Abstract
Leukemia is one of the most dangerous types of malignancies affecting the bone marrow or blood in all age groups, both in children and adults. The most dangerous and deadly type of leukemia is acute lymphoblastic leukemia (ALL). It is diagnosed by hematologists and experts in blood and bone marrow samples using a high-quality microscope with a magnifying lens. Manual diagnosis, however, is considered slow and is limited by the differing opinions of experts and other factors. Thus, this work aimed to develop diagnostic systems for two Acute Lymphoblastic Leukemia Image Databases (ALL_IDB1 and ALL_IDB2) for the early detection of leukemia. All images were optimized before being introduced to the systems by two overlapping filters: the average and Laplacian filters. This study consists of three proposed systems as follows: the first consists of the artificial neural network (ANN), feed forward neural network (FFNN), and support vector machine (SVM), all of which are based on hybrid features extracted using Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM) and Fuzzy Color Histogram (FCH) methods. Both ANN and FFNN reached an accuracy of 100%, while SVM reached an accuracy of 98.11%. The second proposed system consists of the convolutional neural network (CNN) models: AlexNet, GoogleNet, and ResNet-18, based on the transfer learning method, in which deep feature maps were extracted and classified with high accuracy. All the models obtained promising results for the early detection of leukemia in both datasets, with an accuracy of 100% for the AlexNet, GoogleNet, and ResNet-18 models. The third proposed system consists of hybrid CNN–SVM technologies, consisting of two blocks: CNN models for extracting feature maps and the SVM algorithm for classifying feature maps. All the hybrid systems achieved promising results, with AlexNet + SVM achieving 100% accuracy, Goog-LeNet + SVM achieving 98.1% accuracy, and ResNet-18 + SVM achieving 100% accuracy.
Highlights
Blood is one of the significant elements of the human body, consisting of 55% plasma and 45% red blood cells (RBCs) [1]
Three sets of techniques were used to analyze the improved images: (1) neural networks and machine learning algorithms based on image segmentation and hybrid feature extraction via Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM), and Fuzzy Color Histogram (FCH); (2) convolutional neural network (CNN) models for extracting deep feature maps and for classifying them on the basis of the transfer learning technique; and (3) hybrid technologies consisting of two blocks each: deep learning and machine learning
This study focused on three CNN models: AlexNet, GoogLeNet, and ResNet-18
Summary
Blood is one of the significant elements of the human body, consisting of 55% plasma and 45% red blood cells (RBCs) [1]. Microscopic examination is the method of diagnosing the lymphocyte types; it involves taking blood or bone marrow samples, which are diagnosed by a pathologist [11]. It has been proven that many of the shortcomings of manual diagnosis and medical imaging can be analyzed and solved by the convolutional neural network (CNN), which has a superior ability to distinguish between normal and blast cells. The two datasets ALL_IDB1 and ALL_IDB2 were analyzed for leukemia diagnosis using several machine and deep learning networks and hybrid techniques. The hybrid technique was applied between CNN models to extract deep features classified using the SVM algorithm, obtaining promising diagnostic performance results. Systems were developed for analyzing blood microscopy images to assist hematologists and experts in making accurate diagnostic decisions.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
