity and volume of imaging data generated in clinical settings. Traditional methods of image analysis often struggle to keep pace with this growth, leading to a pressing need for innovative solutions that can enhance diagnostic accuracy, efficiency, and accessibility. AI technologies, particularly machine learning and deep learning, have emerged as powerful tools that can transform medical imaging practices by automating and improving various stages of the imaging process, from acquisition to interpretation and workflow optimization[1][2].

The significance of AI in medical imaging cannot be overstated. As healthcare systems grapple with the challenges posed by an aging population and the rising prevalence of chronic diseases, the demand for accurate and timely diagnoses has never been greater. Medical imaging plays a critical role in diagnosing and treating a wide array of conditions, providing essential insights that guide clinical decision-making[3]. The ability of AI to analyze vast amounts of imaging data quickly and accurately holds the potential to not only improve patient outcomes but also alleviate the burden on healthcare providers by streamlining workflows and reducing diagnostic errors[4].

Currently, the application of AI in medical imaging is expanding rapidly, with notable advancements in various domains, including radiology, pathology, and cardiology. In radiology, AI algorithms are being developed to assist in the detection of abnormalities, characterization of diseases, and even the generation of radiology reports[5]. In pathology, AI is enhancing the analysis of whole slide images, enabling pathologists to extract valuable insights from histological data that were previously unattainable[6]. In cardiology, AI-driven tools are being utilized to interpret echocardiograms and other cardiac imaging modalities, further demonstrating the versatility and potential of AI in improving diagnostic capabilities across specialties[7].

Despite the promising developments, the integration of AI into medical imaging is not without challenges. Issues related to data privacy and security, algorithmic bias, and the need for regulatory frameworks pose significant hurdles that must be addressed to ensure the safe and equitable implementation of AI technologies in clinical practice[3]. Furthermore, the ethical implications of relying on AI for diagnostic purposes necessitate careful consideration, as the potential for misinterpretation or over-reliance on automated systems could adversely affect patient care[1].

This report is organized as follows: Section 2 provides an overview of medical imaging, detailing the various techniques employed and their importance in diagnosis and treatment. Section 3 delves into the specific roles that AI plays in medical imaging, including advancements in image acquisition, analysis, and workflow optimization. In Section 4, current applications of AI in radiology, pathology, and cardiology are explored in detail. Section 5 addresses the challenges and ethical considerations associated with AI integration in medical imaging, while Section 6 discusses future directions and research opportunities in this rapidly evolving field. Finally, Section 7 concludes the report by summarizing the transformative potential of AI in medical imaging and its implications for the future of healthcare.

By examining the intersection of AI and medical imaging, this report aims to provide a comprehensive understanding of how these technologies can revolutionize diagnostic practices, enhance patient outcomes, and inform future research and clinical applications in the biomedical field.

2 Overview of Medical Imaging ​

2.1 Types of Medical Imaging Techniques ​

Artificial intelligence (AI) is revolutionizing the field of medical imaging by enhancing various aspects of image acquisition, analysis, and interpretation. The integration of AI technologies into medical imaging workflows has led to significant improvements in diagnostic accuracy, efficiency, and the overall quality of patient care.

AI assists in medical imaging through several key mechanisms:

  1. Image Analysis and Interpretation: AI algorithms, particularly deep learning models, have demonstrated remarkable capabilities in analyzing complex medical images. These models can identify and classify abnormalities with high accuracy, significantly reducing the time required for image interpretation. For instance, AI has been utilized to detect tumors in radiological examinations and early signs of diseases in retinal images, thereby facilitating timely interventions (Pinto-Coelho 2023) [8].

  2. Data Augmentation and Synthesis: Generative AI techniques have shown great potential in medical imaging tasks, such as data augmentation and image synthesis. These methods can enhance the quality of images and generate synthetic images that replicate the characteristics of real clinical images. This is particularly useful in situations where high-quality imaging data is scarce, allowing for improved training of diagnostic models (Koohi-Moghadam 2023) [1].

  3. Optimizing Imaging Protocols: AI can optimize imaging protocols by improving image reconstruction processes and enhancing image quality. For example, AI-driven methods have been employed in PET/CT and PET/MRI studies to improve reconstruction speed and accuracy, which can lead to lower radiation doses and better diagnostic outcomes (Zaharchuk 2021) [9]. Additionally, AI can perform virtual attenuation correction and automate the quantification of risk markers, streamlining the diagnostic process (Miller 2025) [10].

  4. Integration of Multimodal Data: AI facilitates the integration of multimodal data, including clinical, imaging, and laboratory information, to support more accurate diagnoses and refined risk stratification. This comprehensive approach allows for personalized treatment plans that are tailored to individual patient profiles, enhancing the effectiveness of medical interventions (Miller 2025) [10].

  5. Improving Patient Outcomes: By expediting the interpretation of complex images and enhancing early disease detection, AI-based diagnostic tools contribute to better patient outcomes. The ability to rapidly and accurately analyze medical images not only improves diagnostic accuracy but also aids in the development of personalized treatment strategies, ultimately optimizing healthcare delivery (Pinto-Coelho 2023) [8].

  6. Augmenting Clinical Decision-Making: AI technologies can augment clinical decision-making by providing clinicians with advanced analytical tools that enhance their visual workflow. For instance, AI can generate enhanced images that assist cardiologists in making informed decisions based on synthesized clinical data (Olender 2021) [11].

In summary, AI's role in medical imaging encompasses a wide range of applications that enhance the accuracy, efficiency, and quality of diagnostic processes. The continuous evolution of AI technologies promises to further transform medical imaging, leading to more effective and personalized healthcare solutions.

2.2 Importance of Imaging in Diagnosis and Treatment ​

Artificial intelligence (AI) has emerged as a transformative force in the field of medical imaging, significantly enhancing diagnostic accuracy and treatment efficacy. The integration of AI into medical imaging practices has facilitated a paradigm shift in how healthcare professionals analyze and interpret complex imaging data.

One of the primary roles of AI in medical imaging is the enhancement of image analysis through advanced algorithms. Techniques such as deep learning, convolutional neural networks, and generative adversarial networks have been developed to improve the accuracy and efficiency of image interpretation. These innovations enable rapid and precise detection of abnormalities, which is crucial for timely diagnosis and intervention. For instance, AI has shown remarkable capabilities in identifying tumors during radiological examinations and detecting early signs of diseases in various imaging modalities, including retinal images[8].

Moreover, AI-driven tools assist in optimizing the quality of medical images, thereby reducing the need for repeat scans and minimizing patient exposure to radiation. In nuclear cardiology, for example, AI enhances image quality and enables virtual attenuation correction, which significantly improves diagnostic accuracy and efficiency[10]. This capability is particularly important given the increasing volume of imaging studies performed and the associated challenges in managing image acquisition and interpretation.

AI also plays a crucial role in augmenting clinical workflows by integrating multimodal data, which includes clinical, stress, and imaging features. This integration allows for more accurate diagnosis and refined risk stratification, ultimately leading to personalized treatment plans[10]. The ability of AI to capture and analyze changes in imaging "phenotype" over time further aids in response assessment, allowing healthcare providers to tailor treatment strategies based on real-time data[12].

