BiSe-Unet: A Lightweight Dual-path U-Net with Attention-refined Context for Real-time Medical Image Segmentation
Authors: M Iffat Hossain, Laura Brattain
Organizations: Electrical and Computer Engineering, University of Central Florida · Department of Medicine, University of Central Florida College of Medicine
During image-guided procedures, real-time image segmentation is often required. This demands lightweight AI models that can operate on resource-constrained devices. One important use case is endoscopy-guided colonoscopy, where polyps must be detected in real time. The Kvasir-Seg dataset, a publicly available benchmark for this task, contains 1,000 high-resolution endoscopic images of polyps with corresponding pixel-level segmentation masks. Achieving real-time inference speed for clinical deployment in constrained environments requires highly efficient and lightweight network architectures. However, many existing models remain too computationally intensive for embedded deployment. Lightweight architectures, although faster, often suffer from reduced spatial precision and weaker contextual understanding, leading to degraded boundary quality and reduced diagnostic reliability. To address these challenges, we introduce BiSe-UNet, a lightweight dual-path U-Net that integrates an attention-refined context path with a shallow spatial path for detailed feature preservation, followed by a depthwise separable decoder for efficient reconstruction. Evaluated on the Kvasir-Seg dataset, BiSe-UNet achieves competitive Dice and IoU scores while sustaining real-time throughput exceeding 30 FPS on Raspberry Pi 5, demonstrating its effectiveness for accurate, lightweight, and deployable medical image segmentation on edge hardware.
Figures & tables
Figure 1: The workflow shows BiSe-UNet extracting spatial and contextual features in two paths, merging them once for efficient integration, and decoding with a lightweight DSConv module to retain boundaries with minimal computation.
Figure 2: Polyp Segmentation Performance Comparison - BiSe-UNet against popular existing segmentation models
Model
Params (M) ↓
MACs (G) ↓
Dice ↑
IoU ↑
CUDA (GTX 1080 Ti)
Raspberry Pi 5
FPS ↑
Memory (MB) ↓
FPS ↑
Memory (MB) ↓
U-Net (baseline)
7.813
11.67
0.7900
0.7000
217.91
420
2.65
300
BiSeNet
2.533
1.07
0.7501
0.6595
397.37
210
30.06
160
HarDNet
3.809
4.46
0.7775
0.6959
232.62
360
7.17
200
BiSe-UNet (Ours)
2.509
0.97
0.7809
0.6961
358.34
240
30.48
170
Table 1: Comparison of segmentation models on CUDA (GTX 1080 Ti) and Raspberry Pi 5. Shared metrics include model size, computational cost, and segmentation accuracy. FPS and Memory indicate device-specific throughput and runtime footprint.
Figure 3: Ablation of BiSe-UNet tested on Raspberry Pi 5. The square (DSConv encoder) improves speed but lowers Dice Score compared to the base model (circle); the diamond (DSConv in both encoder and decoder) maintains high accuracy, while the triangle (final BiSe-UNet with custom skip connections) results in good speed and Dice score.
Accurate polyp segmentation in colonoscopy is essential for early colorectal cancer detection, yet real-world clinical environments pose persistent challenges such as motion blur, specular reflections, and illumination instability. Most existing methods are optimized on clean benchmark images and suffer noticeable performance degradation when deployed in authentic surgical scenarios. We propose DepthPolyp, a lightweight and robust segmentation framework based on pseudo-depth-guided multi-task learning and efficient feature modulation. The architecture combines hierarchical Ghost factorization for compact feature generation, Interleaved Shuffle Fusion for low-cost cross-scale interaction, and Dynamic Group Gating for adaptive group-wise feature weighting. Extensive experiments demonstrate that DepthPolyp achieves strong cross-dataset generalization when trained on degraded data and evaluated on both clean and noisy target domains, consistently outperforming lightweight baselines and remaining competitive with substantially larger models. In real surgical video evaluation on PolypGen, DepthPolyp achieves better segmentation performance than models up to 20× larger while preserving real-time inference speed. With only 3.57M parameters and 0.86 GMACs, the proposed method runs at over 180 FPS on mobile devices, making it well suited for real-time deployment in resource-constrained clinical environments. Code and pretrained weights are available at: https://github.com/ReaganWu/DepthPolyp/
Zhuoyu Wu, Wenhui Ou, Lexi Zhang +5
CyPhi AI Lab, Monash University, Malaysia Campus, Malaysia · Department of Electronic & Computer Engineering, Hong Kong University of Science & Technology, Hong Kong, P.R. China · Harbin Institute of Technology, Harbin, P.R. China +1
Medical image segmentation requires high accuracy and robustness, yet practical commercial deployment also demands privacy preservation and computational efficiency. In this context, the U-Net architecture, which can be inherently decoupled into independent encoder and decoder components, serves as a natural commercial choice. However, pure Transformer-based variants like Swin-UNet often suffer from insufficient local detail capture and limited interpretability. In this paper, we propose a lightweight hybrid architecture built upon the Swin-UNet framework. Our model integrates a parallel CNN encoder to complement the shallow layer reasoning of Swin Transformers with local texture features. To bridge the semantic gap and enhance fine-grained spatial detail recovery, we design an asymmetric feature fusion strategy and introduce cross-layer skip (XSkip) connections that explicitly propagate shallow CNN features into the decoder. We further incorporate novel loss functions and an auxiliary supervision head (Aux-Head) to strengthen training stability, boundary delineation, and intermediate feature interpretability. Extensive experiments on the Synapse multi-organ segmentation dataset demonstrate that our approach achieves state-of-the-art competitive Dice scores and Hausdorff distances, offering an accurate, efficient, and interpretable solution for clinical deployment.
Automated segmentation of the vertebral column in Computed Tomography (CT) scans is a prerequisite for pathological assessment and surgical planning. However, state-of-the-art methods, particularly those based on Transformers or large-scale ensembles, demand substantial GPU resources, creating a barrier for clinical adoption in resource-constrained environments or on edge devices. To address this, we introduce SpineContextResUNet, a computationally efficient 3D Residual U-Net designed for rapid spinal localization. Our architecture integrates a lightweight Context Block that employs parallel multi-dilated convolutions to capture long-range anatomical dependencies without the high latency of Recurrent Neural Networks (RNNs) or the memory overhead of Self-Attention mechanisms. Extensive validation on two public benchmarks, VerSe2020 and CTSpine1K, demonstrates that our model achieves a Dice score of 88.17% and 88.13% respectively. To evaluate performance under strict hardware constraints, we compared our model against a bottlenecked SwinUNETR scaled to match our ~1.7M hardware footprint. While the constrained Transformer suffers severe performance degradation due to a lack of spatial inductive biases in a limited-data regime, our CNN-based approach successfully maintains high accuracy. Crucially, heavy baselines like TotalSegmentator fail due to memory exhaustion on commodity hardware (Intel Core i5, 8GB RAM), our model performs robust inference, making it a viable solution for point-of-care diagnostics and deployment on edge platforms like the Nvidia Jetson Orin Nano.