SegResMamba: An Efficient Architecture for 3D Medical Image Segmentation
This addresses efficiency and environmental sustainability challenges for researchers and practitioners in medical imaging, though it is incremental as it builds on existing Structured State Space Models.
The authors tackled the high computational and memory demands of Transformer models for 3D medical image segmentation by proposing SegResMamba, which uses less than half the memory during training while achieving comparable performance to state-of-the-art architectures.
The Transformer architecture has opened a new paradigm in the domain of deep learning with its ability to model long-range dependencies and capture global context and has outpaced the traditional Convolution Neural Networks (CNNs) in many aspects. However, applying Transformer models to 3D medical image datasets presents significant challenges due to their high training time, and memory requirements, which not only hinder scalability but also contribute to elevated CO$_2$ footprint. This has led to an exploration of alternative models that can maintain or even improve performance while being more efficient and environmentally sustainable. Recent advancements in Structured State Space Models (SSMs) effectively address some of the inherent limitations of Transformers, particularly their high memory and computational demands. Inspired by these advancements, we propose an efficient 3D segmentation model for medical imaging called SegResMamba, designed to reduce computation complexity, memory usage, training time, and environmental impact while maintaining high performance. Our model uses less than half the memory during training compared to other state-of-the-art (SOTA) architectures, achieving comparable performance with significantly reduced resource demands.