An efficient lymphocytic leukemia detection based on EfficientNets and ensemble voting classifier. Issue 1 (6th July 2022)

• Record Type: Journal Article
• Authors: Baby, Diana; Juliet, Sujitha; Anishin Raj, M. M.
• Is Part Of: International journal of imaging systems and technology. Volume 33:Issue 1(2023)
• Page Start: 419
• Page End: 426
• Publication Date: 2022-07-06
• Subjects: classification -- EfficientNet -- leukemia detection -- transfer learning -- voting classifier; Imaging systems -- Periodicals; Image processing -- Periodicals; 621.367
• DOI: 10.1002/ima.22787
• Languages: English
• ISSNs: 0899-9457

Abstract

Abstract: Early detection of leukemia increases the chances of a speedier recovery. If a patient exhibits any symptoms, doctors would often examine a blood sample slide under a microscope to detect hematological malignancies. Manually categorizing leukocytes as normal or abnormal requires examining the many characteristics of the cells, which is time‐consuming and error‐prone. This research aims to create a transfer learning‐based Acute Lymphocytic Leukemia (ALL) detection system that is both efficient and easy. To overcome the critical challenges associated with feature extraction, we used EfficientNet, the most recent and most substantial deep learning model. In this article, eight EfficientNets variations are used to extract features and are compared based on classification accuracy. This work uses an ensemble of three sophisticated classifiers, namely Support Vector Machine (SVM), Random Forest, and Logistic Regression, which achieves a classification accuracy of 98.5%.