I2U-Net: A dual-path U-Net with rich information interaction for medical image segmentation

S-Net: A novel shallow network for enhanced detail retention in medical image segmentation

BACKGROUND AND OBJECTIVE

In recent years, deep U-shaped network architectures have been widely applied to medical image segmentation tasks, achieving notable successes. However, the inherent limitation of this architecture is that multiple down-sampling lead to significant loss of input image detail information. A series of improvements in skip connections designed to enhance information transfer have not fundamentally resolved the issue. Therefore, we consider retaining information in a simpler and more effective way.

METHODS

In this paper, we propose a novel shallow network, S-Net, which contains only two output resolution stages, allowing for the preservation of more detailed information from the input images. To address the challenge of shallow networks primarily relying on high-resolution feature maps as the main information flow, we propose a Global-Local Feature Fusion (GLFF) module at the network bottleneck layer. This module integrates the superior global contextual information extraction capabilities of Mamba with the local feature capturing abilities of multi-scale depthwise convolutions, enabling the extraction of crucial semantic features from high-resolution feature maps within a shallow network architecture, while maintaining a smaller model size.

RESULTS

Extensive experiments on four different types of medical image datasets show that S-Net achieves the best segmentation performance compared to existing models, with more refined segmentation details. For example, on ultrasound datasets (BUSI), the IOU is 2.95% higher and DICE is 2.27% higher than the second-best model. Additionally, S-Net has only 1.52M parameters, making it competitive in terms of lightweight design.

CONCLUSIONS

Comparative and ablation experiments demonstrate the efficiency of the proposed architecture and modules. It shows that we do not need many down-sampling operations to reduce the size of feature maps significantly. This work provides new research ideas for further improving the accuracy of medical image segmentation and expands the research direction for model lightweight design. The code will be available at: https://github.com/qinghua0715/S-Net.

CMSAF-Net: integrative network design with enhanced decoder for precision segmentation of pear leaf diseases

Pear leaf diseases represent one of the major challenges in agriculture, significantly affecting fruit quality and reducing overall yield. With the advancement of precision agriculture, accurate identification and segmentation of diseased areas are critical for targeted disease management and optimizing crop production. To address these issues, this study proposes a novel segmentation model, CMSAF-Net, for pear leaf diseases. CMSAF-Net integrates a Multi-scale Convolutional Attention Module (MBCA), a Self-adaptive Attention-augmented Upsampling Module (SAUP), and a Cross-layer Feature Alignment Module (CGAG) to enhance feature extraction, preserve edge information in complex disease regions, and optimize cross-layer information fusion. Additionally, CMSAF-Net incorporates pre-trained weights to leverage prior knowledge, accelerating convergence and improving segmentation accuracy. On a self-constructed dataset containing three types of pear leaf diseases, experimental results demonstrate that CMSAF-Net achieves 88.65%, 93.36%, and 93.86% in key metrics of MIoU, MPA, and Dice, respectively. Compared with mainstream models such as Unet++, DeepLabv3+, U2 -Net, and TransUNet, CMSAF-Net exhibits significant performance improvements, with MIoU increases of 2.45%, 3.86%, 2.21%, and 8.28%, respectively. This study highlights CMSAF-Net's potential for large-scale disease monitoring in intelligent agriculture, providing an efficient segmentation solution with substantial theoretical and practical implications.

Medical Image Segmentation: A Comprehensive Review of Deep Learning-Based Methods

Medical image segmentation is a critical application of computer vision in the analysis of medical images. Its primary objective is to isolate regions of interest in medical images from the background, thereby assisting clinicians in accurately identifying lesions, their sizes, locations, and their relationships with surrounding tissues. However, compared to natural images, medical images present unique challenges, such as low resolution, poor contrast, inconsistency, and scattered target regions. Furthermore, the accuracy and stability of segmentation results are subject to more stringent requirements. In recent years, with the widespread application of Convolutional Neural Networks (CNNs) in computer vision, deep learning-based methods for medical image segmentation have become a focal point of research. This paper categorizes, reviews, and summarizes the current representative methods and research status in the field of medical image segmentation. A comparative analysis of relevant experiments is presented, along with an introduction to commonly used public datasets, performance evaluation metrics, and loss functions in medical image segmentation. Finally, potential future research directions and development trends in this field are predicted and analyzed.

Asymmetric Adaptive Heterogeneous Network for Multi-Modality Medical Image Segmentation

Existing studies of multi-modality medical image segmentation tend to aggregate all modalities without discrimination and employ multiple symmetric encoders or decoders for feature extraction and fusion. They often overlook the different contributions to visual representation and intelligent decisions among multi-modality images. Motivated by this discovery, this paper proposes an asymmetric adaptive heterogeneous network for multi-modality image feature extraction with modality discrimination and adaptive fusion. For feature extraction, it uses a heterogeneous two-stream asymmetric feature-bridging network to extract complementary features from auxiliary multi-modality and leading single-modality images, respectively. For feature adaptive fusion, the proposed Transformer-CNN Feature Alignment and Fusion (T-CFAF) module enhances the leading single-modality information, and the Cross-Modality Heterogeneous Graph Fusion (CMHGF) module further fuses multi-modality features at a high-level semantic layer adaptively. Comparative evaluation with ten segmentation models on six datasets demonstrates significant efficiency gains as well as highly competitive segmentation accuracy. (Our code is publicly available at https://github.com/joker-527/AAHN).

