Brain Tumour Removing and Missing Modality Generation using 3D WDM

TL;DR

This paper introduces a novel approach using conditional 3D wavelet diffusion models to improve brain tumor segmentation and missing modality generation in MRI scans, addressing challenges of variability and incomplete data.

Contribution

The paper presents a new method employing 3D wavelet diffusion models for brain tumor removal and missing modality generation, enhancing model robustness and accuracy.

Findings

Achieved second place in BraTS 2024 task 8

Effective full-resolution image prediction without patching or downsampling

Improved handling of missing MRI modalities in brain tumor analysis

Abstract

This paper presents the second-placed solution for task 8 and the participation solution for task 7 of BraTS 2024. The adoption of automated brain analysis algorithms to support clinical practice is increasing. However, many of these algorithms struggle with the presence of brain lesions or the absence of certain MRI modalities. The alterations in the brain's morphology leads to high variability and thus poor performance of predictive models that were trained only on healthy brains. The lack of information that is usually provided by some of the missing MRI modalities also reduces the reliability of the prediction models trained with all modalities. In order to improve the performance of these models, we propose the use of conditional 3D wavelet diffusion models. The wavelet transform enabled full-resolution image training and prediction on a GPU with 48 GB VRAM, without patching or downsampling, preserving all information for prediction. The code for these tasks is available at https://github.com/ShadowTwin41/BraTS_2023_2024_solutions.