MEGA Hub
New

A cross-modal generative model for incomplete and degraded prostate MRI with multicentre clinical validation

Published on Aug 17eess.IV

Authors

Do you know Siyuan Ma?You can claim authorship or link another user.Do you know Liang He?You can claim authorship or link another user.Do you know Mengying Zhu?You can claim authorship or link another user.Do you know Yi Chai?You can claim authorship or link another user.Do you know Mengyao Lyu?You can claim authorship or link another user.Do you know Haowei Wang?You can claim authorship or link another user.Do you know Qizhen Lan?You can claim authorship or link another user.Do you know HaoBo Sun?You can claim authorship or link another user.Do you know Qixin Zhang?You can claim authorship or link another user.Do you know Jingli Chen?You can claim authorship or link another user.Do you know Xiaobing Wei?You can claim authorship or link another user.Do you know Jiaming Liu?You can claim authorship or link another user.Do you know Guiqin Liu?You can claim authorship or link another user.Do you know Qianwen Zhang?You can claim authorship or link another user.Do you know Yang Liu?You can claim authorship or link another user.Do you know Dacheng Tao?You can claim authorship or link another user.Do you know Guangyu Wu?You can claim authorship or link another user.

Abstract

Missing or degraded sequences can limit prostate multiparametric MRI. We developed MSCNet, a sequence-conditioned cross-modal generative framework for reconstructing unavailable contrasts and restoring degraded acquisitions. Across ten completion tasks, task-specific MSCNet achieved mean structural similarity of 0.818 versus 0.798 for the strongest task-matched comparators; matched-capacity analyses showed larger differences in lesion fidelity and boundary preservation. In a blinded 1,000-case reader study, overall image quality met the prespecified non-inferiority criterion for DWI, ADC and T2W completion, but not T1W. In a separate 200-case diagnostic assessment, AUCs for clinically significant cancer were 0.860 with acquired images, 0.841 with MSCNet and 0.797 with baseline-generated images. A locked 186-case three-hospital cohort supported multicentre transportability. These retrospective results support quality-controlled cross-modal reconstruction as an adjunct to acquired prostate MRI.

Community

00