The rapid development of digital image processing and machine learning has increased the need for reliable and task-appropriate evaluation methods. However, the wide range of available metrics, each with different assumptions, strengths, and limitations, makes metric selection challenging across diverse image-processing tasks. This article presents a task-oriented review of commonly used evaluation metrics and proposes a practical framework for selecting appropriate metrics across five major categories: image quality assessment, image classification, image segmentation, image restoration, and object detection. Representative metrics are reviewed based on their mathematical basis, interpretat... More >

Breast cancer is a leading cause of cancer-related mortality worldwide, making accurate histopathological subtype discrimination critical for timely clinical intervention. Existing deep learning approaches often evaluate limited settings (binary or multi-class, single magnification), restricting comparative utility and clinical interpretability. This study proposes a unified Cross Stage Partial Network (CSPNet)-based framework for comprehensive classification on the BreaKHis dataset. A CSPResNet50 backbone pre-trained on ImageNet was extended with a multi-scale Feature Pyramid-style aggregation head, Squeeze-and-Excitation channel attention, dual Global Average and Max Pooling per scale (153... More >

Malaria remains a significant global health challenge, causing hundreds of thousands of deaths annually, particularly in tropical and subtropical regions. This study proposes an advanced automated approach for malaria detection by classifying red blood cell images using machine learning and deep learning techniques. Three distinct models: Logistic Regression (LR), Support Vector Machine (SVM), and Inception-V3 were implemented and rigorously evaluated on a dataset comprising 27,558 cell images. The LR model achieved an accuracy of 65.38%, while SVM demonstrated improved classification performance with an accuracy of 84%. The deep learning-based Inception-V3 model outperformed both, achieving... More >