Brain Tumour Removing and Missing Modality Generation using 3D WDM
This addresses reliability issues in clinical brain tumor prediction models when dealing with morphological variability and incomplete data, though it appears incremental as an adaptation of existing methods.
The paper tackled the problem of automated brain analysis algorithms struggling with brain lesions and missing MRI modalities by proposing conditional 3D wavelet diffusion models, achieving second place in task 8 and participation in task 7 of BraTS 2024.
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.