Automatic delineation of the clinical target volume and organs at risk by deep learning for rectal cancer postoperative radiotherapy. (April 2020)

• Record Type: Journal Article
• Authors: Song, Ying; Hu, Junjie; Wu, Qiang; Xu, Feng; Nie, Shihong; Zhao, Yaqin; Bai, Sen; Yi, Zhang
• Is Part Of: Radiotherapy and oncology. Volume 145(2020)
• Page Start: 186
• Page End: 192
• Publication Date: 2020-04
• Subjects: CTV clinical target volume -- OARs organs at risk -- CNNs convolutional neural networks -- DDCNN deep dilated CNN -- IMRT Intensity modulated radiation therapy -- ASPP Atrous Spatial Pyramid Pooling -- IRF ischiorectal fossa; Automatic contouring -- CNNs -- CTV -- Rectal radiotherapy -- OAR; Oncology -- Periodicals; Radiotherapy -- Periodicals; Tumors -- Periodicals; Medical Oncology -- Periodicals; Neoplasms -- radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiothérapie -- Périodiques; Cancérologie -- Périodiques; Tumeurs -- Périodiques; Electronic journals; 616.9940642
• DOI: 10.1016/j.radonc.2020.01.020
• Languages: English
• ISSNs: 0167-8140

Abstract

Highlights: Automatic contouring quality can be quantitatively improved by convolutional neural networks at different feature resolution levels according to the contouring targets with different textures and volume characteristics. Our proposed convolutional neural networks had better contouring results with 1.1–13.4% higher volumetric Dice similarity coefficient and 1.2–10.0% higher surface Dice coefficient, and reduced the manual correction time to 7.29 min for rectal cancer CTV and 4 min for each OAR. Our proposed algorithms may be possible aided tools for clinical rectal cancer contouring practice. Abstract: Background and purpose: Manual delineation of clinical target volumes (CTVs) and organs at risk (OARs) is time-consuming, and automatic contouring tools lack clinical validation. We aimed to construct and validate the use of convolutional neural networks (CNNs) to set better contouring standards for rectal cancer radiotherapy. Materials and methods: We retrospectively collected and evaluated computed tomography (CT) scans of 199 rectal cancer patients treated at our hospital from February 2018 to April 2019. Two CNNs—DeepLabv3+ for extracting high-level semantic information and ResUNet for extracting low-level visual features—were used for the CTV and small intestine contouring, and bladder and femoral head contouring, respectively. Contouring quality was compared using the paired t test. Five-point objective grading was performed independently by two experienced radiation oncologists and verified by a third. The CNN manual correction time was recorded. Results: CTVs calculated using DeepLabv3+ (CTVDeepLabv3+ ) had significant quantitative parameter advantages over CTVResUNet (volumetric Dice coefficient, 0.88 vs 0.87, P = 0.0005; surface Dice coefficient, 0.79 vs 0.78, P = 0.008). Among 315 graded cases, DeepLabv3+ obtained the highest scores with 284 cases, consistent with the objective criteria, whereas CTVResUNet had the minimum mean manual correction time (7.29 min). DeepLabv3+ performed better than ResUNet for small intestine contouring and ResUNet performed better for bladder and femoral head contouring. The manual correction time for OARs was <4 min for both models. Conclusion: CNNs at various feature resolution levels well delineate rectal cancer CTVs and OARs, displaying high quality and requiring shorter computation and manual correction time.