GFA-Net: Global Feature Aggregation Network Based on Contrastive Learning for Breast Lesion Automated Segmentation in Ultrasound Images
- 20 November 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
Abstract
Accurate automatic segmentation of breast lesions in ultrasound images is a challenging auxiliary diagnostic task for automated deployment in breast cancer screening. In this study, a contrastive learning based global feature aggregation network (GFA-Net) is proposed to reduce false detections and missed detections, thereby providing computer vision assistance for the development of automated equipment for breast screening. The method first utilizes the feature extraction layer to extract multi-scale feature maps from the ultrasound image, and uses atrous spatial pyramid pooling (ASPP) to enhance the receptive field of the feature. In order to better utilize the spatial-channel complementary information between multi-scale features, a global feature aggregation (GFA) module is proposed. This module can effectively utilize shallow features to extract deep features. Fine segmentation of tumor boundaries in ultrasound images is also crucial as it can reveal the edge diagnostic features of benign and malignant tumors. Therefore, a result fine repair (RFR) module is developed to refine the boundaries of segmented lesions. In addition, a contrastive deep supervision (CDS) method based on contrastive learning is designed, which can introduce the loss of contrastive learning into the process of deep supervision, and can use the correlation between different data in the same batch of training to improve the feature extraction ability of each extraction stage of the backbone network. The experimental results show that our GFA-Net has better segmentation performance than other existing advanced methods. The applicability analysis also indicates that our method still has good generalization ability for different medical ultrasound images, and still maintains strong competitiveness compared to advanced methods.Keywords
Funding Information
- State Key Project of Research and Development Plan (2022YFC2401600, 2022YFC2408500)
- National Natural Science Foundation of China (T2225025, 62101249)
- Key Research and development Programs in Jiangsu Province of China (BE2021703, BE2022768)
- Natural Science Foundation of Jiangsu Province (BK20210291)
This publication has 40 references indexed in Scilit:
- AMS-PAN: Breast ultrasound image segmentation model combining attention mechanism and multi-scale featuresBiomedical Signal Processing and Control, 2022
- Contrastive Deep Supervision2022
- D-former: a U-shaped Dilated Transformer for 3D medical image segmentationNeural Computing and Applications, 2022
- A Discriminative Level Set Method with Deep Supervision for Breast Tumor SegmentationComputers in Biology and Medicine, 2022
- Multi-phase Liver Tumor Segmentation with Spatial Aggregation and Uncertain Region Inpainting2021
- RDA-UNET-WGAN: An Accurate Breast Ultrasound Lesion Segmentation Using Wasserstein Generative Adversarial NetworksArabian Journal for Science and Engineering, 2020
- Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour modelMedical Physics, 2018
- Breast density implications and supplemental screeningEuropean Radiology, 2018
- Boundary Regularized Convolutional Neural Network for Layer Parsing of Breast Anatomy in Automated Whole Breast Ultrasound2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015