Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

EUIS-Net: A Convolutional Neural Network for Efficient Ultrasound Image Segmentation

Shahzaib Iqbal, Hasnat Ahmed, Muhammad Sharif, Madiha Hena, Tariq M. Khan, Imran Razzak

TL;DR

EUIS-Net targets efficient and accurate ultrasound image segmentation by combining a compact four-block encoder–decoder architecture with attention-enhanced bottlenecks. It introduces a Region Aware Attention Module (RAAM) in skip connections and a Channel and Spatial Attention Module (CSAM) in the bottleneck to improve region localization and feature representation. Across BUSI and DDTI datasets, EUIS-Net achieves state-of-the-art IoU and Dice scores, while maintaining lower computational complexity, and demonstrates generalization to chest X-ray segmentation. The work highlights practical clinical applicability and points to semi-supervised extensions for reducing data requirements and broader use in medical imaging tasks.

Abstract

Segmenting ultrasound images is critical for various medical applications, but it offers significant challenges due to ultrasound images' inherent noise and unpredictability. To address these challenges, we proposed EUIS-Net, a CNN network designed to segment ultrasound images efficiently and precisely. The proposed EUIS-Net utilises four encoder-decoder blocks, resulting in a notable decrease in computational complexity while achieving excellent performance. The proposed EUIS-Net integrates both channel and spatial attention mechanisms into the bottleneck to improve feature representation and collect significant contextual information. In addition, EUIS-Net incorporates a region-aware attention module in skip connections, which enhances the ability to concentrate on the region of the injury. To enable thorough information exchange across various network blocks, skip connection aggregation is employed from the network's lowermost to the uppermost block. Comprehensive evaluations are conducted on two publicly available ultrasound image segmentation datasets. The proposed EUIS-Net achieved mean IoU and dice scores of 78. 12\%, 85. 42\% and 84. 73\%, 89. 01\% in the BUSI and DDTI datasets, respectively. The findings of our study showcase the substantial capabilities of EUIS-Net for immediate use in clinical settings and its versatility in various ultrasound imaging tasks.

EUIS-Net: A Convolutional Neural Network for Efficient Ultrasound Image Segmentation

TL;DR

EUIS-Net targets efficient and accurate ultrasound image segmentation by combining a compact four-block encoder–decoder architecture with attention-enhanced bottlenecks. It introduces a Region Aware Attention Module (RAAM) in skip connections and a Channel and Spatial Attention Module (CSAM) in the bottleneck to improve region localization and feature representation. Across BUSI and DDTI datasets, EUIS-Net achieves state-of-the-art IoU and Dice scores, while maintaining lower computational complexity, and demonstrates generalization to chest X-ray segmentation. The work highlights practical clinical applicability and points to semi-supervised extensions for reducing data requirements and broader use in medical imaging tasks.

Abstract

Segmenting ultrasound images is critical for various medical applications, but it offers significant challenges due to ultrasound images' inherent noise and unpredictability. To address these challenges, we proposed EUIS-Net, a CNN network designed to segment ultrasound images efficiently and precisely. The proposed EUIS-Net utilises four encoder-decoder blocks, resulting in a notable decrease in computational complexity while achieving excellent performance. The proposed EUIS-Net integrates both channel and spatial attention mechanisms into the bottleneck to improve feature representation and collect significant contextual information. In addition, EUIS-Net incorporates a region-aware attention module in skip connections, which enhances the ability to concentrate on the region of the injury. To enable thorough information exchange across various network blocks, skip connection aggregation is employed from the network's lowermost to the uppermost block. Comprehensive evaluations are conducted on two publicly available ultrasound image segmentation datasets. The proposed EUIS-Net achieved mean IoU and dice scores of 78. 12\%, 85. 42\% and 84. 73\%, 89. 01\% in the BUSI and DDTI datasets, respectively. The findings of our study showcase the substantial capabilities of EUIS-Net for immediate use in clinical settings and its versatility in various ultrasound imaging tasks.
Paper Structure (10 sections, 20 equations, 5 figures, 4 tables)

This paper contains 10 sections, 20 equations, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Proposed Method
  3. Region Aware Attention Module
  4. Channel and Spatial Attention Module
  5. Results and Discussion
  6. Datasets
  7. Evaluation Criteria
  8. Experimental Setup
  9. Comparisons with SOTA Methods
  10. Conclusions

Figures (5)

  • Figure 1: Schematic of the proposed method.
  • Figure 2: Schematic of the attention modules: (a) region aware attention module, (b) channel and spatial attention module.
  • Figure 3: Visual performance comparison of the proposed EUIS-Net on BUSI BUSIdataset dataset.
  • Figure 4: Visual performance comparison of the proposed EUIS-Net on DDTI DDTI dataset.
  • Figure 5: Visual performance comparison of the proposed EUIS-Net on MC MC_Dataset dataset.