Publications

A collection of my research work.

Mitigating Entity Hallucinations in 3D Radiology Report Generation via Dual-Stream Alignment

Lingyu Zhou^†, Yue Yu^†, Zhang Yi, Xiuyuan Xu

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2026

Proposed DEAR framework to mitigate entity hallucinations in 3D radiology report generation through dual-stream alignment. AAAI 2026 Poster, CCF-A.

Code

Glance Before You Tell: Anomaly-Guided 3D Radiology Report Generation with Heat-Conduction Slice Encoders

Lingyu Zhou, Dingwen Pi, Zhang Yi, Jun Wu, Xiuyuan Xu

Proceedings of the Conference on Neural Information Processing Systems (NeurIPS) 2026

Proposed HeatRAD, a glance-before-tell framework that routes anomaly-guided slice evidence into an organ-ordered visual prefix for 3D radiology report generation. NeurIPS 2026, CCF-A, Under Review.

Navigate Before You Generate: Volume Evidence Grounding for 3D Radiology Reports

Lingyu Zhou, Dingwen Pi, Jun Wu, Zhang Yi, Xiuyuan Xu

Proceedings of the Conference on Neural Information Processing Systems (NeurIPS) 2026

Proposed Vol-Nav, a volume evidence grounding paradigm for 3D radiology report generation. NeurIPS 2026, CCF-A, Under Review.

ForeMatch: Rethinking Foreground Consistency for Efficient Semi-Supervised 3D Medical Image Segmentation

Lingyu Zhou, Zhengyang Xu, Zhang Yi, Deng Xiong, Xiuyuan Xu

Proceedings of the ACM International Conference on Multimedia (ACM MM) 2026

Proposed ForeMatch for efficient semi-supervised 3D medical image segmentation via foreground consistency. ACM MM 2026, CCF-A.

Code

Prospective Multicenter Validation of a Self-Supervised Deep Learning Model for Predicting Lung Cancer Invasiveness in Pulmonary Nodular Ground Glass Opacities

Ruichen Cui^†, Xiuyuan Xu^†, Nan Chen^†, Lingyu Zhou^†, others

BMJ Journals - Thorax 2026

Self-supervised learning framework for predicting lung cancer invasiveness in GGOs via prospective multicenter validation. BMJ Journals - Thorax, Under Review, IF=8.3.

A Bayesian Deep Learning Model with Consolidation-to-Tumor Ratio (CTR) Prior Revolutionizes the Prediction of Spread Through Air Spaces (STAS) in Stage IA Lung Adenocarcinoma: A Large-Scale Diagnostic Study

Jie Cao^†, Nan Chen^†, Lingyu Zhou^†, others

Translational Lung Cancer Research 2025

Developed a Bayesian deep learning model with CTR prior for predicting STAS in lung adenocarcinoma. Translational Lung Cancer Research, IF=3.5.

Efficient and Gender-Adaptive Graph Vision Mamba for Pediatric Bone Age Assessment

Lingyu Zhou, Zhang Yi, Kai Zhou, Xiuyuan Xu

Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2024

Proposed GGVMamba, a gender-adaptive Graph Vision Mamba framework for pediatric bone age assessment. MICCAI 2024 Poster, CCF-B.

Code

Deep Learning for Precise Diagnosis and Subtype Triage of Drug-Resistant Tuberculosis on Chest Computed Tomography

Shufan Liang, Xiuyuan Xu, Zhe Yang, Qiuyu Du, Lingyu Zhou, others

MedComm 2024

Deep learning framework for drug-resistant tuberculosis diagnosis and subtype triage from chest CT. MedComm, IF=10.7.

LTS-NET: Lung Tissue Segmentation from CT Images using Fully Convolutional Neural Network

Lingyu Zhou, Xiuyuan Xu, Kai Zhou, Jixiang Guo

2021 11th International Conference on Information Science and Technology (ICIST) 2021

Proposed LTS-NET for automated lung tissue segmentation from CT images using FCN. ICIST 2021.