Application of Artificial Intelligence Technology in Radiotherapy to Delineate Endangered Organs

  • Miwan Hu
  • Longhui Yuan
Keywords: Artificial Intelligence; Machine Learning; Radiation Therapy; Endangers Organs


With the development of science and technology, artificial intelligence technology has been tried to be applied to all aspects of tumor radiotherapy, including respiratory motion prediction during simulated positioning, delineation of dangerous organs and tumor targets, and prediction of dose distribution. At present, clinical radiotherapy is mainly used in the automatic delineation of endangered organs, and artificial intelligence has demonstrated high accuracy in the delineation of dangerous organs, but there are also certain limitations. This article reviews the application and shortcomings of artificial systems in the automatic delineation of dangerous organs.


Crevier D. AI: The Tumultuous History of the Search for Artificial Intelligence[J]. science, 1993.

Wu Z, Pang Y, Wise Wise, et al. Application of artificial intelligence technology in automatic delineation of endangered organs by radiotherapy for nasopharyngeal carcinoma[J]. Journal of Practical Oncology, 2021, 35(02): 137-141.

Liang S, Tang F, Huang X, et al. Deep-learning-based detection and segmentation of organs at risk in nasopharyngeal carcinoma computed tomographic images for radiotherapy planning[J]. Eur Radiol, 2019, 29(4): 1961-1967.

Li JK, Wang PP, Cao YD, et al. Application of Accu Contour software in automatic delineation of head and neck hazardous organs[J]. China Medical Equipment, 2021, 36(06): 66-70.

Kang SW, Wu JX, Tang B, et al. Application of deep convolutional neural network in automatic delineation of small volume and dangerous organs of head and neck tumors[J]. Chinese Journal of Cancer Prevention and Treatment, 2022, 29(08): 571-577.

Zhang S. Safety and efficacy evaluation method of radiotherapy target contouring software[J]. Medical Equipment, 2018, 31(19): 51-54.

He YS, Jiang JL, Yu X, et al. Comparison of Dice coefficient and Hausdorff distance in image segmentation[J]. Chinese Journal of Medical Physics, 2019, 36(11): 1307-1311.

Wang P, Wang JP, Li X, et al. Feasibility of AI for automatic delineation of organs at risk in esophageal cancer[J]. Chinese Journal of Radiation Health, 2019, 28(06): 709-713.

Wang PP, Li JK, Li CH, et al. Application of artificial intelligence based on automatic delineation of dangerous organs in thoracic tumors[J]. Chinese Journal of Medical Physics, 2019, 36(11): 1346-1349.

Feng X, Qing K, Tustison NJ, et al. Deep convolutional neural network for segmentation of thoracic organs-at-risk using cropped 3D images[J]. Med Phys, 2019, 46(5): 2169-2180.

Wang LJ, Zhang SX, Lei HY, et al. Dosimetry of adaptive radiotherapy based on deformation registration dose accumulation[J]. China Medical Equipment, 2017, 32(07): 68-73.

Li Z, Hong WS, Hu LC. Study on the accuracy of three automatic delineation software applied to the delineation of attritional organs in the middle and upper abdomen[J]. China Medical Equipment, 2021, 36(03): 66-70.

Zhou FF, Wang YD, Song Y, et al. Pancreatic segmentation method for CT images based on 2.5D cascaded convolutional neural network[J]. Chinese Journal of Medical Physics, 2020, 37(06): 786-791.

Qin W, Zhuang JY, Shi FY, et al. Comparison of two gastric structures in patients with thoracic and abdominal tumors automatically outlined by AccuContour[J]. China Radiation Health, 2021, 30(03): 264-268.

Wang JY, Xu SP, Liu B, et al. Quantitative evaluation of the effect of Atlas template library case number on automatic delineation of cervical cancer-threatening organs[J]. Chinese Journal of Medical Physics, 2019, 36(07): 760-764.

Men K, Dai J, Li Y. Automatic segmentation of the clinical target volume and organs at risk in the planning CT for rectal cancer using deep dilated convolutional neural networks[J]. Medical physics, 2017, 44(12): 6377-6389.

Original Research Article