基于深度学习自动分割模型乳腺癌放疗临床应用与评价

doi:10.3760/cma.j.issn.1004-4221.2020.03.009

Abstract
Figure/Table
References(28)
Related Citation (15)
Read Tracking
Download Tracking

Download: PDF (0 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS) Supporting Info

Abstract Objective In this study,the deep learning algorithm and the commercial planning system were integrated to establish and validate an automatic segmentation platform for clinical target volume (CTV) and organs at risk (OARs) in breast cancer patients. Methods A total of 400 patients with left and right breast cancer receiving radiotherapy after breast-conserving surgery in Cancer Hospital CAMS were enrolled in this study. A deep residual convolutional neural network was used to train CTV and OARs segmentation models. An end-to-end deep learning-based automatic segmentation platform (DLAS) was established. The accuracy of the DLAS platform delineation was verified using 42 left breast cancer and 40 right breast cancer patients. The overall Dice Similarity Coefficient (DSC) and the average Hausdorff Distance (AHD) were calculated. The relationship between the relative layer position and the DSC value of each layer (DSC_s) was calculated and analyzed layer-by-layer. Results The mean overall DSC and AHD of global CTV in left/right breast cancer patients were 0.87/0.88 and 9.38/8.71 mm. The average overall DSC and AHD range for all OARs in left/right breast cancer patients were ranged from 0.86 to 0.97 and 0.89 to 9.38 mm. The layer-by-layer analysis of CTV and OARs reached 0.90 or above,indicating that the doctors were only required to make slight or no modification, and the DSC_s ≥ 0.9 of CTV automatic delineation accounted for approximately 44.7% of the layers. The automatic delineation range for OARs was 50.9%-89.6%. For DSC_s< 0.7,the DSC_s values of CTV and the regions of interest other than the spinal cord were significantly decreased in the boundary regions on both sides (layer positions 0-0.2,and 0.8-1.0),and the level of decrease toward the edge was more pronounced. The spinal cord was delineated in a full-scale manner,and no significant decrease in DSC_s was observed in a particular area.Conclusions The end-to-end automatic segmentation platform based on deep learning can integrate the breast cancer segmentation model and achieve excellent automatic segmentation effect. In the boundary areas on both sides of the superior and inferior directions,the consistency of the delineation decreases more obviously, which needs to be further improved.

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Chen Xinyuan
	Men Kuo
	Tang Yu
	Wang Shulian
	Dai Jianrong

Key words： Automatic segmentation Deep learning Breast neoplasm/radiotherapy

Received: 18 June 2019

Fund:Pharmaceutical Collaborative Scientific and Technological Innovation Research of Beijing Municipal Commission of Science and Technology (Z181100001918002);National Key Research& Development Program of the Ministry of Science and Technology (2017YFC0107500);Beijing Hope Marathon Special Fund of China Cancer Foundation (LC2018A14);National Natural Science Foundation (11605291,11475261)

Corresponding Authors: Dai Jianrong,Email:dai_jianrong@cicams.ac.cn;Wang Shulian,Email:wsl20040118@yahoo.com

Cite this article:

Chen Xinyuan,Men Kuo,Tang Yu et al. Clinical application and evaluation of automatic segmentation model based on deep learning for breast cancer radiotherapy[J]. Chinese Journal of Radiation Oncology, 2020, 29(3): 197-202.

URL:

http://journal12.magtechjournal.com/Jweb_fszlx/EN/10.3760/cma.j.issn.1004-4221.2020.03.009 OR http://journal12.magtechjournal.com/Jweb_fszlx/EN/Y2020/V29/I3/197

