AI-Driven 3D Liver Segmentation Using Deep Learning and MONAI

DOI

10.2991/978-94-6239-799-6_2How to use a DOI?

Keywords

Three dimensional Medical Imaging; Liver Segmentation; Deep Learning; MONAI; U-Net; CT Imaging

Abstract

An efficient segmentation of the liver in the abdomen computed tomography (CT) images plays an important role in the field of computer-assisted diagnostics, tumor detection, volume measurement, and radiotherapy planning. However, the complexity of the organ’s shape and the low quality of the image make this task laborious and error-prone whether doing manually or semi-automatically. The paper describes a system for automatic three dimensional Liver segmentation based on deep learning implemented with the use of the MONAI toolkit and PyTorch.

For this research, three dimensional abdominal CT scans in the NIfTI format are used. Besides, a specific pre-processing technique, including the following procedures: intensity normalization, re-sampling spatially, correcting the orientation, cropping of the foreground image, and resizing of the images to have the same dimensions, is employed. This was performed using MONAI transforms. For the purpose of Liver region segmentation, a three dimensional U-net network with five levels of encoder-decoder along with batch normalization was used. During training, dice loss function and Adam optimizer were utilized.

The experimental evaluation on various training and test sets illustrates a decrease in the training and validation loss function alongside improved Dice Similarity coefficients. Moreover, qualitative assessment reveals a high level of agreement between the predicted liver masks and ground truth labels.

The results indicate that the proposed MONAI-based deep learning framework can effectively perform end-to-end three dimensional liver segmentation and has the potential to support reliable and efficient clinical workflows in abdominal imaging.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Amrita Priyam
AU  - Umesh Prasad
AU  - Soumitro Chakarvarty
AU  - Mahua Banerjee
AU  - Rishi Raj Choudhary
AU  - Satyam Kumar
PY  - 2026
DA  - 2026/09/30
TI  - AI-Driven 3D Liver Segmentation Using Deep Learning and MONAI
BT  - Proceedings of the International Conference on Emerging Trends and Technologies in Applications of Computer Science (ICETTACS 2026)
PB  - Atlantis Press
SP  - 7
EP  - 28
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-799-6_2
DO  - 10.2991/978-94-6239-799-6_2
ID  - Priyam2026
ER  -