LKCAU-Net: A Large Kernel Coordinated Attention U-Net for Breast Tumors Segmentation in Ultrasound Images.

Lai Jiang Yuxin Zheng Aibin Huang

Jul 2026 · Ultrasonic imaging (Print) · pp. 1617346261463796 · 1 citation · 30 references

Medicine

TL;DR

Experimental results demonstrate that LKCAU-Net outperforms current state-of-the-art segmentation approaches, providing enhanced accuracy and robustness in breast cancer segmentation from ultrasound images.

Abstract

Breast cancer remains a significant health concern for women worldwide. Ultrasound imaging is widely adopted for screening due to its non-invasive and radiation-free nature. However, challenges such as low image contrast, blurred tumor boundaries, and diverse tumor morphologies severely hinder accurate segmentation. To address these issues, we propose LKCAU-Net, a novel hybrid multi-scale network that integrates Large Kernel Coordinate Attention (LKCA) and Atrous Spatial Pyramid Pooling (ASPP). The LKCA module enhances the model's ability to capture spatial details and global contextual information, while the ASPP module enhances multi-scale contextual representation. Embedded within a deep U-Net architecture, these components enable effective global-local feature fusion, significantly improving the robustness and accuracy of breast tumor segmentation in complex ultrasound images. We conducted experiments on four widely used public datasets: BUSI, Dataset B, BUSBRA and QAMEBI. For Dataset B, our proposed LKCAU-Net attained a Dice score of 0.8215, a Jaccard index of 0.7167, a precision of 0.8797, a recall of 0.7937, and a specificity of 0.9949. On the BUSI dataset, it reached a Dice score of 0.7973, Jaccard index of 0.6899, precision of 0.8320, recall of 0.7886, and specificity of 0.9825. When evaluated on the BUSBRA dataset, the model achieved a Dice score of 0.9085, Jaccard index of 0.8402, precision of 0.9206, recall of 0.9057, and specificity of 0.9964. On the QAMEBI, it reached a Dice score of 0.8815, Jaccard index of 0.8770, precision of 0.8993, recall of 0.8937, and specificity of 0.9949. Experimental results demonstrate that LKCAU-Net outperforms current state-of-the-art segmentation approaches, providing enhanced accuracy and robustness in breast cancer segmentation from ultrasound images.

DOI PubMed Semantic Scholar

View source

Similar papers

Jul 2026

CSA-SegNet: enhancing ovarian tumor segmentation from ultrasound images with spatial pooling and contour-based loss functions

A new loss function is proposed that enhances conventional loss functions such as IoU loss, SSIM Loss, and Focal loss function with Active Contour Euler Elastical loss with effectiveness in enhancing segmentation accuracy and boundary delineation of ovarian ultrasound images.

Thi-Loan Pham, Hoang-Son Bui, Van-Hung Le et al. · International Journal of Mac... · 0 citations

Jul 2026

MKSFA-Net: a integrating structural priors for breast cancer segmentation based on multi-scale kernel selection fusion attention network

Extensive experiments demonstrate that MKSFA-Net consistently outperforms state-of-the-art CNN-based, Transformer-based, and hybrid segmentation models across multiple metrics, including Dice similarity coefficient (DSC), Intersection over Union (IoU), and 95% Haus Dorff Distance (HD95).

Zihao Chen, Fengrong Zhao, Wanhu Li et al. · Pattern Analysis and Applica... · 0 citations

Jul 2026

BiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography

BiLoG-Net is proposed, a deep learning framework that jointly performs breast mass segmentation and malignancy classification through bi-context location-aware feature modeling and segmentation-guided attention mechanisms, and holds strong potential for clinical computer-aided detection systems, helping radiologists pr...

Abu Fatema Mohammad Abdun Noor, Md Imam Ahasan, M. S. Ahasan et al. · arXiv.org · 0 citations

Open access Aug 2026

REC-UNet: a 2D U-Net model with residual cross-dimensional attention for liver tumor segmentation

A novel residual “Enhancement-Calibration” U-Net architecture, termed REC-UNet, which achieves high overall segmentation accuracy across diverse lesion sizes and contrast conditions without relying on explicit size-stratified optimization.

Zhiyuan Wang, Li-Jun Liang, Wei Wu et al. · PeerJ Computer Science · 0 citations

Open access Aug 2026

MGT–UNet: a hybrid CNN–transformer network with multi-scale feature learning and global context modeling for breast ultrasound segmentation

This work proposes MGT–UNet, a hybrid CNN–Transformer segmentation network that integrates multi-scale feature learning with global context modeling for breast ultrasound image segmentation and suggests that combining multi-scale feature learning with transformer-based global context modeling is beneficial for breast u...

H. Le, H. T. Huynh · BMC Medical Imaging · 0 citations

Jul 2026

HCDU-net and the shape of precision: advancing liver tumor segmentation with statistical geometry and adaptive deep learning using U-net

The Hybrid Convolutional Deep U-Net is presented, an improved U-Net that incorporates multi-scale atrous convolutions, residual upsampling branches, and refined skip connections to capture contextual features and retain precise edge details across different tumor scales.

Chitra Jain, Puja Das, Ansul et al. · Evolutionary Intelligence · 0 citations