Explainable Knowledge Distillation for Efficient Medical Image Classification

2025-08-21 · Aqib Nazir Mir, Danish Raza Rizvi arxiv

This study comprehensively explores knowledge distillation frameworks for COVID-19 and lung cancer classification using chest X-ray (CXR) images. We employ high-capacity teacher models, including VGG19 and lightweight Vision Transformers (Visformer-S and AutoFormer-V2-T), to guide the training of a compact, hardware-aware student model derived from the OFA-595 supernet. Our approach leverages hybrid supervision, combining ground-truth labels with teacher models' soft targets to balance accuracy and computational efficiency. We validate our models on two benchmark datasets: COVID-QU-Ex and LCS25000, covering multiple classes, including COVID-19, healthy, non-COVID pneumonia, lung, and colon cancer. To interpret the spatial focus of the models, we employ Score-CAM-based visualizations, which provide insight into the reasoning process of both teacher and student networks. The results demonstrate that the distilled student model maintains high classification performance with significantly reduced parameters and inference time, making it an optimal choice in resource-constrained clinical environments. Our work underscores the importance of combining model efficiency with explainability for practical, trustworthy medical AI solutions.

📄 PDF Abstract BibTeX arXiv:2508.15251

Code (0)

등록된 구현이 없습니다.

Tasks

Medical Image Classification Computational Efficiency Knowledge Distillation Cancer Classification

Unlabeled Data Deployment for Classification of Diabetic Retinopathy Images Using Knowledge Transfer

2020-02-09 · Sajjad Abbasi, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi 외

Convolutional neural networks (CNNs) are extensively beneficial for medical image processing. Medical images are plentiful, but there is a lack of annotated data. Transfer learning is used to solve the problem of lack of…

General Classification Knowledge Distillation Medical Image Analysis Transfer Learning

Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification

2021-07-07 · Xiaohan Xing, Yuenan Hou, Hang Li, Yixuan Yuan 외

The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the …

Classification image-classification Image Classification Knowledge Distillation+2

Multi-Dataset Cross-Domain Knowledge Distillation for Unified Medical Image Segmentation, Classification, and Detection

2026-05-02 · Ceausescu Ciprian-Mihai, Anghelina Ion-Marian, Alexe Dumitru-Bogdan arxiv

We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection…

Medical Image Segmentation Knowledge Distillation Transfer Learning Object Detection

Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classification

2024-06-08 · Yunhe Gao, Difei Gu, Mu Zhou, Dimitris Metaxas

Although explainability is essential in the clinical diagnosis, most deep learning models still function as black boxes without elucidating their decision-making process. In this study, we investigate the explainable mod…

Decision Making Diagnostic image-classification Image Classification+3

A ChatGPT Aided Explainable Framework for Zero-Shot Medical Image Diagnosis

2023-07-05 · Jiaxiang Liu, Tianxiang Hu, Yan Zhang, Xiaotang Gai 외

Zero-shot medical image classification is a critical process in real-world scenarios where we have limited access to all possible diseases or large-scale annotated data. It involves computing similarity scores between a …

Diagnostic image-classification Image Classification Medical Image Classification