School of Integrated Circuits, Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, People's Republic of China.
Department of Radiation Oncology, Hubei Cancer Hospital, TongJi Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, People's Republic of China.
Phys Med Biol. 2024 Mar 6;69(6). doi: 10.1088/1361-6560/ad2a97.
Accurate delineation of organs-at-risk (OARs) is a critical step in radiotherapy. The deep learning generated segmentations usually need to be reviewed and corrected by oncologists manually, which is time-consuming and operator-dependent. Therefore, an automated quality assurance (QA) and adaptive optimization correction strategy was proposed to identify and optimize 'incorrect' auto-segmentations.A total of 586 CT images and labels from nine institutions were used. The OARs included the brainstem, parotid, and mandible. The deep learning generated contours were compared with the manual ground truth delineations. In this study, we proposed a novel contour quality assurance and adaptive optimization (CQA-AO) strategy, which consists of the following three main components: (1) the contour QA module classified the deep learning generated contours as either accepted or unaccepted; (2) the unacceptable contour categories analysis module provided the potential error reasons (five unacceptable category) and locations (attention heatmaps); (3) the adaptive correction of unacceptable contours module integrate vision-language representations and utilize convex optimization algorithms to achieve adaptive correction of 'incorrect' contours.. In the contour QA tasks, the sensitivity (accuracy, precision) of CQA-AO strategy reached 0.940 (0.945, 0.948), 0.962 (0.937, 0.913), and 0.967 (0.962, 0.957) for brainstem, parotid and mandible, respectively. The unacceptable contour category analysis, the(FI,AccI,Fmicro,Fmacro)of CQA-AO strategy reached (0.901, 0.763, 0.862, 0.822), (0.855, 0.737, 0.837, 0.784), and (0.907, 0.762, 0.858, 0.821) for brainstem, parotid and mandible, respectively. After adaptive optimization correction, the DSC values of brainstem, parotid and mandible have been improved by 9.4%, 25.9%, and 13.5%, and Hausdorff distance values decreased by 62%, 70.6%, and 81.6%, respectively.. The proposed CQA-AO strategy, which combines QA of contour and adaptive optimization correction for OARs contouring, demonstrated superior performance compare to conventional methods. This method can be implemented in the clinical contouring procedures and improve the efficiency of delineating and reviewing workflow.
器官危及器官（OARs）的精确勾画是放射治疗的关键步骤。深度学习生成的分割通常需要由肿瘤学家手动审查和修正，这既耗时又依赖于操作人员。因此，提出了一种自动化质量保证（QA）和自适应优化校正策略，以识别和优化“不正确”的自动分割。共使用了来自 9 个机构的 586 个 CT 图像和标签。OARs 包括脑干、腮腺和下颌骨。深度学习生成的轮廓与手动勾画的真实轮廓进行比较。在这项研究中，我们提出了一种新颖的轮廓质量保证和自适应优化（CQA-AO）策略，它由以下三个主要部分组成：（1）轮廓 QA 模块将深度学习生成的轮廓分类为接受或不接受；（2）不可接受的轮廓类别分析模块提供潜在的错误原因（五个不可接受类别）和位置（注意热图）；（3）不可接受轮廓的自适应修正模块集成视觉语言表示，并利用凸优化算法实现“不正确”轮廓的自适应修正。在轮廓 QA 任务中，CQA-AO 策略的灵敏度（准确度、精度）分别达到了 0.940（0.945，0.948）、0.962（0.937，0.913）和 0.967（0.962，0.957），用于脑干、腮腺和下颌骨。不可接受的轮廓类别分析，CQA-AO 策略的（FI、AccI、Fmicro、Fmacro）分别达到了（0.901、0.763、0.862、0.822）、（0.855、0.737、0.837、0.784）和（0.907、0.762、0.858、0.821），用于脑干、腮腺和下颌骨。自适应优化校正后，脑干、腮腺和下颌骨的 DSC 值分别提高了 9.4%、25.9%和 13.5%，Hausdorff 距离值分别降低了 62%、70.6%和 81.6%。提出的 CQA-AO 策略结合了 OAR 轮廓的 QA 和自适应优化校正，与传统方法相比表现出优越的性能。该方法可应用于临床轮廓绘制过程，提高勾画和审查工作流程的效率。
