MSAR-Net: A Multi-Scale Residual Network for Automated Detection of Acute Lymphoblastic Leukemia in Microscopic Blood Smear Images

View at publisher Summarise with VIRAT
Authors: Babu H. Hemal, Babu H. Hemal, M. Manickam
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Leukemia involves an abnormal increase in immature white blood cells, making early detection essential. This study introduces MSAR-Net, a deep learning model using multi-scale attention, residual learning, and feature fusion for accurate ALL detection. Enhanced preprocessing and self-supervised learning improve model robustness and generalization. MSAR-Net outperforms traditional CNNs, enabling reliable real-time leukemia diagnosis.

Fields of Study & Subjects

Digital Imaging for Blood Diseases AI in cancer detection Cell Image Analysis Techniques

Publication details

Journal / source
CRC Press eBooks
Pages
272–276
Publication date
31 March 2026
Language
EN
Document type
Book chapter