In addition to enhancing diagnostic capabilities, AI contributes to the generation of synthetic medical images that replicate the style and content of traditionally acquired images. This approach not only improves image quality but also enhances medical education and clinical decision-making by providing a more comprehensive visual representation of the underlying pathology[11].

Furthermore, AI technologies facilitate the identification of disease-specific biomarkers and patient risk stratification, which are essential for prognostication and predicting adverse events[12]. By transforming qualitative imaging characteristics into quantifiable data, AI enables healthcare professionals to make informed decisions regarding patient management and treatment pathways.

In summary, AI's integration into medical imaging has profound implications for diagnosis and treatment. By improving image quality, enhancing diagnostic accuracy, and facilitating personalized care, AI is poised to revolutionize the landscape of medical imaging and ultimately lead to better patient outcomes[13].

3 Role of AI in Medical Imaging ​

3.1 Image Acquisition ​

Artificial intelligence (AI) plays a transformative role in medical imaging, particularly in the domain of image acquisition. The integration of AI technologies enhances various aspects of the imaging workflow, from the initial stages of image capture to the processing and interpretation of the resulting data.

AI is employed to improve image quality, which is crucial for accurate diagnosis and assessment. Techniques such as machine learning algorithms can be utilized to reduce noise and artifacts in images, thereby enhancing clarity and detail. This improvement not only aids radiologists in their evaluations but also minimizes the need for repeat scans, which can expose patients to unnecessary radiation. Furthermore, AI can optimize image acquisition parameters in real-time, ensuring that the images obtained are of the highest possible quality given the specific clinical context.

In addition to enhancing image quality, AI technologies assist in reducing image acquisition times. By streamlining the process, AI can facilitate quicker imaging protocols, which is particularly beneficial in acute care settings where time is critical. This efficiency can lead to faster diagnoses and treatment decisions, ultimately improving patient outcomes.

Once images are acquired, AI contributes significantly to the reconstruction and processing stages. For instance, AI can aid in motion correction and image registration, ensuring that images are accurately aligned and free from distortions caused by patient movement. This is particularly relevant in modalities such as magnetic resonance imaging (MRI) and computed tomography (CT), where precision is paramount.

Moreover, AI can perform image attenuation correction, which is vital for accurate interpretation of imaging data. By utilizing advanced algorithms, AI can analyze and correct for variations in image intensity that may arise from differing tissue densities, thereby providing a more accurate representation of the underlying anatomy.

The segmentation of anatomical features is another area where AI excels. By leveraging deep learning techniques, AI can automatically delineate structures of interest from imaging datasets, facilitating more precise measurements and analyses. This capability is particularly useful in complex imaging scenarios, such as identifying tumors or assessing organ volumes.

In summary, AI enhances the image acquisition process in medical imaging by improving image quality, reducing acquisition times, optimizing reconstruction processes, and automating segmentation tasks. These advancements not only streamline workflows but also contribute to more accurate diagnoses and better patient care, underscoring the pivotal role of AI in modern medical imaging practices[1][12][14].

3.2 Image Analysis and Interpretation ​

Artificial intelligence (AI) plays a transformative role in medical imaging, particularly in the areas of image analysis and interpretation. The integration of AI technologies, especially deep learning algorithms, has significantly enhanced the capabilities of medical image analysis, enabling more accurate and efficient diagnostic processes.

One of the primary applications of AI in medical imaging is in the enhancement of image quality and the reduction of human error. Traditional manual interpretation of medical images, such as those obtained from computed tomography (CT) and X-ray, can be tedious and time-consuming, leading to potential inaccuracies due to human fatigue or oversight. AI algorithms, particularly those based on convolutional neural networks, excel in automatically recognizing complex patterns in imaging data, thereby providing quantitative assessments that surpass qualitative human evaluations (Hosny et al. 2018) [15].

AI also contributes to various stages of the imaging value chain, from image acquisition to the generation of diagnostic reports. For instance, AI can optimize imaging protocols, enhance scheduling, and even shorten acquisition times for magnetic resonance imaging (MRI) while minimizing artifacts and radiation exposure in CT imaging (Gorelik & Gyftopoulos 2021) [16]. Moreover, AI has the potential to assist in the interpretation of images by identifying key features such as fractures, tumors, and other pathological conditions. This capability is particularly beneficial in fields like musculoskeletal radiology, where AI can help in the evaluation of bone age, body composition, and the detection of conditions like osteoporosis and osteoarthritis (Gorelik & Gyftopoulos 2021) [16].

In the realm of nuclear cardiology, AI is poised to enhance myocardial perfusion imaging (MPI) workflows. It can improve image quality, facilitate motion correction, and optimize image registration, ultimately aiding in disease diagnosis and risk prediction (Miller & Slomka 2024) [14]. This demonstrates the versatility of AI across different imaging modalities and its potential to streamline processes that are critical for effective patient care.

Additionally, generative AI techniques are emerging as valuable tools for tasks such as data augmentation and image synthesis, which can further enhance the robustness of medical imaging applications (Koohi-Moghadam & Bae 2023) [1]. The ethical considerations surrounding the use of AI in medical imaging also warrant attention, as the deployment of these technologies must balance innovation with patient safety and data privacy.

In summary, AI significantly enhances medical imaging through improved diagnostics, more accurate risk stratification, and streamlined workflows. By leveraging advanced algorithms for image analysis and interpretation, AI not only accelerates the identification of diseases but also fosters a more efficient and tailored approach to patient care in the medical field. The ongoing development and integration of AI technologies promise to further revolutionize the landscape of medical imaging, ultimately leading to better clinical outcomes.

3.3 Workflow Optimization ​

Artificial intelligence (AI) plays a significant role in optimizing workflows in medical imaging, facilitating improvements in efficiency, accuracy, and clinical decision-making. The integration of AI technologies into clinical imaging has the potential to enhance various aspects of the imaging process, from acquisition to interpretation and reporting.

One of the primary benefits of AI in medical imaging is its ability to streamline workflow processes. In a systematic literature review conducted by Wenderott et al. (2024), the authors assessed the impact of AI implementation on efficiency in real-world clinical workflows. They found that out of 48 original studies included in their review, 67% of the 33 studies measuring task duration reported reductions in time due to AI integration. However, meta-analyses of these studies did not consistently demonstrate significant effects, indicating variability in the outcomes across different implementations of AI[17].

In nuclear cardiology, AI can enhance myocardial perfusion imaging (MPI) workflows by improving image quality, optimizing motion correction, and assisting in image reconstruction processes. AI applications can also facilitate the segmentation of anatomical features and generate synthetic images, thus aiding in disease diagnosis and risk prediction[14].

Furthermore, AI applications are designed to assist radiologists by reducing cognitive and manual burdens, thereby improving diagnostic accuracy and shortening the time required to take clinical action based on imaging results. Gu et al. (2025) highlighted that AI tools can accelerate imaging acquisition and streamline various time-intensive steps in the radiology workflow, ultimately leading to better patient outcomes and enhanced operational efficiency[18].

In emergency radiology, AI algorithms have been developed to support rapid image analysis, which is critical given the high stakes and increased volume of images in emergency settings. These algorithms can automatically identify disease states and provide quantitative assessments of disease severity, significantly improving workflow efficiency and enabling faster turnaround times for complex cases[19].

