Department of Radiation Oncology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academe of Medical Sciences & Peking Union Medical College, Beijing 100730, China.
Department of Radiation Oncology, Cangzhou Central Hospital, Cangzhou, Hebei 061001, China.
Cancer Radiother. 2024 Aug;28(4):354-364. doi: 10.1016/j.canrad.2024.03.002. Epub 2024 Aug 14.
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.
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.
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.
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.
本研究旨在设计一种基于卷积神经网络的自动勾画模型，用于生成图像引导自适应宫颈癌近距离放疗中的高危临床靶区和危及器官。
使用 98 例接受图像引导自适应近距离放疗的局部晚期宫颈癌患者的 CT 扫描对新型 SERes-u-net 进行训练和测试。采用 Dice 相似系数、95%Hausdorff 距离和临床评估进行评估。
我们的模型对高危临床靶区、膀胱、直肠、乙状结肠和肠袢的平均 Dice 相似系数分别为 80.8%、91.9%、85.2%、60.4%和 82.8%。相应的 95%Hausdorff 距离分别为 5.23mm、4.75mm、4.06mm、30.0mm 和 20.5mm。评估结果显示，99.3%的高危临床靶区切片由卷积神经网络生成，A 肿瘤医生认为可以接受，B 肿瘤医生认为 100%可以接受。大多数危及器官的分割在临床上是可以接受的，除了 25%的乙状结肠，A 肿瘤医生认为需要进行重大修改。两位肿瘤医生对卷积神经网络生成的高危临床靶区的临床评估存在显著差异（P<0.001），而两位肿瘤医生对危及器官的评分差异无统计学意义。在一致性评估中，高级和初级临床医生之间存在较大差异。大约 40%的 SERes-u-net 生成的轮廓被初级临床医生认为更好。
该研究提出的卷积神经网络模型生成的宫颈癌高危临床靶区和危及器官可以在临床上使用，有可能提高图像引导自适应近距离放疗工作流程中的勾画一致性和效率。
