Abstract
The recognition and classification of White Blood Cell (WBC) play a remarkable role in blood-related diseases (i.e., leukemia, infections) diagnosis. For the highly similar morphology of different WBC subtypes, it is too confused to classify the WBC effectively and accurately for visual observation of blood cell smears. This paper proposes a Deep Convolutional Neural Network (DCNN) with feature fusion strategies, named WBC-AMNet, for automatically classifying WBC subtypes based on focalized attention mechanism. To obtain more localized attention of CNN, the fusion features of the first and the last convolutional layer are extracted by focalized attention mechanism combining Squeeze-and-Excitation (SE) and Gather-Excite (GE) modules. The new method performs successfully in classifying monocytes, neutrophils, lymphocytes, and eosinophils on the complex background with an overall accuracy of 95.66%, better than that of general CNNs. The multi-classification accuracy of WBC-AMNet with the background segmentation is over 98% in all cases. In addition, Gradient-weighted Class Activation Mapping (Grad-CAM) is employed to visualize the attention heatmaps of different feature maps.
Highlights
The analysis of White Blood Cell (WBC) images can assist clinical medicine experts in diagnosing many blood-related disorders such as leukopenia, Acute Leukemia (AL), agranulocytosis, etc
AL is commonly classified into Acute Lymphoblastic Leukemia (ALL) and Acute Myelogenous Leukemia (AML) [1]
The advent of deep learning has led to experimentation with Convolutional Neural Network (CNN) in models for WBC classification [10]
Summary
The analysis of White Blood Cell (WBC) images can assist clinical medicine experts in diagnosing many blood-related disorders such as leukopenia, Acute Leukemia (AL), agranulocytosis, etc. Machine learning methods have been used for image classification of blood cells and have achieved excellent results in medicine. The advent of deep learning has led to experimentation with Convolutional Neural Network (CNN) in models for WBC classification [10]. A recognition system, WBCsNet, based on deep convolution, was proposed to classify five categories on three different public WBC datasets with an accuracy of 96.1% [13]. A classification scheme involving CNN was proposed to classify 17092 images of normal peripheral blood cells with the best overall classification accuracy of 96.2% [14]. As powerful tools to assist physicians in diagnosing blood-related diseases, CNN algorithms still need further research on the generalizable properties and the explicit mechanisms of models detecting WBC images of blood smears.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
