深度学习在医学影像和放射治疗中的应用。
Deep learning in medical imaging and radiation therapy.
机构信息
DIDSR/OSEL/CDRH U.S. Food and Drug Administration, Silver Spring, MD, 20993, USA.
Department of Radiology, University of Michigan, Ann Arbor, MI, 48109, USA.
出版信息
Med Phys. 2019 Jan;46(1):e1-e36. doi: 10.1002/mp.13264. Epub 2018 Nov 20.
Abstract
The goals of this review paper on deep learning (DL) in medical imaging and radiation therapy are to (a) summarize what has been achieved to date; (b) identify common and unique challenges, and strategies that researchers have taken to address these challenges; and (c) identify some of the promising avenues for the future both in terms of applications as well as technical innovations. We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.
摘要
本文综述了深度学习（DL）在医学影像和放射治疗中的应用，旨在：(a) 总结目前已取得的成果；(b) 确定共同和独特的挑战，以及研究人员为应对这些挑战所采取的策略；(c) 确定未来在应用和技术创新方面的一些有前途的方向。我们介绍了 DL 和卷积神经网络的一般原理，调查了 DL 在医学影像和放射治疗中的五个主要应用领域，确定了共同的主题，讨论了数据集扩展的方法，最后总结了经验教训、遗留的挑战和未来的方向。
相似文献
1
Deep learning in medical imaging and radiation therapy.深度学习在医学影像和放射治疗中的应用。
Med Phys. 2019 Jan;46(1):e1-e36. doi: 10.1002/mp.13264. Epub 2018 Nov 20.
2
Overview of image-to-image translation by use of deep neural networks: denoising, super-resolution, modality conversion, and reconstruction in medical imaging.利用深度神经网络进行图像到图像转换的概述：医学成像中的去噪、超分辨率、模态转换和重建。
Radiol Phys Technol. 2019 Sep;12(3):235-248. doi: 10.1007/s12194-019-00520-y. Epub 2019 Jun 20.
3
A gentle introduction to deep learning in medical image processing.深度学习在医学图像处理中的应用简介。
Z Med Phys. 2019 May;29(2):86-101. doi: 10.1016/j.zemedi.2018.12.003. Epub 2019 Jan 25.
4
Pathology Image Analysis Using Segmentation Deep Learning Algorithms.基于分割深度学习算法的病理学图像分析。
Am J Pathol. 2019 Sep;189(9):1686-1698. doi: 10.1016/j.ajpath.2019.05.007. Epub 2019 Jun 11.
5
Variability and reproducibility in deep learning for medical image segmentation.深度学习在医学图像分割中的可变性和可重复性。
Sci Rep. 2020 Aug 13;10(1):13724. doi: 10.1038/s41598-020-69920-0.
6
Deep computational pathology in breast cancer.深度学习在乳腺癌中的应用。
Semin Cancer Biol. 2021 Jul;72:226-237. doi: 10.1016/j.semcancer.2020.08.006. Epub 2020 Aug 17.
7
Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges.深度学习技术在医学图像分割中的应用：成就与挑战。
J Digit Imaging. 2019 Aug;32(4):582-596. doi: 10.1007/s10278-019-00227-x.
8
Deep Learning in Microscopy Image Analysis: A Survey.深度学习在显微镜图像分析中的应用：综述。
IEEE Trans Neural Netw Learn Syst. 2018 Oct;29(10):4550-4568. doi: 10.1109/TNNLS.2017.2766168. Epub 2017 Nov 22.
9
Deep Learning Approaches Towards Skin Lesion Segmentation and Classification from Dermoscopic Images - A Review.深度学习方法在皮肤镜图像的皮肤损伤分割和分类中的应用综述。
Curr Med Imaging. 2020;16(5):513-533. doi: 10.2174/1573405615666190129120449.
10
A Review Paper about Deep Learning for Medical Image Analysis.深度学习在医学图像分析中的应用综述
Comput Math Methods Med. 2023 May 29;2023:7091301. doi: 10.1155/2023/7091301. eCollection 2023.
引用本文的文献
1
New Insights into Automatic Treatment Planning for Cancer Radiotherapy Using Explainable Artificial Intelligence.利用可解释人工智能对癌症放射治疗自动治疗计划的新见解。
ArXiv. 2025 Aug 19:arXiv:2508.14229v1.
2
Combining curriculum learning and weakly supervised attention for enhanced thyroid nodule assessment in ultrasound imaging.结合课程学习和弱监督注意力以增强超声成像中的甲状腺结节评估
Quant Imaging Med Surg. 2025 Sep 1;15(9):8579-8593. doi: 10.21037/qims-24-2431. Epub 2025 Aug 18.
3
ReactorNet based on machine learning framework to identify control rod position for real time monitoring in PWRs.基于机器学习框架的反应堆网络，用于识别压水堆中控制棒位置以进行实时监测。
Sci Rep. 2025 Aug 18;15(1):30173. doi: 10.1038/s41598-025-13794-7.
4
Early prediction of proton therapy dose distributions and DVHs for hepatocellular carcinoma using contour-based CNN models from diagnostic CT and MRI.使用基于轮廓的卷积神经网络模型，根据诊断性CT和MRI对肝细胞癌质子治疗剂量分布和剂量体积直方图进行早期预测。
Radiat Oncol. 2025 Aug 4;20(1):122. doi: 10.1186/s13014-025-02708-6.
