Dong Chi, Wu Yujiao, Sun Bo, Bo Jiayi, Huang Yufei, Geng Yikang, Zhang Qianhui, Liu Ruixiang, Guo Wei, Wang Xingling, Jiang Xiran
Department of Biomedical Engineering, School of Intelligent Medicine, China Medical University, Liaoning 110122, China.
Department of Radiology, the First Affiliated Hospital of Dalian Medical University, Dalian, Liaoning, China.
Comput Med Imaging Graph. 2025 Jan;119:102477. doi: 10.1016/j.compmedimag.2024.102477. Epub 2024 Dec 8.
This study presents a novel framework that integrates contrastive learning and knowledge distillation to improve early ovarian cancer (OC) recurrence prediction, addressing the challenges posed by limited labeled data and tumor heterogeneity.
The research utilized CT imaging data from 585 OC patients, including 142 cases with complete follow-up information and 125 cases with unknown recurrence status. To pre-train the teacher network, 318 unlabeled images were sourced from public datasets (TCGA-OV and PLAGH-202-OC). Multi-view contrastive learning (MVCL) was employed to generate multi-view 2D tumor slices, enhancing the teacher network's ability to extract features from complex, heterogeneous tumors with high intra-class variability. Building on this foundation, the proposed semi-supervised multi-task self-distillation (Semi-MTSD) framework integrated OC subtyping as an auxiliary task using multi-task learning (MTL). This approach allowed the co-training of a student network for recurrence prediction, leveraging both labeled and unlabeled data to improve predictive performance in data-limited settings. The student network's performance was assessed using preoperative CT images with known recurrence outcomes. Evaluation metrics included area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity (SEN), specificity (SPE), F1 score, floating-point operations (FLOPs), parameter count, training time, inference time, and mean corruption error (mCE).
The proposed framework achieved an ACC of 0.862, an AUC of 0.916, a SPE of 0.895, and an F1 score of 0.831, surpassing existing methods for OC recurrence prediction. Comparative and ablation studies validated the model's robustness, particularly in scenarios characterized by data scarcity and tumor heterogeneity.
The MVCL and Semi-MTSD framework demonstrates significant advancements in OC recurrence prediction, showcasing strong generalization capabilities in complex, data-constrained environments. This approach offers a promising pathway toward more personalized treatment strategies for OC patients.
本研究提出了一种将对比学习和知识蒸馏相结合的新框架，以改善早期卵巢癌（OC）复发预测，应对有限标记数据和肿瘤异质性带来的挑战。
该研究利用了585例OC患者的CT成像数据，其中包括142例具有完整随访信息的病例和125例复发状态未知的病例。为了预训练教师网络，从公共数据集（TCGA-OV和PLAGH-202-OC）获取了318张未标记图像。采用多视图对比学习（MVCL）生成多视图二维肿瘤切片，增强教师网络从具有高类内变异性的复杂异质性肿瘤中提取特征的能力。在此基础上，提出的半监督多任务自蒸馏（Semi-MTSD）框架将OC亚型分类作为辅助任务，采用多任务学习（MTL）。这种方法允许共同训练用于复发预测的学生网络，利用标记和未标记数据来提高在数据有限情况下的预测性能。使用具有已知复发结果的术前CT图像评估学生网络的性能。评估指标包括受试者操作特征曲线下面积（AUC）、准确率（ACC）、灵敏度（SEN）、特异性（SPE）、F1分数、浮点运算次数（FLOPs）、参数数量、训练时间、推理时间和平均损坏误差（mCE）。
所提出的框架实现了0.862的ACC、0.916的AUC、0.895的SPE和0.831的F1分数，超过了现有的OC复发预测方法。比较和消融研究验证了该模型的稳健性，特别是在数据稀缺和肿瘤异质性特征的场景中。
MVCL和Semi-MTSD框架在OC复发预测方面取得了显著进展，在复杂的数据受限环境中展示了强大的泛化能力。这种方法为OC患者更个性化的治疗策略提供了一条有前景的途径。
