Self-supervised tumor segmentation and prognosis prediction in osteosarcoma using multiparametric MRI and clinical characteristics

• Published in: Computer methods and programs in biomedicine Vol. 244; p. 107974
• Main Authors: Zhou, Zhixun, Xie, Peng, Dai, Zhehao, Wu, Jia
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.02.2024
• Subjects: Multiparametric MRI; Osteosarcoma auxiliary diagnosis; Prognosis prediction; Segmentation; Self-supervised learning; Prognosis prediction; Segmentation; Osteosarcoma auxiliary diagnosis; Multiparametric MRI; Self-supervised learning
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2023.107974

•We propose a three-stage comprehensive auxiliary diagnostic solution for osteosarcoma, which first segments the tumor and then predicts prognosis based on tumor masks and clinical characteristics.•Prior to segmentation, our Multi-Parameter Fusion Comparative Learning (MPFCLR) algorithm uses unlabeled data to provide pre-trained weights for segmentation model with better performance and faster convergence.•We built a multi-parameter-based MPFNet segmentation model, which extracts local and fusion features of CE-T1WI and T2WI MR images. It has good performance in multi-region segmentation of osteosarcoma.•We build fusion nomograms based on segmentation masks and clinical characteristics (volume, tumor spread) to predict patient prognosis, which includes the patient's survival time and status. Osteosarcoma has a high mortality among malignant bone tumors. MRI-based tumor segmentation and prognosis prediction are helpful to assist doctors in detecting osteosarcoma, evaluating the patient's status, and improving patient survival. Current intelligent diagnostic approaches focus on segmentation with single-parameter MRI, which ignores the nature of MRI resulting in poor performance, and lacks the connection with prognosis prediction. Besides, osteosarcoma is a rare disease, and their few labeled data may lead to model overfitting. We propose a three-stage pipeline for segmentation and prognosis prediction of osteosarcoma to assist doctors in diagnosis. First, we propose the Multiparameter Fusion Contrast Learning (MPFCLR) algorithm to share pre-training weights for the segmentation model using unlabeled data. Then, we construct a multiparametric fusion network (MPFNet), which fuses the complementary features from multiparametric MRI (CE-T1WI, T2WI). It can automatically segment tumor and necrotic regions. Finally, a fusion nomogram is constructed by segmentation masks and clinical characteristics (volume, tumor spread) to predict the patient's prognostic status. Our experiments used data from 136 patients at the Second Xiangya Hospital in China. According to experiments, the MPFNet achieves 84.19 % mean DSC and 84.56 % mean F1-score in segmenting tumor and necrotic regions, surpassing existing models and single-parameter MRI input for osteosarcoma segmentation. Besides, MPFCLR improves the segmentation performance and convergence speed. In prognosis prediction, our fusion nomogram (C-index: 0.806, 95 %CI: 0.758-0.854) is better than radiomics (C-index: 0.753, 95 %CI: 0.685-0.841) and clinical (C-index: 0.794, 95 %CI: 0.735-0.854) nomograms in predictive performance. Compared to the comparison models, our model is closest to the prediction model based on physician annotations. Moreover, it can accurately distinguish the patients' prognostic status with good or poor. Our proposed solution can provide references for clinicians to detect osteosarcoma, evaluate patient status, and make personalized decisions. It can reduce delayed treatment or overtreatment and improve patient survival.