MaltSci 麦伴科研

Appearance

文献精选 > 高引权威"AI药物发现"文献

Artificial intelligence in cancer imaging: Clinical challenges and applications. ​

文献信息 ​

DOI10.3322/caac.21552
PMID30720861
期刊CA: a cancer journal for clinicians
影响因子232.4
JCR 分区Q1
发表年份2019
被引次数756
关键词人工智能、癌症影像学、临床挑战、深度学习、放射组学
文献类型Journal Article, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Review
ISSN0007-9235
页码127-157
期号69(2)
作者Wenya Linda Bi, Ahmed Hosny, Matthew B Schabath, Maryellen L Giger, Nicolai J Birkbak, Alireza Mehrtash, Tavis Allison, Omar Arnaout, Christopher Abbosh, Ian F Dunn, Raymond H Mak, Rulla M Tamimi, Clare M Tempany, Charles Swanton, Udo Hoffmann, Lawrence H Schwartz, Robert J Gillies, Raymond Y Huang, Hugo J W L Aerts

一句话小结 ​

本文回顾了人工智能在癌症医学影像中的应用现状，强调了其在提升疾病评估、肿瘤特征推断及临床决策中的潜力，尤其在肺癌、脑癌、乳腺癌和前列腺癌等四种肿瘤类型中展现的进展。尽管目前的研究尚缺乏严格的验证，但这些努力表明AI有望在未来癌症护理中发挥重要影响。

在麦伴科研 (maltsci.com) 搜索更多文献 ​

人工智能 · 癌症影像学 · 临床挑战 · 深度学习 · 放射组学

摘要 ​

判断是医学的核心原则之一，它依赖于多层次数据的整合与细致的决策过程。癌症为医学决策提供了独特的背景，不仅因为其多样化的形式及疾病的演变，还因为需要考虑患者的个体状况、接受治疗的能力及对治疗的反应。尽管技术有所改善，准确检测、表征和监测癌症仍然面临挑战。疾病的放射学评估最常依赖于视觉评估，其解释可以通过先进的计算分析得到增强。特别是，人工智能（AI）有望在专家临床医生对癌症影像的定性解读上取得重大进展，包括肿瘤的体积随时间变化的划定、从影像表型推断肿瘤基因型及生物过程、临床结果的预测，以及评估疾病和治疗对邻近器官的影响。AI可能会在图像初步解读过程中实现自动化，并将放射学检测的临床工作流程、是否进行干预的管理决策以及后续观察转变为一种尚未构想的新范式。本文作者回顾了AI在癌症医学影像中的当前应用状态，并描述了在四种肿瘤类型（肺癌、脑癌、乳腺癌和前列腺癌）中的进展，以说明如何解决常见的临床问题。尽管迄今为止大多数评估AI在肿瘤学应用的研究尚未经过严格的可重复性和普遍性验证，但研究结果确实突显了在推动AI技术临床应用和对未来癌症护理方向产生影响方面的日益协调的努力。

英文摘要 ​

Judgement, as one of the core tenets of medicine, relies upon the integration of multilayered data with nuanced decision making. Cancer offers a unique context for medical decisions given not only its variegated forms with evolution of disease but also the need to take into account the individual condition of patients, their ability to receive treatment, and their responses to treatment. Challenges remain in the accurate detection, characterization, and monitoring of cancers despite improved technologies. Radiographic assessment of disease most commonly relies upon visual evaluations, the interpretations of which may be augmented by advanced computational analyses. In particular, artificial intelligence (AI) promises to make great strides in the qualitative interpretation of cancer imaging by expert clinicians, including volumetric delineation of tumors over time, extrapolation of the tumor genotype and biological course from its radiographic phenotype, prediction of clinical outcome, and assessment of the impact of disease and treatment on adjacent organs. AI may automate processes in the initial interpretation of images and shift the clinical workflow of radiographic detection, management decisions on whether or not to administer an intervention, and subsequent observation to a yet to be envisioned paradigm. Here, the authors review the current state of AI as applied to medical imaging of cancer and describe advances in 4 tumor types (lung, brain, breast, and prostate) to illustrate how common clinical problems are being addressed. Although most studies evaluating AI applications in oncology to date have not been vigorously validated for reproducibility and generalizability, the results do highlight increasingly concerted efforts in pushing AI technology to clinical use and to impact future directions in cancer care.

