This project implements a CNN to classify WBCs from microscopic images into 8 different classes. The model is trained using stratified 5-fold CV and a weighted random sampler. It supports single/batch inference. All modules conform to an interface file-based grading/evaluation system.
Microscopic blood cell classification using deep learning and image processing techniques.
Academic deep learning project comparing CNNs, Batch Normalization and ResNet18 transfer learning for blood cell image classification.
Deep learning-based blood cell segmentation and classification using U-Net architecture with automated RBC, WBC, and platelet counting. Achieved 92.83% validation accuracy.
Deep learning-based biomedical image classification using ResNet18 for automated peripheral blood cell recognition with Grad-CAM explainability.
Multi-class blood cell classification using CNNs, transfer learning, and data augmentation, evaluated on Codabench.
Deep learning classification of white blood cells using Custom CNN, VGG16 and ResNet18, with transfer learning, data augmentation, Focal Loss and Grad-CAM++ explainability.
A CNN classification model that classifies between blood cells
End-to-end medical computer vision pipeline for blood cell classification, anomaly detection, segmentation, and explainability.
To associate your repository with the blood-cell-classification topic, visit your repo's landing page and select "manage topics."