Overall, AI's role in medical imaging is multifaceted, with applications that not only enhance the efficiency of imaging workflows but also improve the quality of diagnostic information available to clinicians. However, it is essential to note that the successful implementation of AI technologies in clinical workflows requires ongoing evaluation and standardized reporting to ensure that the benefits are consistently realized across various settings[14][17][18].

4 Current Applications of AI in Medical Imaging ​

4.1 Radiology ​

Artificial Intelligence (AI) has emerged as a transformative force in the field of medical imaging, particularly within radiology. Its applications are diverse and continue to evolve, enhancing various aspects of imaging workflows and diagnostic processes. AI's integration into radiology has the potential to optimize patient care, improve diagnostic accuracy, and streamline operational efficiency.

One of the primary applications of AI in radiology is in the interpretation of medical images. AI algorithms, particularly those utilizing deep learning and radiomics, can analyze vast amounts of imaging data to detect and characterize diseases. For instance, AI systems can automatically segment and register images of the liver and pancreatic glands, aiding in the identification of focal lesions and diffuse diseases such as neoplasms and chronic conditions [20]. The capacity of AI to generate accurate and reproducible imaging diagnoses reduces the workload for physicians and enhances the consistency of results [20].

AI also plays a significant role in non-interpretive tasks within radiology. It assists with workflow management, patient scheduling, and image quality control, thereby allowing radiologists to focus more on complex interpretive tasks. By optimizing these processes, AI can enhance the overall efficiency of radiological services [21]. Additionally, AI can integrate with electronic health record systems to standardize follow-up recommendations and improve the quality of radiology reports [21].

Moreover, AI's applications extend to emergency radiology, where it helps identify common conditions more rapidly, ensuring timely patient care. This is particularly crucial in emergency departments, where speed and accuracy are paramount [22]. AI can prioritize workflow, enabling radiologists to address urgent cases more effectively [22].

The technology also shows promise in augmenting diagnostic capabilities through the use of advanced imaging techniques. For example, AI can enhance MRI-based cortical bone imaging and assist in the generation of high-quality images through deep learning reconstruction [23]. Furthermore, AI can provide quantitative assessments that were previously unattainable, offering insights into disease characterization and prognostication [4].

Despite the significant advancements, the integration of AI in radiology is not without challenges. Issues such as data privacy, algorithm generalizability, and the need for regulatory frameworks remain critical hurdles [21]. The AI landscape in radiology is still developing, with many applications currently theoretical or limited to specific institutions [21].

In conclusion, AI is reshaping the practice of radiology by enhancing diagnostic accuracy, improving workflow efficiency, and enabling more effective patient management. As the technology continues to evolve, it holds the promise of further revolutionizing medical imaging and providing better healthcare outcomes.

4.2 Pathology ​

Artificial intelligence (AI) is significantly transforming the field of medical imaging, particularly in pathology, where it enhances diagnostic accuracy and workflow efficiency. The application of AI in pathology leverages advanced algorithms and machine learning techniques to analyze complex data derived from histopathological images. Current applications of AI in this domain encompass several critical areas.

One of the primary applications of AI in pathology is the analysis of histological images for tumor identification, classification, and prognosis prediction. AI algorithms, particularly deep learning models, have shown remarkable capabilities in detecting and classifying tumors with high precision. For instance, studies have indicated that AI can assist pathologists in identifying potentially negligible lesions, such as small metastatic tumor cells in lymph nodes, and accurately diagnosing histological findings that may be controversial, like well-differentiated carcinomas that mimic normal tissues[24].

Moreover, AI is being utilized to predict genetic alterations and treatment responses directly from routine pathology slides. A survey conducted among computational pathology experts highlighted that the prediction of treatment response is regarded as one of the most promising future applications of AI in this field[25]. This capability is critical for precision oncology, as it allows for tailored treatment plans based on individual tumor characteristics.

In addition to diagnostic tasks, AI is also being integrated into workflows to enhance efficiency. For example, the use of AI algorithms in counting tumor cells has been shown to improve accuracy and reduce the tedious nature of manual assessments. This not only aids in more reliable diagnoses but also alleviates the workload on pathologists, who often face increasing demands and time constraints[26].

However, the integration of AI into clinical practice is not without challenges. The lack of sufficient annotated data for training AI systems, the explainability of AI models, and the difficulty in defining ground truth data for validation are significant barriers that need to be addressed. The concept of "black box" AI, where the decision-making process of the algorithm is not transparent, poses additional risks in a clinical setting where understanding the rationale behind a diagnosis is crucial[6].

Despite these challenges, the potential of AI in pathology is vast. Research has demonstrated that AI can improve diagnostic speed and accuracy, as seen in pilot studies where the sensitivity for detecting micrometastases improved significantly when pathologists used AI-assisted tools[27]. As the field continues to evolve, further studies are necessary to validate these findings and establish standardized protocols for the safe and effective implementation of AI in pathology.

In summary, AI is making substantial contributions to medical imaging in pathology by enhancing diagnostic capabilities, improving workflow efficiency, and facilitating precision medicine. Continued research and development are essential to overcome existing challenges and fully realize the benefits of AI in this critical area of healthcare.

4.3 Cardiology ​

Artificial intelligence (AI) is significantly transforming medical imaging in cardiology by enhancing diagnostic accuracy, improving workflow efficiency, and facilitating better patient outcomes. The applications of AI in this field are diverse and continue to evolve rapidly.

One of the primary applications of AI in cardiology is in the analysis of cardiovascular images. Recent advancements in deep learning have enabled AI to achieve human-level performance in various imaging tasks. For instance, AI algorithms have been developed for automated measurements, image segmentation, and risk prediction related to coronary atherosclerotic plaques. These algorithms assist in identifying plaque properties, detecting vulnerable plaques, and evaluating myocardial function, thereby supporting clinical decision-making processes [28].

In echocardiography, AI tools are employed to improve clinical workflows by assisting with image reconstruction, patient triage, and repetitive clinical tasks. These tools enhance the quality of echocardiographic images and help cardiologists in diagnosing cardiovascular diseases more effectively [29]. Moreover, AI has the potential to augment the cardiologist's visual clinical workflow by generating synthetic images that replicate and sometimes exceed the quality of traditionally acquired images. This capability is particularly useful in intravascular imaging, where AI can improve the interpretability and completeness of the images [11].

AI applications extend to wearable devices and electrocardiograms (ECGs), where machine learning models analyze vast amounts of data to detect conditions such as reduced ejection fraction and valvular heart disease with unprecedented accuracy [30]. These AI models not only facilitate early diagnosis but also assist in monitoring patient health and predicting cardiovascular events [31].

Furthermore, AI enhances the workflow in cardiac computed tomography (CCTA) by automating data analysis and processing, thereby streamlining patient scheduling, result notification, and report generation [31]. The integration of AI in CCTA has led to significant improvements in the speed and accuracy of image acquisition and analysis, enabling better clinical outcomes [32].

Despite the promising advancements, the integration of AI in cardiology is still in its early stages, and several challenges remain. Issues such as model understanding, bias, and ethical considerations regarding patient data security and decision-making processes must be addressed to ensure the safe and effective implementation of AI technologies in clinical practice [33].