[1] Steenbakkers RJ,Duppen JC,Fitton I,et al. Observer variation in target volume delineation of lung cancer related to radiation oncologist-computer interaction:a′Big Brother′ evaluation[J]. Radiother Oncol,2005,77(2):182-190. DOI:10.1016/j.radonc.2005.09.017.
[2] BrouwerCL,Steenbakkers RJ,van den Heuvel E,et al.3D Variation in delineation of head and neck organs at risk[J]. Radiat Oncol,2012,7:32. DOI:10.1186/1748-717X-7-32.
[3] Qazi AA,Pekar V,Kim J,et al. Auto-segmentation of normal and target structures in head and neck CT images:a feature-driven model-based approach[J]. Med Phys,2011,38(11):6160-6170. DOI:10.1118/1.3654160.
[4] Vinod SK,Jameson MG,Min M,et al. Uncertainties in volume delineation in radiation oncology:A systematic review and recommendations for future studies[J]. Radiother Oncol,2016,121(2):169-179. DOI:10.1016/j.radonc.2016.09.009.
[5] Men K,Dai J and 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,2007,44(12):6377-6389. DOI:10.1002/mp.12602.
[6] Men K,Chen X,Zhang Y,et al. Deep Deconvolutional Neural Network for Target Segmentation of Nasopharyngeal Cancer in Planning Computed Tomography Images[J]. Front Oncol,2017,7:315. DOI:10.3389/fonc.2017.00315.
[7] Neylon J,Min Y,Low DA,et al. A neural network approach for fast,automated quantification of DIR performance[J]. Med Phys,2017,44(8):4126-4138. DOI:10.1002/mp.12321.
[8] Tseng HH,Luo Y,Cui S,et al. Deep reinforcement learning for automated radiation adaptation in lung cancer[J]. Med Phys,2017,44(12):6690-6705. DOI:10.1002/mp.12625.
[9] Han X. MR-based synthetic CT generation using a deep convolutional neural network method[J]. Med Phys,2017,44(4):1408-1419. DOI:10.1002/mp.12155.
[10] Zhen X,Chen J,Zhong Z,et al. Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy:a feasibility study[J]. Phys Med Biol,2017,62(21):8246-8263. DOI:10.1088/1361-6560/aa8d09.
[11] Ciardo D,Gerardi MA,Vigorito S,et al. Atlas-based segmentation in breast cancer radiotherapy:Evaluation of specific and generic-purpose atlases[J]. Breast,2017,32:44-52. DOI:10.1016/j.breast.2016.12.010.
[12] Velker VM,Rodrigues GB,Dinniwell R,et al. Creation of RTOG compliant patient CT-atlases for automated atlas based contouring of local regional breast and high-risk prostate cancers[J]. Radiat Oncol,2013,8:188. DOI:10.1186/1748-717X-8-188.
[13] Anders LC,Stieler F,Siebenlist K,et al. Performance of an atlas-based autosegmentation software for delineation of target volumes for radiotherapy of breast and anorectal cancer[J]. Radiother Oncol,2012,102(1):68-73. DOI:10.1016/j.radonc.2011.08.043.
[14] Ibragimov B and Xing L. Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks[J]. Med Phys,2017,44(2):547-557. DOI:10.1002/mp.12045.
[15] Hu P,Wu F,Peng J,et al. Automatic 3D liver segmentation based on deep learning and globally optimized surface evolution[J]. Phys Med Biol,2016,61(24):8676-8698. DOI:10.1088/1361-6560/61/24/8676.
[16] Men K,Dai J and 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.
[17] Men K,Zhang T,Chen X,et al. Fully automatic and robust segmentation of the clinical target volume for radiotherapy of breast cancer using big data and deep learning[J]. Phys Med,2018,50:13-19. DOI:10.1016/j.ejmp.2018.05.006.
[18] Lustberg T,van Soest J,Gooding M,et al. Clinical evaluation of atlas and deep learning based automatic contouring for lung cancer[J]. Radiother Oncol,2018,126(2):312-317. DOI:10.1016/j.radonc.2017.11.012.
[19] Jia Y, Shelhamer E, Donahue J, et al. Caffe convolutional architecture for fast feature embedding[C]. ACM, 2014:675-678.DOI:10.1145/2647868.2654889.
[20] Taha AA and Hanbury A. Metrics for evaluating 3D medical image segmentation:analysis,selection,and tool[J]. BMC Med Imaging,2015,15:29. DOI:10.1186/s12880-015-0068-x.
[21] Martinez F,Romero E,Drean G,et al. Segmentation of pelvic structures for planning CT using a geometrical shape model tuned by a multi-scale edge detector[J]. Phys Med Biol,2014,59(6):1471-1484. DOI:10.1088/0031-9155/59/6/1471.
[22] Hurkmans CW,Borger JH,Pieters BR,et al. Variability in target volume delineation on CT scans of the breast[J]. Int J Radiat Oncol Biol Phys,2001,50(5):1366-1372. DOI:10.1016/s0360-3016(01)01635-2.
[23] Batumalai V,Koh ES,Delaney GP,et al. Interobserver variability in clinical target volume delineation in tangential breast irradiation:a comparison between radiation oncologists and radiation therapists[J]. Clin Oncol (R Coll Radiol),2011,23(2):108-113. DOI:10.1016/j.clon.2010.10.004.
[24] Struikmans H,Warlam-Rodenhuis C,Stam T,et al. Interobserver variability of clinical target volume delineation of glandular breast tissue and of boost volume in tangential breast irradiation[J]. Radiother Oncol,2005,76(3):293-299. DOI:10.1016/j.radonc.2005.03.029.
[25] van der Leij F,Elkhuizen PH,Janssen TM,et al. Target volume delineation in external beam partial breast irradiation:less inter-observer variation with preoperative-compared to postoperative delineation[J]. Radiother Oncol,2014,110(3):467-470. DOI:10.1016/j.radonc.2013.10.033.
[26] Mast M,Coerkamp E,Heijenbrok M,et al. Target volume delineation in breast conserving radiotherapy:are co-registered CT and MR images of added value?[J]. Radiat Oncol,2014,9:65. DOI:10.1186/1748-717X-9-65.
[27] Zijdenbos AP,Dawant BM,Margolin RA,et al. Morphometric analysis of white matter lesions in MR images:Method and validation[J]. Medical Imaging IEEE Transactions on,1994,13(4):716-724. DOI:10.1109/42.363096.
[28] Vinod SK,Min M,Jameson MG,et al. A review of interventions to reduce inter-observer variability in volume delineation in radiation oncology[J]. J Med Imaging Radiat Oncol,2016,60(3):393-406. DOI:10.1111/1754-9485.12462.