Enhancing Liver Segmentation: A Deep Learning Approach with EAS Feature Extraction and Multi-Scale Fusion

Abstract

Deep learning technology have been broadly used in segmentation tasks of liver. To address the limitation of suboptimal segmentation for small targets, an end-to-end EAS(ECA-Attention and Separable convolution) U-Net is proposed based on deep learning. The basic module employs depthwise separable convolutional modules instead of convolutional modules to reduce the parameters count and enhance the extraction of deep-layer information. The pyramid module based on Efficient Channel Attention (ECA) is utilized to obtain different receptive fields. And that model can overcome the limitation of the U-Net model with a single receptive field and improve the segmentation capability for targets of different sizes. A deep supervision module with multi-scale output fusion is designed to extract detailed information about liver with high quality. The proposed method is tested on the Liver Tumor Segmentation (LiTS) dataset for liver segmentation, achieving a Dice Similarity Coefficient (DSC) of 92.20% for liver segmentation. Compared to existing models, the proposed method demonstrates higher accuracy in liver segmentation.

Authors and Affiliations

*Weimin WANG, Yufeng LI, Xu YAN, Mingxuan XIAO, and Min GAO

Keywords

Related Articles

Rapid Web Application Development Using Spring Framework: A Case Study

In the agile world, the web application development has to be accurate and economical. One of the best ways to achieve the productivity is by reducing the complexity. The complexity can be reduced by the separation of co...

Disease Prediction System using Support Vector Machine and Multilinear Regression

Evolution of modern technologies like data science and machine learning has opened the path for healthcare communities and medical institutions, to detect the diseases earliest as possible and it helps to provide better...

A Review on Design of Smart Device for UV Radiation Measurement

The sun plays an important role in our health, and too much sun exposure may cause anything from sunburns to skin cancer. Human skin cancer has become a growing health issue. Despite the fact that individuals are aware o...

The Brief study on the Human Nail

A nail is a structure which is not a bone made up of different composition than skin tissue like keratin which is also found in hair and this is also shown as an outer layer of skin for protection. Nail used to protect f...

Free/Open Source Software and Health Care: Benefits and Challenges

Health care occupies an important place in every country. Information technology (IT) can play a vital role to improve the quality, safety and efficiency of health care. But there are several hiccups in wide spread usage...

Download PDF file
  • EP ID EP745021
  • DOI 10.55524/ijircst.2024.12.1.6
  • Views 69
  • Downloads 0

How To Cite

*Weimin WANG, Yufeng LI, Xu YAN, Mingxuan XIAO, and Min GAO (2024). Enhancing Liver Segmentation: A Deep Learning Approach with EAS Feature Extraction and Multi-Scale Fusion. International Journal of Innovative Research in Computer Science and Technology, 12(1), -. https://europub.co.uk/articles/-A-745021