tsta

Home / سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران

Benchmarking Class Activation Map Methods for Explainable Brain Hemorrhage Classification on Hemorica Dataset

Authors :

Zahra Rafati¹ Mohamad Hoseyni² Javad Khoramdel³ Amirhossein Nikoofard⁴

1- دانشگاه صنعتی خواجه نصیرالدین طوسی 2- دانشگاه صنعتی خواجه نصیرالدین طوسی 3- دانشگاه تربیت مدرس 4- دانشگاه صنعتی خواجه نصیرالدین طوسی

Keywords :

Explainable Artificial Intelligence،Class Activation Map،Brain Hemorrhage Classification،Deep Learning

Abstract :

Explainable Artificial Intelligence (XAI) has become an essential component of medical imaging research, aiming to increase transparency and clinical trust in deep learning models. This study investigates brain hemorrhage diagnosis with a focus on explainability through Class Activation Mapping (CAM) techniques. A pipeline was developed to extract pixellevel segmentation and detection annotations from classification models using nine state-of-the-art CAM algorithms, applied across multiple network stages, and quantitatively evaluated on the Hemorica [1] dataset, which uniquely provides both slice-level labels and high-quality segmentation masks. Metrics including Dice, IoU, and pixel-wise overlap were employed to benchmark CAM variants. Results show that the strongest localization performance occurred at stage 5 of EfficientNetV2-S, with HiResCAM yielding the highest bounding-box alignment and AblationCAM achieving the best pixel-level Dice (≈ 0.57) and IoU (≈ 0.40), representing strong accuracy given that models were trained solely for classification without segmentation supervision. To the best of current knowledge, this is among the first works to quantitatively compare CAM methods for brain hemorrhage detection, establishing a reproducible benchmark and underscoring the potential of XAI-driven pipelines for clinically meaningful AI-assisted diagnosis.