Multiple Types of Cancer Classification Using CTMRI Images Based on Learning Without Forgetting Powered Deep Learning Models

DOI

10.2991/978-94-6463-858-5_256How to use a DOI?

Keywords

Pretrained models; Bayesian optimization; cancer; convolutional neural networks (CNN); transfer learning; learning without for-getting; Mobile net; DenseNet; VGG16; and VGG19

Abstract

Almost one in six deaths worldwide is due to infection, although the speed and accuracy of conventional diagnostic techniques are limited. Medical image analysis, such as CT and MRI scans, can now be done more quickly and accurately thanks to artificial intelligence (AI), which has become a potent tool for automating cancer detection (HealthITAnalytics, 2021). Lung, breast, and brain tumors are among the many cancers that deep learning models, and convolutional neural networks (CNNs) in particular, have demonstrated impressive success in classifying (Masud et al., 2021; Alanazi et al., 2021). By using pre-trained architectures such as VGGNet and MobileNet, which have been optimized for medical imaging tasks, transfer learning improves these models (Subramanian, 2022). Catastrophic forgetting, in which models lose previously learned information, is a significant obstacle. While adapting to new data, strategies such as Learning without Forgetting (LwF) assist in maintaining initial capabilities (Krishnamoorthy et al., 2022). The performance of the model is further enhanced by hyperparameter optimization, such as Bayesian techniques (Subramanian et al., 2022). This study investigates the use of optimized deep learning models for AI-driven classification of eight types of cancer. We hope to improve on current diagnostic accuracy while preserving model adaptability by combining transfer learning, LwF, and hyperparameter tuning. These results support earlier detection and improved patient outcomes in AI-assisted cancer care (Roy et al., 2022; Rezayi et al., 2021).

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  - Avudurthi SaiKiran
AU  - D. Sarala
AU  - P. Raja Rajeshwari
AU  - Abhiram
AU  - K. Shiva Sai Prasad
PY  - 2025
DA  - 2025/11/04
TI  - Multiple Types of Cancer Classification Using CTMRI Images Based on Learning Without Forgetting Powered Deep Learning Models
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 3065
EP  - 3075
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_256
DO  - 10.2991/978-94-6463-858-5_256
ID  - SaiKiran2025
ER  -