In conclusion, AI is poised to revolutionize medical imaging in cardiology by providing tools that enhance diagnostic capabilities, improve patient care, and optimize clinical workflows. As research continues to expand, it is crucial to establish rigorous validation processes to ensure that AI applications meet the high standards required for clinical use [34].

5 Challenges and Ethical Considerations ​

5.1 Data Privacy and Security ​

Artificial intelligence (AI) significantly enhances medical imaging by automating and improving various tasks, yet it also presents challenges and ethical considerations, particularly regarding data privacy and security.

AI's applications in medical imaging include automating image segmentation, feature extraction, and risk prediction, which collectively lead to improved diagnostic precision and efficiency. Generative AI techniques have shown potential in tasks such as data augmentation, image synthesis, and radiology report generation, facilitating enhanced medical imaging capabilities [1]. Moreover, AI algorithms can learn to recognize imaging features without relying on expert knowledge, thus advancing personalized medicine through the analysis of large quantities of medical data [35].

However, the integration of AI into medical imaging raises significant ethical and legal concerns. The development and deployment of AI systems necessitate careful consideration of privacy, data quality, and model efficacy. Ethical risks identified in the context of AI in medical imaging include the privacy of data subjects, the potential for biased outcomes affecting marginalized populations, and the transparency of clinical performance [36]. The need for robust ethical frameworks is underscored by the requirement to ensure that AI-driven solutions do not compromise patient safety or privacy.

Data privacy is particularly critical in the context of medical imaging, as images and associated data are sensitive. The collection and use of such data require comprehensive de-identification processes to protect patient confidentiality [37]. As AI models rely on large and diverse datasets for training, the challenge lies in balancing the need for comprehensive data with the ethical obligation to safeguard individual privacy. Synthetic data generated by AI can augment existing datasets while addressing privacy concerns, yet this approach also presents challenges in ensuring the realism and diversity of the synthesized images [38].

Furthermore, the growing reliance on AI systems introduces cybersecurity concerns, as breaches in patient data privacy could have far-reaching implications. The increasing complexity of AI technologies necessitates the establishment of updated regulations and best practices to govern their ethical use [39]. The collaborative efforts of regulatory bodies, clinicians, and AI developers are essential to create frameworks that address these ethical dilemmas and promote the responsible implementation of AI in medical imaging.

In summary, while AI enhances the capabilities of medical imaging and offers substantial benefits in diagnosis and treatment, it also presents challenges that must be addressed to ensure patient safety and data security. The ethical implications surrounding data privacy and the potential for bias require careful consideration and proactive measures to mitigate risks associated with AI in this rapidly evolving field.

5.2 Bias and Fairness in AI Algorithms ​

Artificial intelligence (AI) plays a transformative role in medical imaging, significantly enhancing diagnostic capabilities, optimizing workflows, and improving patient care. The application of AI in this field leverages advanced technologies such as machine learning, neural networks, and natural language processing to increase the efficiency and accuracy of medical imaging tasks. AI systems can assist in data augmentation, image synthesis, image-to-image translation, and even the generation of radiology reports, thus facilitating more precise diagnoses and treatment plans [1].

However, the integration of AI in medical imaging is not without its challenges and ethical considerations. A primary concern is the issue of bias within AI algorithms. Bias can arise from non-representative datasets that fail to encompass the diversity of patient populations, leading to disparities in diagnostic accuracy and treatment outcomes. This is particularly critical as biased AI systems may exacerbate existing inequities in healthcare delivery, affecting marginalized groups disproportionately [40]. The algorithms may inadvertently learn and perpetuate these biases if they are trained on data that does not accurately reflect the broader population [41].

Furthermore, the "black-box problem" associated with many AI models raises significant ethical concerns regarding transparency and accountability. Many AI systems operate in ways that are not easily interpretable by clinicians, which can hinder trust in their recommendations and outputs. The lack of transparency complicates the ability of healthcare providers to understand and justify AI-driven decisions, particularly when patient safety is at stake [42].

To address these challenges, it is essential to adopt strategies that promote fairness and mitigate bias in AI algorithms. This includes the development of diverse and representative datasets, which are crucial for training equitable AI systems. Implementing fairness-aware algorithms and regulatory frameworks can also help ensure that AI applications do not reinforce existing disparities in healthcare delivery [40]. Continuous ethical scrutiny and collaboration among AI developers, clinicians, and ethicists are necessary to create responsible AI implementations that prioritize patient-centered care and equitable outcomes [41].

In summary, while AI holds great potential to enhance medical imaging and improve patient outcomes, addressing the ethical challenges of bias and fairness is crucial for its successful integration into clinical practice. The establishment of comprehensive frameworks and best practices will be vital in ensuring that AI technologies serve all populations equitably, thereby enhancing both their clinical value and the trustworthiness of AI systems among patients and healthcare professionals [43].

5.3 Regulatory and Legal Issues ​

Artificial intelligence (AI) is playing a transformative role in medical imaging, significantly enhancing diagnostic capabilities and operational efficiencies. AI applications in this field include data augmentation, image synthesis, image-to-image translation, and the generation of radiology reports. These advancements facilitate improved accuracy in diagnosis and treatment, while also streamlining workflows within healthcare settings. However, the integration of AI into medical imaging is accompanied by a host of challenges and ethical considerations, particularly concerning regulatory and legal issues.

One of the primary challenges associated with AI in medical imaging is the need for large and diverse datasets for training AI models. Due to privacy and ethical concerns, as well as barriers related to data sharing, assembling such datasets can be difficult. Synthetic medical imaging data generated by AI from existing datasets could mitigate this issue by augmenting and anonymizing real imaging data. This approach not only addresses data scarcity but also opens new avenues for applications, such as modality translation and professional training for radiologists [38].

Despite these advantages, the use of synthetic data raises significant technical and ethical challenges. Key concerns include ensuring the realism and diversity of synthesized images while maintaining patient anonymity, as well as evaluating the performance and generalizability of models trained on synthetic data. Moreover, the high computational costs associated with generating and processing synthetic data can be prohibitive [38]. As existing regulations may not sufficiently address the safe and ethical use of synthetic images, there is a pressing need for updated laws and rigorous oversight. Collaboration among regulatory bodies, physicians, and AI developers is essential to establish and refine best practices for the utilization of synthetic data [38].

Legal and ethical considerations are further complicated by the inherent opacity of certain AI systems, often referred to as the "black box problem." This lack of transparency can lead to difficulties in accountability and liability, particularly when AI-generated outputs are not easily interpretable by healthcare professionals. In cases where AI systems produce errors, the assignment of responsibility becomes contentious, raising questions about the extent to which developers and healthcare providers share liability [44].

Furthermore, the ethical implications of AI in medical imaging extend to issues of bias, which can exacerbate disparities in healthcare delivery. Ensuring that AI systems are fair and equitable necessitates the implementation of rigorous validation frameworks to monitor performance across diverse populations [45]. As AI technologies continue to evolve, the importance of establishing clear guidelines and regulatory frameworks becomes increasingly critical to promote safe and effective integration into clinical practice [46].

