Contrastive learning and prior knowledge-induced feature extraction network for prediction of high-risk recurrence areas in Gliomas

Gliomas can easily recur even after standard treatments, and their recurrence may be related to insufficient radiation doses received by high-risk recurrence areas (HRA). Therefore, HRA prediction can help clinical experts in formulating effective radiotherapy plans. However, research on HRA prediction using early postoperative conventional MRI images with total resection is lacking. This gap is due to multifold challenges, including visually minimal differences between HRA and non-HRA and small dataset size caused by missing follow-up data. A contrastive learning and prior knowledge-induced feature extraction network (CLPKnet) to explore HRA-related features and achieve HRA prediction was proposed in this paper. First, a contrastive and multisequence learning-based encoder was proposed to effectively extract diverse features across multiple MRI sequences around the operative cavity. Specifically, a contrastive learning method was employed to pretrain the encoder, which enabled it to capture subtle differences between HRA and non-HRA regions while mitigating the challenges posed by the limited dataset size. Second, clinical prior knowledge was incorporated into the CLPKnet to guide the model in learning the patterns of glioma growth and improve its discriminative capability for identifying HRA regions. Third, a dual-focus fusion module was utilized to explore important sequential features and spatial regions and effectively fused multisequence features to provide complementary information associated with glioma recurrence. Fourth, to balance clinical needs and task difficulty, we used a patch-based prediction method to predict the recurrent probability. The CLPKnet was validated on a multicenter dataset from four hospitals, and a remarkable performance was achieved. Moreover, the interpretability and robustness of our method were evaluated to illustrate its effectiveness and credibility. Therefore, the CLPKnet displays a great application potential for HRA prediction. The codes will be available at https://github.com/Meiyan88/CLPKnet.