AMS-PAN: Breast ultrasound image segmentation model combining attention mechanism and multi-scale features. (March 2023)

• Record Type: Journal Article
• Authors: Lyu, Yuchao; Xu, Yinghao; Jiang, Xi; Liu, Jianing; Zhao, Xiaoyan; Zhu, Xijun
• Is Part Of: Biomedical signal processing and control. Volume 81(2023)
• Publication Date: 2023-03
• Subjects: Ultrasound image -- Multi-scale features -- Attention mechanisms -- Breast tumor segmentation -- Feature pyramid; AMS-PAN Pyramid Attention Network model combining Attention mechanism and Multi-Scale features -- GAU Global Attention Upsample -- SCA Spatial and Channel Attention -- BUSI Breast Ultrasound Image dataset for segmentation -- OASBUD Open Access Series of Breast Ultrasonic Dataset -- DM Digital Mammography -- MRI Magnetic Resonance Imaging -- SoTA State-of-The-Art -- PAN Pyramid Attention Network -- FPA Feature Pyramid Attention -- MW Marker Watershed -- MS Morphological Snake -- AMSMW Adaptive Morphological Snake based on Marker Watershed -- SSD Single Shot multi-box Detector -- FPN Feature Pyramid Network -- CBAM Convolutional Block Attention Module -- ReLU Rectified Linear Units -- IoU Intersection over Union -- TP True Positives -- TN True Negatives -- FP False Positives -- FN False Negatives -- ROC Receiver Operating Characteristic -- PR Precision-Recall -- AUC Area Under Curve -- mAP mean Average Precision -- Att U-Net U-Net with Spatial and Channel'Squeeze Excitation' Attention; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104425
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A deep learning model with PAN as the base structure was designed for the low definition of ultrasound breast images, and the effectiveness of this model was verified on BUSI and OASBUD. A multi-scale feature extraction module is designed, which can acquire deep image local information while preserving shallow image global information. The attention module called SCA is added to the decoder based on PAN to prompt the model to pay attention to the edges and details in the image and strengthen the segmentation ability of the model. Abstract: Breast ultrasound medical images are characterized by poor imaging quality and irregular target edges. During the diagnosis process, it is difficult for physicians to segment tumors manually, and the segmentation accuracy required for diagnosis is high, so there is an urgent need for an automated method to improve the segmentation accuracy as a technical tool to assist diagnosis. This study designed an improved Pyramid Attention Network combining Attention mechanism and Multi-Scale features (AMS-PAN) for breast ultrasound image segmentation. On the encoding side, the model adopts the depthwise separable convolution strategy to achieve a multi-scale receptive field with cumulative small-size convolution, which performs multi-dimensional feature extraction and forms a feature pyramid. The model uses Global Attention Upsample (GAU) feature fusion on the decoding side. In order to further process the fused feature information, the proposed method uses a Spatial and Channel Attention (SCA) module to shift the model's segmentation focus to the edge texture information. The good segmentation performance of our method is verified through experiments on BUSI and OASBUD. All the designed parts have contributed to the segmentation performance in practical applications. Compared with the traditional non-deep learning methods and the current mainstream deep learning methods, the improvement of the model in Dice and IoU metrics is pronounced. AMS-PAN has high computational efficiency, and its good performance has been proven to play a role in ultrasound detection tasks of breast tumors for physicians to specific auxiliary diagnostic roles to guide the subsequent diagnosis and treatment services for patients.