Cooperative multi-task learning and reliability assessment for glioma segmentation and IDH genotyping

Abstract

The high heterogeneity of gliomas presents significant challenges in distinguishing isocitrate dehydrogenase (IDH) genotypes based on magnetic resonance imaging (MRI) features. To address this issue, we propose a joint optimization framework based on multi-task learning (MLNet), which enables the simultaneous optimization of glioma segmentation and IDH genotype prediction within a unified framework. First, we design a glioma segmentation network based on a CNN-Transformer hybrid architecture to extract glioma features. Second, feature fusion is employed to provide feature support for the IDH genotyping task. A reliability assessment mechanism is introduced to evaluate the IDH genotyping results, determining whether a secondary assessment is necessary. Finally, we construct a multi-task learning loss function and achieve end-to-end joint training through feature sharing across tasks. We evaluate the proposed method on the BraTs2020 dataset, and comparisons with state-of-the-art methods demonstrate that the multi-task learning method offers superior performance.