Lei Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lei Yu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
Cuiyun Gao
Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Saving, Anhui Jianzhu University, Hefei, China
1 shared publicationDaoying Wen
School of Computer and Information, Hefei University of Technology, Hefei, China
1 shared publication- Dongdong Wang
School of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China
1 shared publication - Guangling Sun
School of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China
1 shared publication Jing Wang
The Second Affiliated Hospital, Anhui Medical University, Hefei, China
1 shared publicationLei Shi
School of Computer and Information, Hefei University of Technology, Hefei, China
1 shared publication
Latest Publications
- 21 August 2026
- Published by Springer Nature in Health Information Science and Systems
- Vol. 14 (1) , 81
Medrecord-CLIP: enhancing fundus disease diagnosis via EHR-guided vision-language pre-training
- 21 August 2026
- Published by Springer Nature in Health Information Science and Systems
- Vol. 14 (1) , 81
Medrecord-CLIP: enhancing fundus disease diagnosis via EHR-guided vision-language pre-training
- 29 July 2026
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 23 (4) , 147
MDeepLab: a real-time lightweight network for accurate road crack segmentation
- 29 July 2026
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 23 (4) , 147
MDeepLab: a real-time lightweight network for accurate road crack segmentation
- 28 September 2025
- Published by Springer Nature in Health Information Science and Systems
- Vol. 13 (1) , 1-16
Knowledge-enhanced medical image classification via descriptive priors from large language models
Medical image classification aims to categorise clinically significant imaging patterns, thereby facilitating accurate and timely diagnosis. However, existing approaches predominantly rely on visual features extracted from raw pixel data, often overlooking fine-grained diagnostic cues grounded in medical expertise. To address this limitation, we propose a novel knowledge-enhanced Model, called KEM, that leverages medical large vision-language models (Medical LVLMs) as domain experts to generate descriptive priors, which are used to guide and support clinical decision-making. Specifically, we prompt Medical LVLMs to generate rich, Multi-Dimension clinical descriptions tailored to each input image, capturing nuanced semantics. These descriptive priors are then encoded and fused with visual features through a dual cross-attention module, which enables bidirectional interaction and alignment between modalities. This design allows the model to dynamically attend to both textual and visual cues, thereby enhancing its ability to recognise subtle disease patterns. Comprehensive experiments on four benchmark datasets demonstrate that the proposed method significantly outperforms state-of-the-art vision-only models and exhibits strong generalization across varied clinical settings.
- 28 September 2025
- Published by Springer Nature in Health Information Science and Systems
- Vol. 13 (1) , 1-16
Knowledge-enhanced medical image classification via descriptive priors from large language models
Medical image classification aims to categorise clinically significant imaging patterns, thereby facilitating accurate and timely diagnosis. However, existing approaches predominantly rely on visual features extracted from raw pixel data, often overlooking fine-grained diagnostic cues grounded in medical expertise. To address this limitation, we propose a novel knowledge-enhanced Model, called KEM, that leverages medical large vision-language models (Medical LVLMs) as domain experts to generate descriptive priors, which are used to guide and support clinical decision-making. Specifically, we prompt Medical LVLMs to generate rich, Multi-Dimension clinical descriptions tailored to each input image, capturing nuanced semantics. These descriptive priors are then encoded and fused with visual features through a dual cross-attention module, which enables bidirectional interaction and alignment between modalities. This design allows the model to dynamically attend to both textual and visual cues, thereby enhancing its ability to recognise subtle disease patterns. Comprehensive experiments on four benchmark datasets demonstrate that the proposed method significantly outperforms state-of-the-art vision-only models and exhibits strong generalization across varied clinical settings.