Abstract：
OBJECTIVE: This study aimed to design an autodelineation model based on convolutional neural networks for generating high-risk clinical target volumes and organs at risk in image-guided adaptive brachytherapy for cervical cancer.
METHODS: A novel SERes-u-net was trained and tested using CT scans from 98 patients with locally advanced cervical cancer who underwent image-guided adaptive brachytherapy. The Dice similarity coefficient, 95th percentile Hausdorff distance, and clinical assessment were used for evaluation.
RESULTS: The mean Dice similarity coefficients of our model were 80.8%, 91.9%, 85.2%, 60.4%, and 82.8% for the high-risk clinical target volumes, bladder, rectum, sigmoid, and bowel loops, respectively. The corresponding 95th percentile Hausdorff distances were 5.23mm, 4.75mm, 4.06mm, 30.0mm, and 20.5mm. The evaluation results revealed that 99.3% of the convolutional neural networks-generated high-risk clinical target volumes slices were acceptable for oncologist A and 100% for oncologist B. Most segmentations of the organs at risk were clinically acceptable, except for the 25% sigmoid, which required significant revision in the opinion of oncologist A. There was a significant difference in the clinical evaluation of convolutional neural networks-generated high-risk clinical target volumes between the two oncologists (P<0.001), whereas the score differences of the organs at risk were not significant between the two oncologists. In the consistency evaluation, a large discrepancy was observed between senior and junior clinicians. About 40% of SERes-u-net-generated contours were thought to be better by junior clinicians.
CONCLUSIONS: The high-risk clinical target volumes and organs at risk of cervical cancer generated by the proposed convolutional neural networks model can be used clinically, potentially improving segmentation consistency and efficiency of contouring in image-guided adaptive brachytherapy workflow.
METHODS: A novel SERes-u-net was trained and tested using CT scans from 98 patients with locally advanced cervical cancer who underwent image-guided adaptive brachytherapy. The Dice similarity coefficient, 95th percentile Hausdorff distance, and clinical assessment were used for evaluation.
RESULTS: The mean Dice similarity coefficients of our model were 80.8%, 91.9%, 85.2%, 60.4%, and 82.8% for the high-risk clinical target volumes, bladder, rectum, sigmoid, and bowel loops, respectively. The corresponding 95th percentile Hausdorff distances were 5.23mm, 4.75mm, 4.06mm, 30.0mm, and 20.5mm. The evaluation results revealed that 99.3% of the convolutional neural networks-generated high-risk clinical target volumes slices were acceptable for oncologist A and 100% for oncologist B. Most segmentations of the organs at risk were clinically acceptable, except for the 25% sigmoid, which required significant revision in the opinion of oncologist A. There was a significant difference in the clinical evaluation of convolutional neural networks-generated high-risk clinical target volumes between the two oncologists (P<0.001), whereas the score differences of the organs at risk were not significant between the two oncologists. In the consistency evaluation, a large discrepancy was observed between senior and junior clinicians. About 40% of SERes-u-net-generated contours were thought to be better by junior clinicians.
CONCLUSIONS: The high-risk clinical target volumes and organs at risk of cervical cancer generated by the proposed convolutional neural networks model can be used clinically, potentially improving segmentation consistency and efficiency of contouring in image-guided adaptive brachytherapy workflow.
摘要：
目的：本研究旨在设计一种基于卷积神经网络的自动描绘模型，用于在图像引导的自适应近距离放射治疗中生成高风险的临床目标体积和风险器官。
方法：使用CT扫描对98例接受图像引导自适应近距离放射治疗的局部晚期宫颈癌患者进行了新的SERes-u-net训练和测试。骰子相似系数，95百分位数Hausdorff距离,和临床评估用于评估。
结果：我们模型的平均Dice相似系数为80.8%，91.9%,85.2%,60.4%,高风险临床目标量为82.8%，膀胱,直肠,乙状结肠,和肠循环，分别。对应的95百分位数Hausdorff距离为5.23mm，4.75mm,4.06mm,30.0mm,和20.5毫米。评估结果显示，99.3％的卷积神经网络生成的高风险临床目标体积切片对于肿瘤学家A是可接受的，对于肿瘤学家B是100％。除了25%的乙状结肠,这需要对肿瘤学家A的意见进行重大修订。两位肿瘤学家对卷积神经网络生成的高风险临床目标体积的临床评估存在显着差异（P<0.001），而两位肿瘤学家的危险器官评分差异不显著.在一致性评价中,观察到高级和初级临床医生之间存在很大差异。初级临床医生认为大约40％的SERes-u-net生成的轮廓更好。
结论：提出的卷积神经网络模型产生的宫颈癌高危临床靶区和器官可用于临床，潜在改善图像引导自适应近距离放射治疗工作流程中的分割一致性和轮廓效率。
方法：使用CT扫描对98例接受图像引导自适应近距离放射治疗的局部晚期宫颈癌患者进行了新的SERes-u-net训练和测试。骰子相似系数，95百分位数Hausdorff距离,和临床评估用于评估。
结果：我们模型的平均Dice相似系数为80.8%，91.9%,85.2%,60.4%,高风险临床目标量为82.8%，膀胱,直肠,乙状结肠,和肠循环，分别。对应的95百分位数Hausdorff距离为5.23mm，4.75mm,4.06mm,30.0mm,和20.5毫米。评估结果显示，99.3％的卷积神经网络生成的高风险临床目标体积切片对于肿瘤学家A是可接受的，对于肿瘤学家B是100％。除了25%的乙状结肠,这需要对肿瘤学家A的意见进行重大修订。两位肿瘤学家对卷积神经网络生成的高风险临床目标体积的临床评估存在显着差异（P<0.001），而两位肿瘤学家的危险器官评分差异不显著.在一致性评价中,观察到高级和初级临床医生之间存在很大差异。初级临床医生认为大约40％的SERes-u-net生成的轮廓更好。
结论：提出的卷积神经网络模型产生的宫颈癌高危临床靶区和器官可用于临床，潜在改善图像引导自适应近距离放射治疗工作流程中的分割一致性和轮廓效率。
