ReCoSeg++:Extended Residual-Guided Cross-Modal Diffusion for Brain Tumor Segmentation

TL;DR

This paper introduces ReCoSeg++, a semi-supervised, two-stage framework that leverages residual-guided diffusion models and cross-modal synthesis to improve brain tumor segmentation accuracy on large, heterogeneous MRI datasets without relying on ground-truth masks.

Contribution

The paper extends the ReCoSeg approach with a residual-guided diffusion model and a two-stage segmentation process, enhancing scalability and accuracy on the BraTS 2021 dataset.

Findings

Achieved 93.02% Dice score on BraTS 2021 for whole tumor segmentation.

Outperformed previous ReCoSeg baseline on BraTS 2020.

Demonstrated improved scalability and robustness for multi-center MRI data.

Abstract

Accurate segmentation of brain tumors in MRI scans is critical for clinical diagnosis and treatment planning. We propose a semi-supervised, two-stage framework that extends the ReCoSeg approach to the larger and more heterogeneous BraTS 2021 dataset, while eliminating the need for ground-truth masks for the segmentation objective. In the first stage, a residual-guided denoising diffusion probabilistic model (DDPM) performs cross-modal synthesis by reconstructing the T1ce modality from FLAIR, T1, and T2 scans. The residual maps, capturing differences between predicted and actual T1ce images, serve as spatial priors to enhance downstream segmentation. In the second stage, a lightweight U-Net takes as input the concatenation of residual maps, computed as the difference between real T1ce and synthesized T1ce, with T1, T2, and FLAIR modalities to improve whole tumor segmentation. To address the increased scale and variability of BraTS 2021, we apply slice-level filtering to exclude non-informative samples and optimize thresholding strategies to balance precision and recall. Our method achieves a Dice score of $93.02\%$ and an IoU of $86.7\%$ for whole tumor segmentation on the BraTS 2021 dataset, outperforming the ReCoSeg baseline on BraTS 2020 (Dice: $91.7\%$, IoU: $85.3\%$), and demonstrating improved accuracy and scalability for real-world, multi-center MRI datasets.