An Optimization Framework for Processing and Transfer Learning for the Brain Tumor Segmentation

TL;DR

This paper introduces an optimization framework using a 3D U-Net model with transfer learning and processing techniques to improve brain tumor segmentation accuracy and generalizability on multi-modal MRI data.

Contribution

The paper presents a novel optimization framework that combines pre/post-processing and transfer learning to enhance brain tumor segmentation performance.

Findings

Achieved lesion-wise Dice scores of 0.79, 0.72, 0.74 on BraTS 2023 challenges.

Improved segmentation accuracy over existing methods.

Framework enhances model generalizability for clinical application.

Abstract

Tumor segmentation from multi-modal brain MRI images is a challenging task due to the limited samples, high variance in shapes and uneven distribution of tumor morphology. The performance of automated medical image segmentation has been significant improvement by the recent advances in deep learning. However, the model predictions have not yet reached the desired level for clinical use in terms of accuracy and generalizability. In order to address the distinct problems presented in Challenges 1, 2, and 3 of BraTS 2023, we have constructed an optimization framework based on a 3D U-Net model for brain tumor segmentation. This framework incorporates a range of techniques, including various pre-processing and post-processing techniques, and transfer learning. On the validation datasets, this multi-modality brain tumor segmentation framework achieves an average lesion-wise Dice score of 0.79, 0.72, 0.74 on Challenges 1, 2, 3 respectively.