In summary, while AI holds great promise for enhancing medical imaging, its integration is fraught with challenges that require careful consideration of ethical, regulatory, and legal issues. Addressing these concerns is vital to ensure that the benefits of AI are realized in a manner that prioritizes patient safety and equity in healthcare delivery. Collaborative efforts among stakeholders are essential to navigate the complexities of AI in medical imaging and to establish a framework that supports responsible innovation.

6 Future Directions and Research Opportunities ​

6.1 Innovations in AI Technologies ​

Artificial intelligence (AI) significantly enhances medical imaging through various applications, innovations, and future research opportunities. AI's integration into medical imaging is transforming the landscape of healthcare, improving diagnostic accuracy, patient care, and the overall efficiency of medical processes.

AI assists in medical imaging primarily by enabling the quantification and synthesis of previously qualitative imaging characteristics. This capability facilitates the identification of novel disease-specific biomarkers, aids in patient risk stratification, prognostication, and adverse event prediction. AI-driven image analysis captures changes in imaging "phenotype" over time, thereby optimizing treatment plans based on real-time analysis. The application of AI in this context is not only beneficial for diagnostics but also plays a crucial role in staging and response assessment, which is essential for effective patient management [12].

The advancements in generative AI have also shown great potential in enhancing medical imaging tasks. These include data augmentation, image synthesis, image-to-image translation, and the generation of radiology reports. Such capabilities can significantly improve the quality and interpretability of medical images, thereby aiding clinicians in making more informed decisions [1]. Furthermore, the emergence of machine learning methodologies has enabled algorithms to become integral to clinical care. They enhance image reconstruction, detect cancer, and predict individual risks, which support treatment decisions and patient management [47].

Innovations in AI technologies, such as deep learning algorithms, convolutional neural networks, and generative adversarial networks, have drastically improved the accuracy and efficiency of medical image analysis. These technologies enable rapid and precise detection of abnormalities, from identifying tumors in radiological examinations to detecting early signs of diseases in retinal images [8]. The role of AI extends beyond diagnostics; it facilitates personalized treatment plans, optimizing healthcare delivery and ultimately improving patient outcomes.

Looking forward, the integration of AI into medical imaging presents numerous research opportunities. Future directions may involve the development of more sophisticated AI models that combine imaging data with other modalities, such as genomics, to enhance understanding of biological processes underlying diseases. Additionally, there is a need for ongoing research into the ethical considerations and challenges posed by AI in medical imaging, ensuring that advancements are made responsibly and equitably [1].

In summary, AI is reshaping medical imaging by enhancing diagnostic capabilities, improving patient care, and offering innovative solutions that address current challenges in healthcare. The continuous evolution of AI technologies will further propel advancements in medical imaging, ultimately leading to more efficient and effective healthcare systems.

6.2 Integration of AI with Other Technologies ​

Artificial intelligence (AI) plays a transformative role in medical imaging by enhancing various processes such as diagnostics, treatment planning, and patient care. Its integration into clinical workflows and research methodologies is rapidly evolving, presenting numerous future directions and research opportunities.

AI assists in medical imaging through advanced image analysis techniques that significantly improve the accuracy and efficiency of image interpretation. For instance, AI-driven image analysis allows for the quantification and synthesis of imaging characteristics, which facilitates the identification of novel disease-specific biomarkers, risk stratification, prognostication, and prediction of adverse events [12]. This capability not only enhances diagnostic accuracy but also aids in tailoring treatment plans based on real-time analysis of imaging phenotypes over time [12].

The current landscape indicates a robust application of AI across various imaging modalities, such as radiology, pathology, and cardiology. Intelligent imaging technology demonstrates high accuracy, sensitivity, and specificity, thereby improving clinical diagnostics and enhancing the overall quality of healthcare services [48]. For example, deep learning algorithms and convolutional neural networks have been pivotal in enhancing medical image analysis, contributing to improved detection of abnormalities and enabling faster interpretation of complex images [8].

Future directions for AI in medical imaging include further integration with other technologies, such as generative adversarial networks (GANs) and large language models (LLMs). These technologies can augment the visual clinical workflow by generating synthetic medical images that replicate and enhance the quality of traditionally acquired images [11]. This capability not only addresses challenges related to image quality and interpretability but also facilitates more comprehensive clinical decision-making [11].

Moreover, AI's role in optimizing diagnostic processes through techniques such as data augmentation and image synthesis highlights the potential for AI to reshape clinical workflows [1]. The integration of AI with emerging technologies can lead to innovative solutions that enhance the diagnostic capabilities of medical imaging systems, ultimately contributing to better patient outcomes.

As the field continues to evolve, there is a pressing need for research that focuses on the reproducibility and generalizability of AI applications in medical imaging. Investigating the clinical utility of AI approaches using large datasets will be essential to validate findings and ensure their applicability across diverse clinical settings [49]. Additionally, addressing ethical considerations and potential challenges in the deployment of AI technologies in healthcare will be crucial for fostering trust and acceptance among medical professionals and patients alike [1].

In summary, AI significantly enhances medical imaging by improving diagnostic accuracy and efficiency, and its integration with other technologies promises to further revolutionize the field. Future research opportunities should focus on validating AI applications, exploring ethical implications, and ensuring that these advancements lead to improved patient care and clinical outcomes.

6.3 Enhancing Clinical Decision-Making ​

Artificial intelligence (AI) plays a transformative role in medical imaging by enhancing clinical decision-making through various methodologies and applications. The integration of AI technologies into medical imaging workflows is aimed at improving image quality, accuracy, and interpretability, thereby facilitating better patient outcomes.

AI enhances clinical decision-making primarily through its ability to analyze and interpret vast amounts of imaging data. For instance, in cardiology, AI is employed to synthesize enhanced clinical images that augment the cardiologist's visual workflow. A digital health platform utilizing a conditional generative adversarial network was developed to generate synthetic optical coherence tomography and intravascular ultrasound images based on specified plaque morphology. This approach allows for rapid generation of images that not only replicate the style of normally acquired images but also exceed them in content and function, thus improving image quality and interpretability [11].

In spinal imaging, AI contributes significantly by automating analysis and improving diagnostic accuracy. It enhances image quality through techniques such as denoising and artifact reduction. Moreover, AI facilitates the efficient quantification of anatomical measurements and the detection of key spinal pathologies, achieving expert-level performance in identifying conditions such as fractures and tumors. These advancements empower clinicians to make more informed treatment decisions based on reliable diagnostic information [50].

AI's capabilities extend to drug discovery as well, where it assists in identifying novel disease-specific biomarkers and predicting treatment outcomes. By quantifying and synthesizing previously qualitative imaging characteristics, AI aids in patient risk stratification and optimizing treatment plans. This integration of AI into drug discovery pipelines accelerates the identification and development of new pharmaceuticals, ultimately enhancing therapeutic strategies [12].

Additionally, AI applications in medical imaging can improve the detection of high-risk characteristics in various diseases, enabling a more precise and efficient clinical decision-making process. For example, AI algorithms can analyze imaging data to uncover detailed pathological information, linking macroscopic imaging characteristics with microscopic molecular changes [2].

The future directions for AI in medical imaging suggest an ongoing emphasis on improving model interpretability and generalizability, addressing current limitations, and enhancing the integration of imaging data with other modalities such as genomics. The successful implementation of AI in clinical settings will depend on overcoming barriers to adoption, including the need for multicenter collaborations that utilize large, diverse datasets to validate AI models [12][50].

