Swin-Net: A Swin-Transformer-Based Network Combing with Multi-Scale Features for Segmentation of Breast Tumor Ultrasound Images
Open Access
- 26 January 2024
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 14 (3) , 269
Abstract
Breast cancer is one of the most common cancers in the world, especially among women. Breast tumor segmentation is a key step in the identification and localization of the breast tumor region, which has important clinical significance. Inspired by the swin-transformer model with powerful global modeling ability, we propose a semantic segmentation framework named Swin-Net for breast ultrasound images, which combines Transformer and Convolutional Neural Networks (CNNs) to effectively improve the accuracy of breast ultrasound segmentation. Firstly, our model utilizes a swin-transformer encoder with stronger learning ability, which can extract features of images more precisely. In addition, two new modules are introduced in our method, including the feature refinement and enhancement module (RLM) and the hierarchical multi-scale feature fusion module (HFM), given that the influence of ultrasonic image acquisition methods and the characteristics of tumor lesions is difficult to capture. Among them, the RLM module is used to further refine and enhance the feature map learned by the transformer encoder. The HFM module is used to process multi-scale high-level semantic features and low-level details, so as to achieve effective cross-layer feature fusion, suppress noise, and improve model segmentation performance. Experimental results show that Swin-Net performs significantly better than the most advanced methods on the two public benchmark datasets. In particular, it achieves an absolute improvement of 1.4–1.8% on Dice. Additionally, we provide a new dataset of breast ultrasound images on which we test the effect of our model, further demonstrating the validity of our method. In summary, the proposed Swin-Net framework makes significant advancements in breast ultrasound image segmentation, providing valuable exploration for research and applications in this domain.Keywords
Funding Information
- National Natural Science Foundation of China (62376287, 61702559, 2021CB1013, 2022SK2054, 2022JJ30762, 2023JJ60334, 2023JJ70016, 202209024847)
- International Science and Technology Innovation Joint Base of Machine Vision and Medical Image Processing in Hunan Province (62376287, 61702559, 2021CB1013, 2022SK2054, 2022JJ30762, 2023JJ60334, 2023JJ70016, 202209024847)
- Key Research and Development Program of Hunan Province (62376287, 61702559, 2021CB1013, 2022SK2054, 2022JJ30762, 2023JJ60334, 2023JJ70016, 202209024847)
- Natural Science Foundation of Hunan Province (62376287, 61702559, 2021CB1013, 2022SK2054, 2022JJ30762, 2023JJ60334, 2023JJ70016, 202209024847)
- Health Commission Project of Hunan Province (62376287, 61702559, 2021CB1013, 2022SK2054, 2022JJ30762, 2023JJ60334, 2023JJ70016, 202209024847)
This publication has 28 references indexed in Scilit:
- Automatic breast ultrasound image segmentation: A surveyPattern Recognition, 2018
- A survey on deep learning in medical image analysisMedical Image Analysis, 2017
- A deep learning framework for supporting the classification of breast lesions in ultrasound imagesPhysics in Medicine & Biology, 2017
- Automated Breast Ultrasound Lesions Detection Using Convolutional Neural NetworksIEEE Journal of Biomedical and Health Informatics, 2017
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Pyramid Scene Parsing Network2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015