Blood Slide Image Analysis to Classify WBC Types for Prediction Haematology Based on a Hybrid Model of CNN and Handcrafted Features

Abstract

White blood cells (WBCs) are one of the main components of blood produced by the bone marrow. WBCs are part of the immune system that protects the body from infectious diseases and an increase or decrease in the amount of any type that causes a particular disease. Thus, recognizing the WBC types is essential for diagnosing the patient’s health and identifying the disease. Analyzing blood samples to determine the amount and WBC types requires experienced doctors. Artificial intelligence techniques were applied to analyze blood samples and classify their types to help doctors distinguish between types of infectious diseases due to increased or decreased WBC amounts. This study developed strategies for analyzing blood slide images to classify WBC types. The first strategy is to classify WBC types by the SVM-CNN technique. The second strategy for classifying WBC types is by SVM based on hybrid CNN features, which are called VGG19-ResNet101-SVM, ResNet101-MobileNet-SVM, and VGG19-ResNet101-MobileNet-SVM techniques. The third strategy for classifying WBC types by FFNN is based on a hybrid model of CNN and handcrafted features. With MobileNet and handcrafted features, FFNN achieved an AUC of 99.43%, accuracy of 99.80%, precision of 99.75%, specificity of 99.75%, and sensitivity of 99.68%.

Efficient Malaria Parasite Detection From Diverse Images of Thick Blood Smears for Cross-Regional Model Accuracy

“…They achieved this by using an average value filter to enhance the image and employing a hybrid model based on CNN and manual features. This approach yielded an impressive accuracy rate of 99.8% [20]. Ghosh et al employed gradient-based region growing with neighbourhood influence to achieve a more accurate recovery of region boundaries and classification of WBCs.…”

“…In most studies, automatic detection is performed on light microscopy images because light microscopy is widely used for malaria diagnosis in resource-restricted regions [7]. Currently, the segmentation of WBCs in thin blood smears using color gamut space, combined with deep learning techniques for classifying and counting WBCs, has been extensively researched across various diseases, yielding significant and promising results [18], [19], [20]. Our study focuses on preprocessing techniques aimed at eliminating redundant details, such as WBCs and artifacts, from the acquired images.…”