Multiscale Encoder and Omni-Dimensional Dynamic Convolution Enrichment in nnU-Net for Brain Tumor Segmentation
This work addresses brain tumor segmentation for medical diagnosis, presenting an incremental improvement over existing methods.
The study tackled brain tumor segmentation by enhancing nnU-Net with omni-dimensional dynamic convolution and multi-scale attention, resulting in improved performance on datasets like BraTS-2023 and good accuracy on the BraTS Africa dataset.
Brain tumor segmentation plays a crucial role in computer-aided diagnosis. This study introduces a novel segmentation algorithm utilizing a modified nnU-Net architecture. Within the nnU-Net architecture's encoder section, we enhance conventional convolution layers by incorporating omni-dimensional dynamic convolution layers, resulting in improved feature representation. Simultaneously, we propose a multi-scale attention strategy that harnesses contemporary insights from various scales. Our model's efficacy is demonstrated on diverse datasets from the BraTS-2023 challenge. Integrating omni-dimensional dynamic convolution (ODConv) layers and multi-scale features yields substantial improvement in the nnU-Net architecture's performance across multiple tumor segmentation datasets. Remarkably, our proposed model attains good accuracy during validation for the BraTS Africa dataset. The ODconv source code along with full training code is available on GitHub.