5
Application of deep learning models in gastric cancer pathology image analysis: a systematic scoping review.深度学习模型在胃癌病理图像分析中的应用：一项系统的范围综述。
BMC Cancer. 2025 Aug 1;25(1):1257. doi: 10.1186/s12885-025-14662-3.
6
Deep Learning Approaches for Automated Prediction of Treatment Response in Non-Small-Cell Lung Cancer Patients Based on CT and PET Imaging.基于CT和PET成像的非小细胞肺癌患者治疗反应自动预测的深度学习方法
Tomography. 2025 Jun 30;11(7):78. doi: 10.3390/tomography11070078.
7
Deep learning-based delineation of whole-body organs at risk empowering adaptive radiotherapy.基于深度学习的全身危及器官勾画助力自适应放疗。
BMC Med Inform Decis Mak. 2025 Jul 15;25(1):268. doi: 10.1186/s12911-025-03062-z.
8
Artificial Intelligence Detection and Segmentation Models: A Systematic Review and Meta-Analysis of Brain Tumors in Magnetic Resonance Imaging.人工智能检测与分割模型：磁共振成像中脑肿瘤的系统评价与荟萃分析
Mayo Clin Proc Digit Health. 2024 Feb 4;2(1):75-91. doi: 10.1016/j.mcpdig.2024.01.002. eCollection 2024 Mar.
9
A feasibility study of deep learning prediction model for VMAT patient-specific QA.容积调强放疗（VMAT）患者特异性质量保证的深度学习预测模型可行性研究。
Front Oncol. 2025 Mar 26;15:1509449. doi: 10.3389/fonc.2025.1509449. eCollection 2025.
10
NRG Oncology Assessment of Artificial Intelligence for Automatic Treatment Planning in Radiation Therapy Clinical Trials: Present and Future.NRG肿瘤学对人工智能在放射治疗临床试验自动治疗计划中的评估：现状与未来。
Int J Radiat Oncol Biol Phys. 2025 Mar 29. doi: 10.1016/j.ijrobp.2025.03.045.
本文引用的文献
1
Fine-tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally.用于生物医学图像分析的卷积神经网络微调：主动式与增量式
Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2017 Jul;2017:4761-4772. doi: 10.1109/CVPR.2017.506. Epub 2017 Nov 9.
2
Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks.使用基于形状表示模型约束的全卷积神经网络进行头颈部癌症放疗的全自动多器官分割。
Med Phys. 2018 Oct;45(10):4558-4567. doi: 10.1002/mp.13147. Epub 2018 Sep 19.
3
Deep Learning and Radiomics predict complete response after neo-adjuvant chemoradiation for locally advanced rectal cancer.深度学习和放射组学预测局部晚期直肠癌新辅助放化疗后完全缓解。
Sci Rep. 2018 Aug 22;8(1):12611. doi: 10.1038/s41598-018-30657-6.
4
Dose evaluation of fast synthetic-CT generation using a generative adversarial network for general pelvis MR-only radiotherapy.使用生成对抗网络进行快速合成 CT 生成的剂量评估，用于普通骨盆仅磁共振放疗。
Phys Med Biol. 2018 Sep 10;63(18):185001. doi: 10.1088/1361-6560/aada6d.
5
Cascaded atrous convolution and spatial pyramid pooling for more accurate tumor target segmentation for rectal cancer radiotherapy.级联空洞卷积和空间金字塔池化以提高直肠癌放疗中肿瘤靶区分割的准确性。
Phys Med Biol. 2018 Sep 17;63(18):185016. doi: 10.1088/1361-6560/aada6c.
6
Automated prediction of dosimetric eligibility of patients with prostate cancer undergoing intensity-modulated radiation therapy using a convolutional neural network.使用卷积神经网络对接受调强放射治疗的前列腺癌患者的剂量学适形性进行自动预测。
Radiol Phys Technol. 2018 Sep;11(3):320-327. doi: 10.1007/s12194-018-0472-3. Epub 2018 Aug 14.
7
Development of deep neural network for individualized hepatobiliary toxicity prediction after liver SBRT.用于肝 SBRT 后个体化肝胆毒性预测的深度神经网络的开发。
Med Phys. 2018 Oct;45(10):4763-4774. doi: 10.1002/mp.13122. Epub 2018 Sep 10.
8
A fully integrated computer-aided diagnosis system for digital X-ray mammograms via deep learning detection, segmentation, and classification.基于深度学习检测、分割和分类的全集成数字 X 射线乳腺计算机辅助诊断系统。
Int J Med Inform. 2018 Sep;117:44-54. doi: 10.1016/j.ijmedinf.2018.06.003. Epub 2018 Jun 18.
9
Medical Image Synthesis with Context-Aware Generative Adversarial Networks.基于上下文感知生成对抗网络的医学图像合成
Med Image Comput Comput Assist Interv. 2017 Sep;10435:417-425. doi: 10.1007/978-3-319-66179-7_48. Epub 2017 Sep 4.
10
Computer-Aided Diagnostic System for Early Detection of Acute Renal Transplant Rejection Using Diffusion-Weighted MRI.基于磁共振弥散加权成像的急性肾移植排斥反应早期诊断的计算机辅助诊断系统。
IEEE Trans Biomed Eng. 2019 Feb;66(2):539-552. doi: 10.1109/TBME.2018.2849987. Epub 2018 Jun 25.
Zotero 插件