In summary, AI significantly enhances clinical decision-making in medical imaging by improving image quality, automating analysis, facilitating accurate diagnoses, and aiding in treatment planning. As research continues to advance, AI is poised to revolutionize medical imaging workflows, providing clinicians with actionable insights that ultimately lead to improved patient care.

7 Conclusion ​

The integration of artificial intelligence (AI) into medical imaging is transforming the landscape of healthcare by enhancing diagnostic accuracy, optimizing workflows, and improving patient outcomes. Key findings indicate that AI technologies, particularly deep learning and machine learning, are significantly improving image acquisition, analysis, and interpretation across various medical specialties, including radiology, pathology, and cardiology. These advancements enable quicker detection of abnormalities, facilitate personalized treatment plans, and streamline clinical processes. However, the integration of AI is accompanied by challenges such as data privacy concerns, algorithmic bias, and the need for robust regulatory frameworks. Future research should focus on developing equitable AI systems, enhancing model interpretability, and ensuring that the benefits of AI are realized across diverse patient populations. The ongoing evolution of AI technologies holds great promise for further revolutionizing medical imaging, ultimately leading to improved healthcare delivery and patient care.

References ​

  • [1] Mohamad Koohi-Moghadam;Kyongtae Ty Bae. Generative AI in Medical Imaging: Applications, Challenges, and Ethics.. Journal of medical systems(IF=5.7). 2023. PMID:37651022. DOI: 10.1007/s10916-023-01987-4.
  • [2] Chong Zhang;Jionghui Gu;Yangyang Zhu;Zheling Meng;Tong Tong;Dongyang Li;Zhenyu Liu;Yang Du;Kun Wang;Jie Tian. AI in spotting high-risk characteristics of medical imaging and molecular pathology.. Precision clinical medicine(IF=5.0). 2021. PMID:35692858. DOI: 10.1093/pcmedi/pbab026.
  • [3] Divya Tripathi;Kasturee Hajra;Aditya Mulukutla;Romi Shreshtha;Dipak Maity. Artificial Intelligence in Biomedical Engineering and Its Influence on Healthcare Structure: Current and Future Prospects.. Bioengineering (Basel, Switzerland)(IF=3.7). 2025. PMID:40001682. DOI: 10.3390/bioengineering12020163.
  • [4] Taha M Ahmed;Satomi Kawamoto;Ralph H Hruban;Elliot K Fishman;Philippe Soyer;Linda C Chu. A primer on artificial intelligence in pancreatic imaging.. Diagnostic and interventional imaging(IF=8.1). 2023. PMID:36967355. DOI: 10.1016/j.diii.2023.03.002.
  • [5] Alexandra Derevianko;Silvia Francesca Maria Pizzoli;Filippo Pesapane;Anna Rotili;Dario Monzani;Roberto Grasso;Enrico Cassano;Gabriella Pravettoni. The Use of Artificial Intelligence (AI) in the Radiology Field: What Is the State of Doctor-Patient Communication in Cancer Diagnosis?. Cancers(IF=4.4). 2023. PMID:36672417. DOI: 10.3390/cancers15020470.
  • [6] Markus Plass;Michaela Kargl;Tim-Rasmus Kiehl;Peter Regitnig;Christian Geißler;Theodore Evans;Norman Zerbe;Rita Carvalho;Andreas Holzinger;Heimo Müller. Explainability and causability in digital pathology.. The journal of pathology. Clinical research(IF=3.7). 2023. PMID:37045794. DOI: 10.1002/cjp2.322.
  • [7] Thomas Beyer;Luc Bidaut;John Dickson;Marc Kachelriess;Fabian Kiessling;Rainer Leitgeb;Jingfei Ma;Lalith Kumar Shiyam Sundar;Benjamin Theek;Osama Mawlawi. What scans we will read: imaging instrumentation trends in clinical oncology.. Cancer imaging : the official publication of the International Cancer Imaging Society(IF=3.5). 2020. PMID:32517801. DOI: 10.1186/s40644-020-00312-3.
  • [8] Luís Pinto-Coelho. How Artificial Intelligence Is Shaping Medical Imaging Technology: A Survey of Innovations and Applications.. Bioengineering (Basel, Switzerland)(IF=3.7). 2023. PMID:38136026. DOI: 10.3390/bioengineering10121435.
  • [9] Greg Zaharchuk;Guido Davidzon. Artificial Intelligence for Optimization and Interpretation of PET/CT and PET/MR Images.. Seminars in nuclear medicine(IF=5.9). 2021. PMID:33509370. DOI: 10.1053/j.semnuclmed.2020.10.001.
  • [10] Robert J H Miller;Panithaya Chareonthaitawee;Piotr J Slomka. Artificial intelligence in nuclear cardiology: Enhancing diagnostic accuracy and efficiency.. Progress in cardiovascular diseases(IF=7.6). 2025. PMID:41038418. DOI: 10.1016/j.pcad.2025.09.010.
  • [11] Max L Olender;José M de la Torre Hernández;Lambros S Athanasiou;Farhad R Nezami;Elazer R Edelman. Artificial intelligence to generate medical images: augmenting the cardiologist's visual clinical workflow.. European heart journal. Digital health(IF=4.4). 2021. PMID:36713593. DOI: 10.1093/ehjdh/ztab052.
  • [12] Harrison J Howell;Jeremy P McGale;Aurélie Choucair;Dorsa Shirini;Nicolas Aide;Michael A Postow;Lucy Wang;Mickael Tordjman;Egesta Lopci;Augustin Lecler;Stéphane Champiat;Delphine L Chen;Désirée Deandreis;Laurent Dercle. Artificial Intelligence for Drug Discovery: An Update and Future Prospects.. Seminars in nuclear medicine(IF=5.9). 2025. PMID:39966029. DOI: 10.1053/j.semnuclmed.2025.01.004.
  • [13] Daniele Giansanti. Joint Expedition: Exploring Clinical Medical Imaging and Artificial Intelligence as a Team Integration.. Diagnostics (Basel, Switzerland)(IF=3.3). 2024. PMID:38535005. DOI: 10.3390/diagnostics14060584.
  • [14] Robert J H Miller;Piotr J Slomka. Artificial Intelligence in Nuclear Cardiology: An Update and Future Trends.. Seminars in nuclear medicine(IF=5.9). 2024. PMID:38521708. DOI: 10.1053/j.semnuclmed.2024.02.005.
  • [15] Ahmed Hosny;Chintan Parmar;John Quackenbush;Lawrence H Schwartz;Hugo J W L Aerts. Artificial intelligence in radiology.. Nature reviews. Cancer(IF=66.8). 2018. PMID:29777175. DOI: 10.1038/s41568-018-0016-5.