麦伴智能科研服务 ​

智能阅读回答你对文献的任何问题，帮助理解文献中的复杂图表和公式
定位观点定位某个观点在文献中的蛛丝马迹
加入知识库完成数据提取，报告撰写等更多高级知识挖掘功能

主要研究问题 ​

  1. 在人工智能的应用中，如何确保其在不同癌症类型的影像学评估中具有足够的准确性和可靠性？
  2. 人工智能在肿瘤的体积划分和基因型推断方面有哪些具体的技术挑战？
  3. 在临床实践中，人工智能如何改变医生对癌症影像的解读流程？
  4. 针对不同患者的个体化治疗，人工智能如何帮助医生评估治疗对周围器官的影响？
  5. 目前有哪些成功的案例展示了人工智能在癌症影像学中的应用，特别是在肺癌、脑癌、乳腺癌和前列腺癌方面？

核心洞察 ​

研究背景和目的 ​

癌症的复杂性和多样性使得其早期检测、准确分类和监测治疗反应成为医学界的重大挑战。尽管技术进步带来了新的医学成像手段，但如何有效利用这些数据仍然是一个难题。本文旨在探讨人工智能（AI）在癌症成像中的应用，包括其在肺癌、脑癌、乳腺癌和前列腺癌等四种肿瘤类型中的潜在价值与挑战。

主要方法/材料/实验设计 ​

本研究回顾了AI在癌症成像中的应用现状，特别关注深度学习和放射组学（radiomics）技术。研究中提到的AI应用可以分为三个主要任务：肿瘤的检测、特征描述和监测。以下是研究的技术路线图：

Mermaid diagram

关键结果和发现 ​

  1. 检测：AI技术提高了肿瘤检测的敏感性和特异性，尤其是在低剂量CT和MRI成像中，CADe系统能够有效识别漏诊的癌症。
  2. 特征描述：通过放射组学，AI能够量化肿瘤的形状、大小和纹理等特征，这些信息对肿瘤的分类和预后评估至关重要。
  3. 监测：AI能够跟踪肿瘤随时间的变化，评估治疗反应，帮助医生做出更好的临床决策。

主要结论/意义/创新性 ​

AI在癌症成像中的应用展现了其在提升早期检测、优化治疗方案和监测疾病进展方面的巨大潜力。尽管目前大多数研究仍处于预临床阶段，但AI技术的不断进步有望在未来改变癌症护理的格局。

研究局限性和未来方向 ​

尽管AI在癌症成像中显示出良好的前景，但仍存在以下局限性：

  • 数据集的可用性和质量：缺乏标准化的、高质量的标注数据集限制了AI模型的训练和验证。
  • 可解释性：AI模型的“黑箱”特性使得其决策过程难以解释，这可能影响临床医生的信任和使用。
  • 伦理和法律问题：AI在医疗中的应用引发了伦理和法律上的担忧，需要建立相应的监管框架。

未来的研究应集中于数据集的构建、AI模型的可解释性以及在实际临床环境中的验证，以推动AI在癌症成像中的广泛应用。

参考文献 ​

  1. Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. - T W Freer;M J Ulissey - Radiology (2001)
  2. Computer aided detection of masses in mammograms as decision support. - N Karssemeijer;J D M Otten;H Rijken;R Holland - The British journal of radiology (2006)
  3. Reduced lung-cancer mortality with low-dose computed tomographic screening. - ;Denise R Aberle;Amanda M Adams;Christine D Berg;William C Black;Jonathan D Clapp;Richard M Fagerstrom;Ilana F Gareen;Constantine Gatsonis;Pamela M Marcus;JoRean D Sicks - The New England journal of medicine (2011)
  4. Machine Learning methods for Quantitative Radiomic Biomarkers. - Chintan Parmar;Patrick Grossmann;Johan Bussink;Philippe Lambin;Hugo J W L Aerts - Scientific reports (2015)
  5. Semi-automated brain tumor segmentation on multi-parametric MRI using regularized non-negative matrix factorization. - Nicolas Sauwen;Marjan Acou;Diana M Sima;Jelle Veraart;Frederik Maes;Uwe Himmelreich;Eric Achten;Sabine Van Huffel - BMC medical imaging (2017)
  6. Computer-aided diagnosis: how to move from the laboratory to the clinic. - Bram van Ginneken;Cornelia M Schaefer-Prokop;Mathias Prokop - Radiology (2011)
  7. A critical analysis of the tumor volume threshold for clinically insignificant prostate cancer using a data set of a randomized screening trial. - Tineke Wolters;Monique J Roobol;Pim J van Leeuwen;Roderick C N van den Bergh;Robert F Hoedemaeker;Geert J L H van Leenders;Fritz H Schröder;Theodorus H van der Kwast - The Journal of urology (2011)
  8. Radiogenomics of Glioblastoma: Machine Learning-based Classification of Molecular Characteristics by Using Multiparametric and Multiregional MR Imaging Features. - Philipp Kickingereder;David Bonekamp;Martha Nowosielski;Annekathrin Kratz;Martin Sill;Sina Burth;Antje Wick;Oliver Eidel;Heinz-Peter Schlemmer;Alexander Radbruch;Jürgen Debus;Christel Herold-Mende;Andreas Unterberg;David Jones;Stefan Pfister;Wolfgang Wick;Andreas von Deimling;Martin Bendszus;David Capper - Radiology (2016)
  9. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. - Varun Gulshan;Lily Peng;Marc Coram;Martin C Stumpe;Derek Wu;Arunachalam Narayanaswamy;Subhashini Venugopalan;Kasumi Widner;Tom Madams;Jorge Cuadros;Ramasamy Kim;Rajiv Raman;Philip C Nelson;Jessica L Mega;Dale R Webster - JAMA (2016)
  10. A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets. - Natalia Antropova;Benjamin Q Huynh;Maryellen L Giger - Medical physics (2017)