Grouped multi-scale vision transformer for medical image segmentation

Medical image segmentation plays a pivotal role in clinical diagnosis and pathological research by delineating regions of interest within medical images. While early approaches based on Convolutional Neural Networks (CNNs) have achieved significant success, their limited receptive field constrains their ability to capture long-range dependencies. Recent advances in Vision Transformers (ViTs) have demonstrated remarkable improvements by leveraging self-attention mechanisms. However, existing ViT-based segmentation models often struggle to effectively capture multi-scale variations within a single attention layer, limiting their capacity to model complex anatomical structures. To address this limitation, we propose Grouped Multi-Scale Attention (GMSA), which enhances multi-scale feature representation by grouping channels and performing self-attention at different scales within a single layer. Additionally, we introduce Inter-Scale Attention (ISA) to facilitate cross-scale feature fusion, further improving segmentation performance. Extensive experiments on the Synapse, ACDC, and ISIC2018 datasets demonstrate the effectiveness of our model, achieving state-of-the-art results in medical image segmentation. Our code is available at: https://github.com/Chen2zheng/ScaleFormer .

BDFormer: Boundary-aware dual-decoder transformer for skin lesion segmentation

Segmenting skin lesions from dermatoscopic images is crucial for improving the quantitative analysis of skin cancer. However, automatic segmentation of skin lesions remains a challenging task due to the presence of unclear boundaries, artifacts, and obstacles such as hair and veins, all of which complicate the segmentation process. Transformers have demonstrated superior capabilities in capturing long-range dependencies through self-attention mechanisms and are gradually replacing CNNs in this domain. However, one of their primary limitations is the inability to effectively capture local details, which is crucial for handling unclear boundaries and significantly affects segmentation accuracy. To address this issue, we propose a novel boundary-aware dual-decoder transformer that employs a single encoder and dual-decoder framework for both skin lesion segmentation and dilated boundary segmentation. Within this model, we introduce a shifted window cross-attention block to build the dual-decoder structure and apply multi-task distillation to enable efficient interaction of inter-task information. Additionally, we propose a multi-scale aggregation strategy to refine the extracted features, ensuring optimal predictions. To further enhance boundary details, we incorporate a dilated boundary loss function, which expands the single-pixel boundary mask into planar information. We also introduce a task-wise consistency loss to promote consistency across tasks. Our method is evaluated on three datasets: ISIC2018, ISIC2017, and PH2, yielding promising results with excellent performance compared to state-of-the-art models. The code is available at https://github.com/Yuxuan-Ye/BDFormer.

A novel framework for segmentation of small targets in medical images

Medical image segmentation represents a pivotal and intricate procedure in the domain of medical image processing and analysis. With the progression of artificial intelligence in recent years, the utilization of deep learning techniques for medical image segmentation has witnessed escalating popularity. Nevertheless, the intricate nature of medical image poses challenges on the segmentation of diminutive targets is still in its early stages. Current networks encounter difficulties in addressing the segmentation of exceedingly small targets, especially when the number of training samples is limited. To overcome this constraint, we have implemented a proficient strategy to enhance lesion images containing small targets and constrained samples. We introduce a segmentation framework termed STS-Net, specifically designed for small target segmentation. This framework leverages the established capacity of convolutional neural networks to acquire effective image representations. The proposed STS-Net network adopts a ResNeXt50-32x4d architecture as the encoder, integrating attention mechanisms during the encoding phase to amplify the feature representation capabilities of the network. We evaluated the proposed network on four publicly available datasets. Experimental results underscore the superiority of our approach in the domain of medical image segmentation, particularly for small target segmentation. The codes are available at https://github.com/zlxokok/STSNet .

FocusU2Net: Pioneering dual attention with gated U-Net for colonoscopic polyp segmentation

The detection and excision of colorectal polyps, precursors to colorectal cancer (CRC), can improve survival rates by up to 90%. Automated polyp segmentation in colonoscopy images expedites diagnosis and aids in the precise identification of adenomatous polyps, thus mitigating the burden of manual image analysis. This study introduces FocusU2Net, an innovative bi-level nested U-structure integrated with a dual-attention mechanism. The model integrates Focus Gate (FG) modules for spatial and channel-wise attention and Residual U-blocks (RSU) with multi-scale receptive fields for capturing diverse contextual information. Comprehensive evaluations on five benchmark datasets - Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, ETISLarib, and EndoScene - demonstrate Dice score improvements of 3.14% to 43.59% over state-of-the-art models, with an 85% success rate in cross-dataset validations, significantly surpassing prior competing models with sub-5% success rates. The model combines high segmentation accuracy with computational efficiency, featuring 46.64 million parameters, 78.09 GFLOPs, and 39.02 GMacs, making it suitable for real-time applications. Enhanced with Explainable AI techniques, FocusU2Net provides clear insights into its decision-making process, improving interpretability. This combination of high performance, efficiency, and transparency positions FocusU2Net as a powerful, scalable solution for automated polyp segmentation in clinical practice, advancing medical image analysis and computer-aided diagnosis.

Attention-based multi-residual network for lung segmentation in diseased lungs with custom data augmentation

Lung disease analysis in chest X-rays (CXR) using deep learning presents significant challenges due to the wide variation in lung appearance caused by disease progression and differing X-ray settings. While deep learning models have shown remarkable success in segmenting lungs from CXR images with normal or mildly abnormal findings, their performance declines when faced with complex structures, such as pulmonary opacifications. In this study, we propose AMRU++, an attention-based multi-residual UNet++ network designed for robust and accurate lung segmentation in CXR images with both normal and severe abnormalities. The model incorporates attention modules to capture relevant spatial information and multi-residual blocks to extract rich contextual and discriminative features of lung regions. To further enhance segmentation performance, we introduce a data augmentation technique that simulates the features and characteristics of CXR pathologies, addressing the issue of limited annotated data. Extensive experiments on public and private datasets comprising 350 cases of pneumoconiosis, COVID-19, and tuberculosis validate the effectiveness of our proposed framework and data augmentation technique.