  • [16] Natalia Gorelik;Soterios Gyftopoulos. Applications of Artificial Intelligence in Musculoskeletal Imaging: From the Request to the Report.. Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes(IF=3.7). 2021. PMID:32809857. DOI: 10.1177/0846537120947148.
  • [17] Katharina Wenderott;Jim Krups;Fiona Zaruchas;Matthias Weigl. Effects of artificial intelligence implementation on efficiency in medical imaging-a systematic literature review and meta-analysis.. NPJ digital medicine(IF=15.1). 2024. PMID:39349815. DOI: 10.1038/s41746-024-01248-9.
  • [18] Zehui Gu;Siddhant Dogra;Mutita Siriruchatanon;Jerard Kneifati-Hayek;Stella K Kang. Radiology Workflow Assistance With Artificial Intelligence: Establishing the Link to Outcomes.. Journal of the American College of Radiology : JACR(IF=5.1). 2025. PMID:41106573. DOI: 10.1016/j.jacr.2025.10.018.
  • [19] Jeffrey Liu;Bino Varghese;Farzaneh Taravat;Liesl S Eibschutz;Ali Gholamrezanezhad. An Extra Set of Intelligent Eyes: Application of Artificial Intelligence in Imaging of Abdominopelvic Pathologies in Emergency Radiology.. Diagnostics (Basel, Switzerland)(IF=3.3). 2022. PMID:35741161. DOI: 10.3390/diagnostics12061351.
  • [20] M Alvaro Berbís;Felix Paulano Godino;Javier Royuela Del Val;Lidia Alcalá Mata;Antonio Luna. Clinical impact of artificial intelligence-based solutions on imaging of the pancreas and liver.. World journal of gastroenterology(IF=5.4). 2023. PMID:36998424. DOI: 10.3748/wjg.v29.i9.1427.
  • [21] Neena Kapoor;Ronilda Lacson;Ramin Khorasani. Workflow Applications of Artificial Intelligence in Radiology and an Overview of Available Tools.. Journal of the American College of Radiology : JACR(IF=5.1). 2020. PMID:33153540. DOI: 10.1016/j.jacr.2020.08.016.
  • [22] Benjamin D Katzman;Christian B van der Pol;Philippe Soyer;Michael N Patlas. Artificial intelligence in emergency radiology: A review of applications and possibilities.. Diagnostic and interventional imaging(IF=8.1). 2023. PMID:35933269. DOI: 10.1016/j.diii.2022.07.005.
  • [23] Taiki Nozaki;Masahiro Hashimoto;Daiju Ueda;Shohei Fujita;Yasutaka Fushimi;Koji Kamagata;Yusuke Matsui;Rintaro Ito;Takahiro Tsuboyama;Fuminari Tatsugami;Noriyuki Fujima;Kenji Hirata;Masahiro Yanagawa;Akira Yamada;Tomoyuki Fujioka;Mariko Kawamura;Takeshi Nakaura;Shinji Naganawa. Recent topics in musculoskeletal imaging focused on clinical applications of AI: How should radiologists approach and use AI?. La Radiologia medica(IF=4.8). 2025. PMID:39992330. DOI: 10.1007/s11547-024-01947-z.
  • [24] Sangjoon Choi;Seokhwi Kim. Artificial Intelligence in the Pathology of Gastric Cancer.. Journal of gastric cancer(IF=3.8). 2023. PMID:37553129. DOI: 10.5230/jgc.2023.23.e25.
  • [25] Céline N Heinz;Amelie Echle;Sebastian Foersch;Andrey Bychkov;Jakob Nikolas Kather. The future of artificial intelligence in digital pathology - results of a survey across stakeholder groups.. Histopathology(IF=4.1). 2022. PMID:35373378. DOI: 10.1111/his.14659.
  • [26] Taro Sakamoto;Tomoi Furukawa;Kris Lami;Hoa Hoang Ngoc Pham;Wataru Uegami;Kishio Kuroda;Masataka Kawai;Hidenori Sakanashi;Lee Alex Donald Cooper;Andrey Bychkov;Junya Fukuoka. A narrative review of digital pathology and artificial intelligence: focusing on lung cancer.. Translational lung cancer research(IF=3.5). 2020. PMID:33209648. DOI: 10.21037/tlcr-20-591.
  • [27] Sebastian Försch;Frederick Klauschen;Peter Hufnagl;Wilfried Roth. Artificial Intelligence in Pathology.. Deutsches Arzteblatt international(IF=7.1). 2021. PMID:34024323. DOI: .
  • [28] Jia Zhang;Ruijuan Han;Guo Shao;Bin Lv;Kai Sun. Artificial Intelligence in Cardiovascular Atherosclerosis Imaging.. Journal of personalized medicine(IF=3.0). 2022. PMID:35330420. DOI: 10.3390/jpm12030420.
  • [29] Kenya Kusunose. Radiomics in Echocardiography: Deep Learning and Echocardiographic Analysis.. Current cardiology reports(IF=3.3). 2020. PMID:32648059. DOI: 10.1007/s11886-020-01348-4.
  • [30] Pierre Elias;Sneha S Jain;Timothy Poterucha;Michael Randazzo;Francisco Lopez Jimenez;Rohan Khera;Marco Perez;David Ouyang;James Pirruccello;Michael Salerno;Andrew J Einstein;Robert Avram;Geoffrey H Tison;Girish Nadkarni;Vivek Natarajan;Emma Pierson;Ashley Beecy;Deepa Kumaraiah;Chris Haggerty;Jennifer N Avari Silva;Thomas M Maddox. Artificial Intelligence for Cardiovascular Care-Part 1: Advances: JACC Review Topic of the Week.. Journal of the American College of Cardiology(IF=22.3). 2024. PMID:38593946. DOI: 10.1016/j.jacc.2024.03.400.
  • [31] Afolasayo A Aromiwura;Tyler Settle;Muhammad Umer;Jonathan Joshi;Matthew Shotwell;Jishanth Mattumpuram;Mounica Vorla;Maryta Sztukowska;Sohail Contractor;Amir Amini;Dinesh K Kalra. Artificial intelligence in cardiac computed tomography.. Progress in cardiovascular diseases(IF=7.6). 2023. PMID:37689230. DOI: 10.1016/j.pcad.2023.09.001.
  • [32] Ludovica R M Lanzafame;Giuseppe M Bucolo;Giuseppe Muscogiuri;Sandro Sironi;Michele Gaeta;Giorgio Ascenti;Christian Booz;Thomas J Vogl;Alfredo Blandino;Silvio Mazziotti;Tommaso D'Angelo. Artificial Intelligence in Cardiovascular CT and MR Imaging.. Life (Basel, Switzerland)(IF=3.4). 2023. PMID:36836864. DOI: 10.3390/life13020507.
  • [33] Alexandrina Danilov;Wilbert S Aronow. Artificial Intelligence in Cardiology: Applications and Obstacles.. Current problems in cardiology(IF=3.3). 2023. PMID:37088174. DOI: 10.1016/j.cpcardiol.2023.101750.
  • [34] Elena Stamate;Alin-Ionut Piraianu;Oana Roxana Ciobotaru;Rodica Crassas;Oana Duca;Ana Fulga;Ionica Grigore;Vlad Vintila;Iuliu Fulga;Octavian Catalin Ciobotaru. Revolutionizing Cardiology through Artificial Intelligence-Big Data from Proactive Prevention to Precise Diagnostics and Cutting-Edge Treatment-A Comprehensive Review of the Past 5 Years.. Diagnostics (Basel, Switzerland)(IF=3.3). 2024. PMID:38893630. DOI: 10.3390/diagnostics14111103.