引用本文的文献 ​

  1. Open access image repositories: high-quality data to enable machine learning research. - F Prior;J Almeida;P Kathiravelu;T Kurc;K Smith;T J Fitzgerald;J Saltz - Clinical radiology (2020)
  2. An overview of GeoAI applications in health and healthcare. - Maged N Kamel Boulos;Guochao Peng;Trang VoPham - International journal of health geographics (2019)
  3. Integrating manual diagnosis into radiomics for reducing the false positive rate of 18F-FDG PET/CT diagnosis in patients with suspected lung cancer. - Fei Kang;Wei Mu;Jie Gong;Shengjun Wang;Guoquan Li;Guiyu Li;Wei Qin;Jie Tian;Jing Wang - European journal of nuclear medicine and molecular imaging (2019)
  4. Predicting progression of in situ carcinoma in the era of precision genomics. - Monica Cheng;Nasser H Hanna;Darrell D Davidson;Richard B Gunderman - Journal of thoracic disease (2019)
  5. Computed tomography-based predictive nomogram for differentiating primary progressive pulmonary tuberculosis from community-acquired pneumonia in children. - Bei Wang;Min Li;He Ma;Fangfang Han;Yan Wang;Shunying Zhao;Zhimin Liu;Tong Yu;Jie Tian;Di Dong;Yun Peng - BMC medical imaging (2019)
  6. Association of radiomic imaging features and gene expression profile as prognostic factors in pancreatic ductal adenocarcinoma. - Ke Li;Jingjing Xiao;Jiali Yang;Meng Li;Xuanqi Xiong;Yongjian Nian;Linbo Qiao;Huaizhi Wang;Aydin Eresen;Zhuoli Zhang;Xianling Hu;Jian Wang;Wei Chen - American journal of translational research (2019)
  7. Artificial Intelligence in the Management of Glioma: Era of Personalized Medicine. - Houman Sotoudeh;Omid Shafaat;Joshua D Bernstock;Michael David Brooks;Galal A Elsayed;Jason A Chen;Paul Szerip;Gustavo Chagoya;Florian Gessler;Ehsan Sotoudeh;Amir Shafaat;Gregory K Friedman - Frontiers in oncology (2019)
  8. Artificial Intelligence in Imaging: The Radiologist's Role. - Daniel L Rubin - Journal of the American College of Radiology : JACR (2019)
  9. Computed Tomography Radiomic Nomogram for Preoperative Prediction of Extrathyroidal Extension in Papillary Thyroid Carcinoma. - Bin Chen;Lianzhen Zhong;Di Dong;Jianjun Zheng;Mengjie Fang;Chunyao Yu;Qi Dai;Liwen Zhang;Jie Tian;Wei Lu;Yinhua Jin - Frontiers in oncology (2019)
  10. "Après Mois, Le Déluge": Preparing for the Coming Data Flood in the MRI-Guided Radiotherapy Era. - Kendall J Kiser;Benjamin D Smith;Jihong Wang;Clifton D Fuller - Frontiers in oncology (2019)

... (746 更多 篇文献)

© 2025 MaltSci 麦伴科研 - 我们用人工智能技术重塑科研