Challenges and solutions of deep learning-based automated liver segmentation: A systematic review

Ghobadi V 1 , Ismail LI 2 , Wan Hasan WZ 3 , Ahmad H 4 , Ramli HR 5 , Norsahperi NMH 6 Show all authors , Tharek A 7 , Hanapiah FA 8

Affiliations 

  • 1 Faculty of Engineering, Universiti Putra Malaysia, Serdang, 43400, Selangor, Malaysia. Electronic address: gs56498@student.upm.edu.my
  • 2 Faculty of Engineering, Universiti Putra Malaysia, Serdang, 43400, Selangor, Malaysia. Electronic address: luthffi.ismail@upm.edu.my
  • 3 Faculty of Engineering, Universiti Putra Malaysia, Serdang, 43400, Selangor, Malaysia. Electronic address: wanzuha@upm.edu.my
  • 4 KPJ Specialist Hospital, Damansara Utama, Petaling Jaya, 47400, Selangor, Malaysia. Electronic address: drharon@gmail.com
  • 5 Faculty of Engineering, Universiti Putra Malaysia, Serdang, 43400, Selangor, Malaysia. Electronic address: hrhr@upm.edu.my
  • 6 Faculty of Engineering, Universiti Putra Malaysia, Serdang, 43400, Selangor, Malaysia. Electronic address: nmhaziq@upm.edu.my
  • 7 Hospital Sultan Abdul Aziz Shah, University Putra Malaysia, Serdang, 43400, Selangor, Malaysia. Electronic address: anastharek@upm.edu.my
  • 8 Faculty of Medicine, Universiti Teknologi MARA, Damansara Utama, Sungai Buloh, 47000, Selangor, Malaysia. Electronic address: fazah@uitm.edu.my
Comput Biol Med, 2024 Dec 05;185:109459.
PMID: 39642700 DOI: 10.1016/j.compbiomed.2024.109459

Abstract

The liver is one of the vital organs in the body. Precise liver segmentation in medical images is essential for liver disease treatment. The deep learning-based liver segmentation process faces several challenges. This research aims to analyze the challenges of liver segmentation in prior studies and identify the modifications made to network models and other enhancements implemented by researchers to tackle each challenge. In total, 88 articles from Scopus and ScienceDirect databases published between January 2016 and January 2022 have been studied. The liver segmentation challenges are classified into five main categories, each containing some subcategories. For each challenge, the proposed technique to overcome the challenge is investigated. The provided report details the authors, publication years, dataset types, imaging technologies, and evaluation metrics of all references for comparison. Additionally, a summary table outlines the challenges and solutions.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.

Similar publications