  • [35] Jacob L Jaremko;Marleine Azar;Rebecca Bromwich;Andrea Lum;Li Hsia Alicia Cheong;Martin Gibert;François Laviolette;Bruce Gray;Caroline Reinhold;Mark Cicero;Jaron Chong;James Shaw;Frank J Rybicki;Casey Hurrell;Emil Lee;An Tang; . Canadian Association of Radiologists White Paper on Ethical and Legal Issues Related to Artificial Intelligence in Radiology.. Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes(IF=3.7). 2019. PMID:30962048. DOI: 10.1016/j.carj.2019.03.001.
  • [36] Jonathan Herington;Melissa D McCradden;Kathleen Creel;Ronald Boellaard;Elizabeth C Jones;Abhinav K Jha;Arman Rahmim;Peter J H Scott;John J Sunderland;Richard L Wahl;Sven Zuehlsdorff;Babak Saboury. Ethical Considerations for Artificial Intelligence in Medical Imaging: Data Collection, Development, and Evaluation.. Journal of nuclear medicine : official publication, Society of Nuclear Medicine(IF=9.1). 2023. PMID:37827839. DOI: 10.2967/jnumed.123.266080.
  • [37] Haridimos Kondylakis;Rocio Catalan;Sara Martinez Alabart;Caroline Barelle;Paschalis Bizopoulos;Maciej Bobowicz;Jonathan Bona;Dimitrios I Fotiadis;Teresa Garcia;Ignacio Gomez;Ana Jimenez-Pastor;Giannis Karatzanis;Karim Lekadir;Magdalena Kogut-Czarkowska;Antonios Lalas;Kostas Marias;Luis Marti-Bonmati;Jose Munuera;Katerina Nikiforaki;Manon Pelissier;Fred Prior;Michael Rutherford;Laure Saint-Aubert;Zisis Sakellariou;Karine Seymour;Thomas Trouillard;Konstantinos Votis;Manolis Tsiknakis. Documenting the de-identification process of clinical and imaging data for AI for health imaging projects.. Insights into imaging(IF=4.5). 2024. PMID:38816658. DOI: 10.1186/s13244-024-01711-x.
  • [38] Lennart R Koetzier;Jie Wu;Domenico Mastrodicasa;Aline Lutz;Matthew Chung;W Adam Koszek;Jayanth Pratap;Akshay S Chaudhari;Pranav Rajpurkar;Matthew P Lungren;Martin J Willemink. Generating Synthetic Data for Medical Imaging.. Radiology(IF=15.2). 2024. PMID:39254456. DOI: 10.1148/radiol.232471.
  • [39] Ayesha Saadat;Tasmiyah Siddiqui;Shafaq Taseen;Sanila Mughal. Revolutionising Impacts of Artificial Intelligence on Health Care System and Its Related Medical In-Transparencies.. Annals of biomedical engineering(IF=5.4). 2024. PMID:37548817. DOI: 10.1007/s10439-023-03343-6.
  • [40] Sribala Vidyadhari Chinta;Zichong Wang;Avash Palikhe;Xingyu Zhang;Ayesha Kashif;Monique Antoinette Smith;Jun Liu;Wenbin Zhang. AI-driven healthcare: Fairness in AI healthcare: A survey.. PLOS digital health(IF=7.7). 2025. PMID:40392801. DOI: 10.1371/journal.pdig.0000864.
  • [41] Ellison B Weiner;Irene Dankwa-Mullan;William A Nelson;Saeed Hassanpour. Ethical challenges and evolving strategies in the integration of artificial intelligence into clinical practice.. PLOS digital health(IF=7.7). 2025. PMID:40198594. DOI: 10.1371/journal.pdig.0000810.
  • [42] Maria Cristina Savastano;Clara Rizzo;Claudia Fossataro;Daniela Bacherini;Fabrizio Giansanti;Alfonso Savastano;Giovanni Arcuri;Stanislao Rizzo;Francesco Faraldi. Artificial intelligence in ophthalmology: Progress, challenges, and ethical implications.. Progress in retinal and eye research(IF=14.7). 2025. PMID:40473198. DOI: 10.1016/j.preteyeres.2025.101374.
  • [43] Debesh Jha;Gorkem Durak;Vanshali Sharma;Elif Keles;Vedat Cicek;Zheyuan Zhang;Abhishek Srivastava;Ashish Rauniyar;Desta Haileselassie Hagos;Nikhil Kumar Tomar;Frank H Miller;Ahmet Topcu;Anis Yazidi;Jan Erik Håkegård;Ulas Bagci. A Conceptual Framework for Applying Ethical Principles of AI to Medical Practice.. Bioengineering (Basel, Switzerland)(IF=3.7). 2025. PMID:40001699. DOI: 10.3390/bioengineering12020180.
  • [44] Michael Lang;Alexander Bernier;Bartha Maria Knoppers. Artificial Intelligence in Cardiovascular Imaging: "Unexplainable" Legal and Ethical Challenges?. The Canadian journal of cardiology(IF=5.3). 2022. PMID:34737036. DOI: 10.1016/j.cjca.2021.10.009.
  • [45] James P Howard;Qiang Zhang;Ahmed M Salih;Steffen E Petersen;Karim Lekadir;Zahra Raisi-Estabragh. Artificial intelligence in cardiovascular imaging: risks, mitigations and the path to safe implementation.. Heart (British Cardiac Society)(IF=4.4). 2025. PMID:40579214. DOI: 10.1136/heartjnl-2024-324612.
  • [46] Maria Teresa Contaldo;Giovanni Pasceri;Giacomo Vignati;Laura Bracchi;Sonia Triggiani;Gianpaolo Carrafiello. AI in Radiology: Navigating Medical Responsibility.. Diagnostics (Basel, Switzerland)(IF=3.3). 2024. PMID:39061643. DOI: 10.3390/diagnostics14141506.
  • [47] Georg Langs. Artificial intelligence in medical imaging is a tool for clinical routine and scientific discovery.. Seminars in arthritis and rheumatism(IF=4.4). 2024. PMID:38007360. DOI: 10.1016/j.semarthrit.2023.152321.
  • [48] Ke Fan;Lei Yang;Fei Ren;Xueyuan Zhang;Bo Liu;Ze Zhao;Jianwen Gu. Intelligent imaging technology applications in multidisciplinary hospitals.. Chinese medical journal(IF=7.3). 2024. PMID:39690448. DOI: 10.1097/CM9.0000000000003436.
  • [49] Fernando Cendes;Carrie R McDonald. Artificial Intelligence Applications in the Imaging of Epilepsy and Its Comorbidities: Present and Future.. Epilepsy currents(IF=6.3). 2022. PMID:35444507. DOI: 10.1177/15357597211068600.
  • [50] Sungwon Lee;Joon-Yong Jung;Akaworn Mahatthanatrakul;Jin-Sung Kim. Artificial Intelligence in Spinal Imaging and Patient Care: A Review of Recent Advances.. Neurospine(IF=3.6). 2024. PMID:38955525. DOI: 10.14245/ns.2448388.194.

MaltSci Intelligent Research Services ​

Search for more papers on MaltSci.com ​

Artificial Intelligence · Medical Imaging · Machine Learning · Deep Learning · Diagnostic Accuracy

© 2025 MaltSci