Efficient 3D Brain Tumor Segmentation with Axial-Coronal-Sagittal Embedding
This addresses efficiency and performance issues in medical imaging for brain tumor segmentation, though it is incremental as it builds on existing nnU-Net methods.
The paper tackled brain tumor segmentation by integrating Axial-Coronal-Sagittal convolutions and pre-trained weights into nnU-Net, resulting in reduced training epochs and parameters while achieving comparable or better performance than ensemble models.
In this paper, we address the crucial task of brain tumor segmentation in medical imaging and propose innovative approaches to enhance its performance. The current state-of-the-art nnU-Net has shown promising results but suffers from extensive training requirements and underutilization of pre-trained weights. To overcome these limitations, we integrate Axial-Coronal-Sagittal convolutions and pre-trained weights from ImageNet into the nnU-Net framework, resulting in reduced training epochs, reduced trainable parameters, and improved efficiency. Two strategies for transferring 2D pre-trained weights to the 3D domain are presented, ensuring the preservation of learned relationships and feature representations critical for effective information propagation. Furthermore, we explore a joint classification and segmentation model that leverages pre-trained encoders from a brain glioma grade classification proxy task, leading to enhanced segmentation performance, especially for challenging tumor labels. Experimental results demonstrate that our proposed methods in the fast training settings achieve comparable or even outperform the ensemble of cross-validation models, a common practice in the brain tumor segmentation literature.