Back to all papers

Improving Parameter-Efficient Medical Image Classification with Lesion-Aware Hierarchical Knowledge Distillation.

September 11, 2026pubmed logopapers

Authors

Liu Y,Xie R,Xie X,Zheng H

Affiliations (2)

  • School of Computer Science and Engineering, Guilin University of Technology, Guilin 541006, China.
  • Guangxi Key Laboratory of Embedded Technology and Intelligent System, Guilin University of Technology, Guilin 541006, China.

Abstract

Compact deep models are attractive for medical image classification, but conventional knowledge distillation mainly transfers class-level predictions and may not adequately preserve lesion-relevant spatial cues. To address this limitation, we propose LaHKD, a lesion-aware hierarchical knowledge distillation framework for parameter-efficient medical image classification. LaHKD enables a lightweight student to learn hierarchical semantic representations together with lesion-focused guidance from a stronger teacher. We evaluate LaHKD on HAM10000 dermoscopic lesion classification and a brain tumor MRI classification benchmark. Across both datasets, LaHKD improves compact-student classification performance, with the clearest lesion-focused spatial benefits observed on HAM10000, where lesion morphology is central to diagnosis and direct lesion supervision is available. On the magnetic resonance imaging (MRI) benchmark, localization analysis is limited to an auxiliary recovered-mask subset and is therefore interpreted as exploratory; under this setting, consistent localization gains are not observed. Overall, LaHKD provides an effective framework for compact medical image classification, with spatial benefits most clearly supported in tasks with reliable lesion supervision.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAISlice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.