Exploring Transfer Learning for BTCV Dataset: A Comparative Study of CNN Architectures

DOI

10.2991/978-94-6463-858-5_221How to use a DOI?

Keywords

Deep Learning; Transfer Learning; BTCV Dataset; Convolutional Neural Networks (CNN); ResNet; VGG; LeNet; AlexNet; Model Comparison; Accuracy Evaluation; Computational Efficiency; Medical Imaging; Multi-Organ Segmentation; Medical Image Analysis; Abdominal Imaging

Abstract

Medical image segmentation is an important task to assist radiologists in accurate diagnosis and treatment planning, particularly for complex anatomical structures. Traditional CNN-based models have demonstrated good performance but often suffer from computationally costly costs and poor generalizability. In this work, we explore the effectiveness of transfer learning on the Beyond The Cranial Vault (BTCV) dataset with pre-trained deep learning models for improved segmentation accuracy. We compare several CNN models like LeNet, AlexNet, ResNet-20, ResNet-50, and transfer learning using ResNet and VGG. Our analysis shows that transfer learning using ResNet delivers the highest accuracy of 97.97%, which is significantly higher than other models. The findings confirm that transfer learning enhances model efficiency and accuracy, making it an effective tool for medical image analysis tasks.

Copyright

© 2025 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  - M. Rekha Sundari
AU  - R. Lalithanjali
AU  - S. Eekshita
AU  - T. Bhavana
PY  - 2025
DA  - 2025/11/04
TI  - Exploring Transfer Learning for BTCV Dataset: A Comparative Study of CNN Architectures
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 2659
EP  - 2670
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_221
DO  - 10.2991/978-94-6463-858-5_221
ID  - Sundari2025
ER  -