Taming Mambas for Voxel Level 3D Medical Image Segmentation
This work addresses segmentation challenges in medical imaging by introducing a novel architecture, though it appears incremental as it applies an existing method to a new domain.
The paper tackles the problem of 3D medical image segmentation by adapting Mamba, a state space model with linear complexity, to overcome limitations of CNNs and transformers, achieving competitive results on medical datasets.
Recently, the field of 3D medical segmentation has been dominated by deep learning models employing Convolutional Neural Networks (CNNs) and Transformer-based architectures, each with their distinctive strengths and limitations. CNNs are constrained by a local receptive field, whereas transformers are hindered by their substantial memory requirements as well as they data hungriness, making them not ideal for processing 3D medical volumes at a fine-grained level. For these reasons, fully convolutional neural networks, as nnUNet, still dominate the scene when segmenting medical structures in 3D large medical volumes. Despite numerous advancements towards developing transformer variants with subquadratic time and memory complexity, these models still fall short in content-based reasoning. A recent breakthrough is Mamba, a Recurrent Neural Network (RNN) based on State Space Models (SSMs) outperforming Transformers in many long-context tasks (million-length sequences) on famous natural language processing and genomic benchmarks while keeping a linear complexity.