Downloads: 1 | Views: 8 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1
Review Papers | Computer Science and Information Technology | India | Volume 13 Issue 7, July 2024 | Rating: 3.2 / 10
A Comprehensive Review on Machine Learning and Transfer Learning Approaches in Liver Tumor Classification
Sheik Imran [4] | Pradeep N [3]
Abstract: Using improvements in medical imaging technology like CT and MRI scans, liver tumor classification is essential for early detection and therapy planning. Nonetheless, there are several obstacles to overcome due to the variety of tumor features and the requirement for precise and effective classification. By utilizing pre-trained deep learning models, transfer learning has become a viable strategy to address these issues in recent years. Transfer learning improves the efficiency and accuracy of liver tumor classification by enabling models learned on large-scale datasets, like ImageNet, to be modified for medical imaging applications with sparsely labeled data. This paper delves into the use of transfer learning techniques in the classification of liver tumors, emphasizing evaluation metrics, adaption of pre-trained models, and augmentation strategies for dataset enrichment. It also covers the most recent datasets, clinical ramifications, and potential research avenues to increase the effectiveness of transfer learning in this crucial area of medical imaging.
Keywords: CAD, MRI, CT, DL, ML, TL
Edition: Volume 13 Issue 7, July 2024,
Pages: 1034 - 1038