[an error occurred while processing this directive] | [an error occurred while processing this directive]
Automatic‐delineation model construction for prostate cancer target volume of postoperative radiotherapy based on artificial intelligence
Wang Fang1, Miao Dong2,3, Shen Yali1,4, Chen Zhebin2,3, Yao Yu2,3, Wang Xin1,4
1Department of Abdominal Oncology, Cancer Center, West China Hospital of Sichuan University, Chengdu 610041, China; 2Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610044, China; 3School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 101408, China; 4Department of Radiation Oncology, Cancer Center, West China Hospital of Sichuan University, Chengdu 610041, China
AbstractObjective To explore the method of constructing automatic delineation model for clinical target volume (CTV) and partially organs at risk (OAR) of postoperative radiotherapy for prostate cancer based on convolutional neural network, aiming to improve the clinical work efficiency and the unity of target area delineation. Methods Postoperative CT data of 117 prostate cancer patients manually delineated by one experienced clinician were retrospectively analyzed. A multi‐class auto‐delineation model was designed based on 3D UNet. Dice similarity coefficient (DSC), 95% Hausdorf distance (95%HD), and average surface distance (ASD) were used to evaluate the segmentation ability of the model. In addition, the segmentation results in the test set were evaluated by two senior physicians. And the CT data of 78 patients treated by other physicians were also collected for external validation of the model. The automatic segmentation of these 78 patients by CTV‐UNet model was also evaluated by two physicians. Results The mean DSC for tumor bed area (CTV1), pelvic lymph node drainage area (CTV2), bladder and rectum of CVT‐UNet auto‐segmentation model in the test set were 0.74, 0.82, 0.94 and 0.79, respectively. Both physicians' scoring results of the test set and the external validation showed more consensus on the delineation of CTV2 and OAR. However, the consensus of CTV1 delineation was less. Conclusions The automatic delineation model based on convolutional neural network is feasible for CTV and related OAR of postoperative radiotherapy for prostate cancer. The automatic segmentation ability of tumor bed area still needs to be improved.
Fund:Surface Project of National Natural Science Foundation of China (82073338); Sichuan Science and Technology Support Project (2021YFSY0039); The 1‐3‐5 Project for Disciplines of Excellence‐ Clinical Research Incubation Project, West China Hospital, Sichuan University (2020HXFH002); The 1‐3‐5 Project for Disciplines of Excellence, West China Hospital, Sichuan University (ZYJC21059)
Corresponding Authors:
Wang Xin, Email: wangxin213@sina.com
Cite this article:
Wang Fang,Miao Dong,Shen Yali et al. Automatic‐delineation model construction for prostate cancer target volume of postoperative radiotherapy based on artificial intelligence[J]. Chinese Journal of Radiation Oncology, 2023, 32(3): 222-228.
Wang Fang,Miao Dong,Shen Yali et al. Automatic‐delineation model construction for prostate cancer target volume of postoperative radiotherapy based on artificial intelligence[J]. Chinese Journal of Radiation Oncology, 2023, 32(3): 222-228.
[1] Hwee J, Louie AV, Gaede S, et al.Technology assessment of automated atlas based segmentation in prostate bed contouring[J]. Radiat Oncol, 2011,6:110. DOI: 10.1186/1748-717X-6-110. [2] Cardenas CE, Anderson BM, Aristophanous M, et al.Auto-delineation of oropharyngeal clinical target volumes using 3D convolutional neural networks[J]. Phys Med Biol, 2018,63(21):215026. DOI: 10.1088/1361-6560/aae8a9. [3] 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]. Med Phys, 2017,44(12):6377-6389. DOI: 10.1002/mp.12602. [4] Michalski JM, Lawton C, El Naqa I, et al.Development of RTOG consensus guidelines for the definition of the clinical target volume for postoperative conformal radiation therapy for prostate cancer[J]. Int J Radiat Oncol Biol Phys, 2010,76(2):361-368. DOI: 10.1016/j.ijrobp.2009.02.006. [5] Robin S, Jolicoeur M, Palumbo S, et al.Prostate bed delineation guidelines for postoperative radiation therapy: on behalf of the francophone group of urological radiation therapy[J]. Int J Radiat Oncol Biol Phys, 2021,109(5):1243-1253. DOI: 10.1016/j.ijrobp.2020.11.010. [6] Balagopal A, Nguyen D, Morgan H, et al.A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy[J]. Med Image Anal, 2021,72:102101. DOI: 10.1016/j.media.2021.102101. [7] Gay HA, Barthold HJ, O'Meara E, et al. Pelvic normal tissue contouring guidelines for radiation therapy: a radiation therapy oncology group consensus panel atlas[J]. Int J Radiat Oncol Biol Phys, 2012,83(3):e353-362. DOI: 10.1016/j.ijrobp.2012.01.023. [8] Çiçek Ö, Abdulkadir A, Lienkamp SS, et al.3D U‐net: learning dense volumetric segmentation from sparse annotation[C]// Ourselin S, Joskowicz L, Sabuncu M, et al. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016. Cham: Springer, 2016. [9] Hatamizadeh A, Tang YC, Nath V, et al. UNETR: transformers for 3D medical image segmentation[EB/OL]. (2021‐10-09)[2022-06-15]. https://arxiv.org/abs/2103.10504. [10] Balagopal A, Kazemifar S, Nguyen D, et al.Fully automated organ segmentation in male pelvic CT images[J]. Phys Med Biol, 2018,63(24):245015. DOI: 10.1088/1361-6560/aaf11c. [11] Zhang ZZ, Zhao TY, Gay H, et al.ARPM-net: a novel CNN-based adversarial method with Markov random field enhancement for prostate and organs at risk segmentation in pelvic CT images[J]. Med Phys, 2021,48(1):227-237. DOI: 10.1002/mp.14580. [12] Tao L, Ma L, Xie MQ, et al. Automatic segmentation of the prostate on MR images based on anatomy and deep learning[J]. Proc SPIE Int Soc Opt Eng, 2021,11598DOI: 10.1117/12.2581893. [13] Elguindi S, Zelefsky MJ, Jiang J, et al.Deep learning-based auto-segmentation of targets and organs-at-risk for magnetic resonance imaging only planning of prostate radiotherapy[J]. Phys Imaging Radiat Oncol, 2019,12:80-86. DOI: 10.1016/j.phro.2019.11.006. [14] Ayadi M, Delpon G, Lafay F, et al. Evaluation of abastm : multi‐center study in the case of prostate cancer[J]. Physica Medica, 2011,27:S14‐S15. DOI:10.1016/j.ejmp.2011.06.032. [15] Da-Ano R, Lucia F, Masson I, et al.A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets[J]. PLoS One, 2021,16(7):e0253653. DOI: 10.1371/journal.pone.0253653. [16] Balagopal A, Morgan H, Dohopolski M, et al.PSA-Net: deep learning-based physician style-aware segmentation network for postoperative prostate cancer clinical target volumes[J]. Artif Intell Med, 2021,121:102195. DOI: 10.1016/j.artmed.2021.102195.
2023, Vol. 32 
