GLIMS: Attention-Guided Lightweight Multi-Scale Hybrid Network for Volumetric Semantic Segmentation

Abstract

Convolutional Neural Networks (CNNs) have become widely adopted for medical image segmentation tasks, demonstrating promising performance. However, the inherent inductive biases in convolutional architectures limit their ability to model long-range dependencies and spatial correlations. While recent transformer-based architectures address these limitations by leveraging self-attention mechanisms to encode long-range dependencies and learn expressive representations, they often struggle to extract low-level features and are highly dependent on data availability. This motivated us for the development of GLIMS, a data-efficient attention-guided hybrid volumetric segmentation network. GLIMS utilizes Dilated Feature Aggregator Convolutional Blocks (DACB) to capture local-global feature correlations efficiently. Furthermore, the incorporated Swin Transformer-based bottleneck bridges the local and global features to improve the robustness of the model. Additionally, GLIMS employs an attention-guided segmentation approach through Channel and Spatial-Wise Attention Blocks (CSAB) to localize expressive features for fine-grained border segmentation. Quantitative and qualitative results on glioblastoma and multi-organ CT segmentation tasks demonstrate GLIMS' effectiveness in terms of complexity and accuracy. GLIMS demonstrated outstanding performance on BraTS2021 and BTCV datasets, surpassing the performance of Swin UNETR. Notably, GLIMS achieved this high performance with a significantly reduced number of trainable parameters. Specifically, GLIMS has 47.16M trainable parameters and 72.30G FLOPs, while Swin UNETR has 61.98M trainable parameters and 394.84G FLOPs. The code is publicly available on https://github.com/yaziciz/GLIMS.

The article was accepted for publication in the Image and Vision Computing journal

References in corpus (14)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Attention U-Net: Learning Where to Look for the Pancreas
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• SpectralGPT: Spectral Remote Sensing Foundation Model
• Medical Image Segmentation Using Deep Learning: A Survey
• CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation
• nnFormer: Interleaved Transformer for Volumetric Segmentation
• Segment Everything Everywhere All at Once
• Foundational Models Defining a New Era in Vision: A Survey and Outlook
• SegGPT: Segmenting Everything In Context
• Image Segmentation Using Text and Image Prompts