ORIGINAL RESEARCH
J. Abdom. Wall Surg.
Deep Learning in Ventral Hernia Imaging: Automated Multi-Structure CT Segmentation for Surgical Planning
- VR
Vinayak Rengan 1
- PM
Pravin Meenashi Sundaram 2
- EA
Eham Arora 3
- SG
Sabari Girieasen 4
- AB
Ashvind Bawa 5
- NA
Naveen Alexander 6
- RR
Rengan Ravanasamudram Sitaraman 7
- VR
Vimalakar Reddy 8
- VK
Vishakha Kalikar 9
- AA
Aman Arora 10
- LK
Lakshmi Kona 11
- RV
Rochita Venkataramanan 12
- DL
Devansh Lalwani 13
- DM
Dakshin Meenashi Sundaram 14
- RK
Rohit Kalla 15
1. Dr. Mehta's Children's Hospital, Chennai, India
2. Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, United Kingdom
3. Grant Government Medical College and Sir J J Group of Hospitals, Mumbai, India
4. Madras Medical College and Government General Hospital, Chennai, India
5. Dayanand Medical College and Hospital, Ludhiana, India
6. Sri Ramachandra Medical College and Research Institute, Chennai, India
7. Chennai Hernia Centre, Chennai, India
8. KIMS-Sunshine Hospital, Hyderabad, India
9. Zen Multi Speciality Hospital, Chembur, India
10. Army Medical Corps Centre and College, Lucknow, India
11. Yashoda Hospital, Hyderabad, India
12. Advantage Imaging and Research Institute, Chennai, India
13. King Edward Memorial Hospital and Seth Gordhandas Sunderdas Medical College, Mumbai, India
14. Saint Peter's University Hospital, New Brunswick, United States
15. Curium Life Tech, Chennai, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Abstract
Background: Accurate preoperative assessment of ventral hernia defects remains time-intensive and subject to inter-observer variability. Current manual CT analysis for surgical planning is time-consuming, with inconsistent measurements affecting operative decision-making. Methods: 215 CT scans of adults with ventral hernias were analyzed using TransUNet-inspired deep learning models. Expert annotations of anatomical landmarks and hernia features served as ground truth. Models were trained to automate segmentation of hernia defects and other critical anatomical structures. Results: Automated segmentation achieved IoU values of 0.85 for hernia defects, 0.89 for rectus abdominis muscles, 0.87 for lateral abdominal wall muscles, and 0.91 for psoas muscles. Conclusion: Deep learning automation provides rapid, standardized hernia assessment for surgical planning. The system delivers objective measurements with significant time savings, demonstrating technical feasibility as a proof-of-concept that warrants further prospective clinical validation before deployment in operative decision-making.
Summary
Keywords
Artificial intelligence, Computed tomography, computer vision, Hernia imaging, surgical planning
Received
05 September 2025
Accepted
20 July 2026
Copyright
© 2026 Rengan, Meenashi Sundaram, Arora, Girieasen, Bawa, Alexander, Ravanasamudram Sitaraman, Reddy, Kalikar, Arora, Kona, Venkataramanan, Lalwani, Meenashi Sundaram and Kalla. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Vinayak Rengan
Disclaimer
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.