White blood cell classification using multi-hop attention graph neural networks

• Hematopoiesis: This process occurs in the bone marrow, where hematopoietic stem cells (HSCs) divide and differentiate to maintain the balance between blood cell lines. Disorders in this process can cause blood diseases such as anemia, leukocytosis, or thrombocytopenia. • Identification of malignant white blood cells in leukemia: Accurate identification of malignant white blood cells through images is important in diagnosing and treating leukemia. This helps doctors make accurate diagnoses and apply appropriate treatments. • New method using Graph Neural Networks (GNN): The author proposes a method for identifying and classifying white blood cells based on images using the Multi-hop Attention GNN method ( Fig. 1 ), along with the following supporting methods: • YOLO-v10: Used for object detection and image preprocessing through the Centre Net network architecture. • Salp Swam Optimization (SSO): Used to select optimal features of white blood cell images, helping to put these features into each node in the GNN architecture for classification. • Dataset and model performance: The dataset includes 16,027 white blood cell images with a resolution of about 42 pixels per 1 μm, annotated and classified into 9 different types of white blood cells. • The YLSSOGNN model achieves a classification accuracy of 99.18 %, while the YLGNN achieves 99.03 %. • Application of the model: The model can be applied to other image objects thanks to the object recognition function of YOLO-v10 and the classification ability of the graph neural network with SSO optimization technique and the Multi-hop Attention GNN model. The process of creating blood cells (hematopoiesis) occurs in the bone marrow, where Hematopoietic Stem Cells (HSCs) are located. The division and differentiation of hematopoietic stem cells are tightly regulated to ensure a balance between blood cell lineages. Disturbances in the process can lead to blood diseases such as anemia, high White Blood Cell (WBC) count, or thrombocytopenia. Detecting malignant leukemia cells based on images is crucial in diagnosing and treating leukemia, helping doctors make accurate diagnoses, and providing appropriate treatment. The author proposes a new method for recognizing and classifying WBC images using the Multi-hop Attention Graph Neural Networks method. The YOLO-v10 method is used for object detection and image preprocessing through the Centre Net network architecture. The Salp Swarm Optimization (SSO) method is deployed to select the features of the WBC images optimally and put the image features into each node in the architecture of the Graph Neural Network (GNN) model to perform classification. The dataset used has an image quality of approximately 42 pixels per 1 μm resolution with a total of 16,027 annotated White Blood Cell images classified into 9 types of WBC with characteristic images of clinically significant pathologies. The classification accuracy of the system of the YLSSOGNN model is 99.18 %, and the classification accuracy of the system of the YLGNN model is 99.03 %. The WBC image recognition and classification model using the post-learning method has a GNN architecture with object recognition function using the YOLO-v10 method and feature extraction and optimization using the SSO method and performs WBC image classification using Multi-hop Attention Graph Neural Networks model, which helps to bring high performance and can apply the model to other types of image objects.