A Unified CNN-Based Instance Segmentation Architecture for Blood Cell Classification and Early Cancer Abnormality Recognition
Nathaniel H. Dumayas, Rhomwell Ace C. Merced, Kenniniah A. Rit, Gabriel Marc B. Verzosa, Lysa V. Comia
Abstract
This study presents a YOLOv11-YOLOv12based deep learning framework for automated detection, segmentation, and classification of five hematologic cell types—Basophil, Erythroblast, Monocyte, Myeloblast, and Segmented Neutrophil-from microscopic blood images. A dataset of annotated cell images was preprocessed and augmented to enhance model generalization, and transfer learning was applied to optimize performance on unseen samples. Quantitative evaluations demonstrated exceptional accuracy, with mAP50 scores exceeding 0.99 for both bounding box and mask predictions, an overall [email protected] of 0.992, and F1-scores peaking at 0.98. Precision-recall, precision-confidence, and recall-confidence curves further confirmed stable highconfidence behavior across all classes. Qualitative assessments showed accurate delineation of cell morphology under varying staining conditions, with minor misclassification observed only in morphologically similar cells. The system also achieved realtime inference speeds of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$0.2-0.4$</tex> seconds per image and was deployed via a Gradio web interface to enable immediate visualization of detection outputs. These findings demonstrate that the proposed YOLO-based framework delivers fast, accurate, and robust performance, establishing a viable foundation for AI-assisted hematological screening and supporting future integration into clinical diagnostic workflows.