CNN-Based Quality Assurance for Automatic Segmentation of Breast Cancer in Radiotherapy

• Published in: Frontiers in oncology Vol. 10; p. 524
• Main Authors: Chen, Xinyuan, Men, Kuo, Chen, Bo, Tang, Yu, Zhang, Tao, Wang, Shulian, Li, Yexiong, Dai, Jianrong
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 28.04.2020
• Subjects: automatic segmentation; convolutional neural networks; deep learning; Oncology; quality assurance; radiotherapy; radiotherapy; deep learning; convolutional neural networks; automatic segmentation; quality assurance
• ISSN: 2234-943X; 2234-943X
• DOI: 10.3389/fonc.2020.00524

More and more automatic segmentation tools are being introduced in routine clinical practice. However, physicians need to spend a considerable amount of time in examining the generated contours slice by slice. This greatly reduces the benefit of the tool's automaticity. In order to overcome this shortcoming, we developed an automatic quality assurance (QA) method for automatic segmentation using convolutional neural networks (CNNs). The study cohort comprised 680 patients with early-stage breast cancer who received whole breast radiation. The overall architecture of the automatic QA method for deep learning-based segmentation included the following two main parts: a segmentation CNN model and a QA network that was established based on ResNet-101. The inputs were from computed tomography, segmentation probability maps, and uncertainty maps. Two kinds of Dice similarity coefficient (DSC) outputs were tested. One predicted the DSC quality level of each slice ([0.95, 1] for "good," [0.8, 0.95] for "medium," and [0, 0.8] for "bad" quality), and the other predicted the DSC value of each slice directly. The performances of the method to predict the quality levels were evaluated with quantitative metrics: balanced accuracy, score, and the area under the receiving operator characteristic curve (AUC). The mean absolute error (MAE) was used to evaluate the DSC value outputs. The proposed methods involved two types of output, both of which achieved promising accuracy in terms of predicting the quality level. For the good, medium, and bad quality level prediction, the balanced accuracy was 0.97, 0.94, and 0.89, respectively; the score was 0.98, 0.91, and 0.81, respectively; and the AUC was 0.96, 0.93, and 0.88, respectively. For the DSC value prediction, the MAE was 0.06 ± 0.19. The prediction time was approximately 2 s per patient. Our method could predict the segmentation quality automatically. It can provide useful information for physicians regarding further verification and revision of automatic contours. The integration of our method into current automatic segmentation pipelines can improve the efficiency of radiotherapy contouring.