Patient-level grading prediction of prostate cancer from mp-MRI via GMINet

Magnetic resonance imaging (MRI) is considered the best imaging modality for non-invasive observation of prostate cancer. However, the existing quantitative analysis methods still have challenges in patient-level pre-diction, including accuracy, interpretability, context understanding, tumor delineation dependence, and multiple sequence fusion. Therefore, we propose a topological graph-guided multi-instance network (GMINet) to catch global contextual information of multi-parametric MRI for patient-level prediction. We integrate visual infor-mation from multi-slice MRI with slice-to-slice correlations for a more complete context. A novel strategy of attention folwing is proposed to fuse different MRI-based network branches for mp-MRI. Our method achieves state-of-the-art performance for Prostate cancer on a multi-center dataset (N = 478) and a public dataset (N = 204). The five-classification accuracy of Grade Group is 81.1 +/- 1.8% (multi-center dataset) from the test set of five-fold cross-validation, and the area under curve of detecting clinically significant prostate cancer is 0.801 +/- 0.018 (public dataset) from the test set of five-fold cross-validation respectively. The model also achieves tumor detection based on attention analysis, which improves the interpretability of the model. The novel method is hopeful to further improve the accurate prediction ability of MRI in the diagnosis and treatment of prostate cancer.

Automated summary

Magnetic resonance imaging (MRI) is the best imaging modality for non-invasive observation of prostate cancer. However, existing quantitative analysis methods face challenges in patient-level prediction. Therefore, a new method called GMINet is proposed to improve the accuracy and interpretability of MRI in prostate cancer diagnosis and treatment. The method achieves state-of-the-art performance and enables tumor detection through attention analysis.