Lesion Mask-based Simultaneous Synthesis of Anatomic and MolecularMR Images using a GAN
This addresses a data scarcity problem for neuro-oncology researchers and clinicians, enabling improved automatic diagnostic methods, though it is incremental as it builds on existing GAN techniques.
The paper tackles the lack of annotated MRI data for gliomas by proposing a GAN-based method that simultaneously synthesizes anatomic and molecular MR images from manipulated lesion masks, achieving significantly better performance than state-of-the-art synthesis methods.
Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas for patients with malignant gliomas in neuro-oncology with the help of conventional and advanced molecular MR images. However, the lack of sufficient annotated MRI data has vastly impeded the development of such automatic methods. Conventional data augmentation approaches, including flipping, scaling, rotation, and distortion are not capable of generating data with diverse image content. In this paper, we propose a method, called synthesis of anatomic and molecular MR images network (SAMR), which can simultaneously synthesize data from arbitrary manipulated lesion information on multiple anatomic and molecular MRI sequences, including T1-weighted (T1w), gadolinium enhanced T1w (Gd-T1w), T2-weighted (T2w), fluid-attenuated inversion recovery (FLAIR), and amide proton transfer-weighted (APTw). The proposed framework consists of a stretch-out up-sampling module, a brain atlas encoder, a segmentation consistency module, and multi-scale label-wise discriminators. Extensive experiments on real clinical data demonstrate that the proposed model can perform significantly better than the state-of-the-art synthesis methods.