Confidence-guided Lesion Mask-based Simultaneous Synthesis of Anatomic and Molecular MR Images in Patients with Post-treatment Malignant Gliomas
This work addresses data scarcity for neuro-oncology diagnostics, but it is incremental as it extends a previous method with confidence guidance and unsupervised training.
The authors tackled the problem of limited data quantity and quality for clinical diagnostic applications in neuro-oncology by proposing CG-SAMR, a method that synthesizes multi-modal anatomic and molecular MR images from lesion information, achieving better performance than state-of-the-art synthesis methods in experiments on real clinical data.
Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas in neuro-oncology, especially with the help of standard anatomic and advanced molecular MR images. However, data quantity and quality remain a key determinant of, and a significant limit on, the potential of such applications. In our previous work, we explored synthesis of anatomic and molecular MR image network (SAMR) in patients with post-treatment malignant glioms. Now, we extend it and propose Confidence Guided SAMR (CG-SAMR) that synthesizes data from lesion information to multi-modal anatomic sequences, including T1-weighted (T1w), gadolinium enhanced T1w (Gd-T1w), T2-weighted (T2w), and fluid-attenuated inversion recovery (FLAIR), and the molecular amide proton transfer-weighted (APTw) sequence. We introduce a module which guides the synthesis based on confidence measure about the intermediate results. Furthermore, we extend the proposed architecture for unsupervised synthesis so that unpaired data can be used for training the network. Extensive experiments on real clinical data demonstrate that the proposed model can perform better than the state-of-theart synthesis methods.