Qiushi Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qiushi Yang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Yixuan Yuan
The Chinese University of Hong Kong
3 shared publications - Meilu Zhu
Department of Mechanical Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong
2 shared publications - Yupei Zhang
Department of Clinical Neurosciences, University of Cambridge, Cambridge, U.K.
2 shared publications - Zhen Chen
The Hong Kong Polytechnic University
2 shared publications - Hao Nan Sheng
Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China
1 shared publication - Hing Cheung So
City University of Hong Kong
1 shared publication
Latest Publications
- 4 September 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 115, 104274
PromptMatch: Semi-supervised visual prompt tuning for medical image classification
- 4 September 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 115, 104274
PromptMatch: Semi-supervised visual prompt tuning for medical image classification
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (9) , 1
PIPA: Prior-Driven Prompting with Diagnosis-Oriented Retrieval-Augmentation for 3D Radiology Report Generation
Automatic radiology report generation has gained increasing attention for its potential to assist in clinical reporting and reduce the workload of radiologists. Existing 3D radiology report generation methods employ multi-modal foundation model to encode volume-text inputs and produce diagnosis reports, while they ignore the characteristics of 3D volumes including much background regions and suffer from generating hallucinations, especially in medical domain that contains many uncommon professional terms. In this paper, we aim to efficiently adapt the pre-trained foundation model to specific 3D radiology report generation, and present a Prior-drIven Prompting with diagnosis-oriented retrieval-Augmentation (PIPA) framework. In PIPA, we design a Prior-drIven Prompting (PIP) strategy to exploit diagnostic knowledge from input volumes and a Diagnosis-oriented volume-report retrievalaugmentation Generation (DIG) module to explore beneficial knowledge from external database. Specifically, in PIP, to take full advantage of the patient's clinical information, e.g., age and symptoms, and the possible disease information, e.g., brain tumor, edema, we formulate them as the patient and disease priors to mine clinical relevant knowledge. Furthermore, we propose utilizing visual and textual embeddings as queries to retrieve similar external data by devising a diagnosis-oriented retrieval-augmentation scheme for leveraging more report resources as references for LLM to produce accuracy outcomes. With PIP and DIG, PIPA integrates clinical priors and external data to learn effective diagnostic representations for high-quality report generation. We evaluate the framework on both public and in-house 3D medical datasets with corresponding reports, demonstrating its strong performance in generating accurate diagnosis reports. Source codes have been published at https://github.com/CUHK-AIM-Group/PIPA/tree/ main.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (9) , 1
PIPA: Prior-Driven Prompting with Diagnosis-Oriented Retrieval-Augmentation for 3D Radiology Report Generation
Automatic radiology report generation has gained increasing attention for its potential to assist in clinical reporting and reduce the workload of radiologists. Existing 3D radiology report generation methods employ multi-modal foundation model to encode volume-text inputs and produce diagnosis reports, while they ignore the characteristics of 3D volumes including much background regions and suffer from generating hallucinations, especially in medical domain that contains many uncommon professional terms. In this paper, we aim to efficiently adapt the pre-trained foundation model to specific 3D radiology report generation, and present a Prior-drIven Prompting with diagnosis-oriented retrieval-Augmentation (PIPA) framework. In PIPA, we design a Prior-drIven Prompting (PIP) strategy to exploit diagnostic knowledge from input volumes and a Diagnosis-oriented volume-report retrievalaugmentation Generation (DIG) module to explore beneficial knowledge from external database. Specifically, in PIP, to take full advantage of the patient's clinical information, e.g., age and symptoms, and the possible disease information, e.g., brain tumor, edema, we formulate them as the patient and disease priors to mine clinical relevant knowledge. Furthermore, we propose utilizing visual and textual embeddings as queries to retrieve similar external data by devising a diagnosis-oriented retrieval-augmentation scheme for leveraging more report resources as references for LLM to produce accuracy outcomes. With PIP and DIG, PIPA integrates clinical priors and external data to learn effective diagnostic representations for high-quality report generation. We evaluate the framework on both public and in-house 3D medical datasets with corresponding reports, demonstrating its strong performance in generating accurate diagnosis reports. Source codes have been published at https://github.com/CUHK-AIM-Group/PIPA/tree/ main.
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (3) , 1503-1514
Order-Optimal Byzantine-Robust Learning Under Heterogeneity via Fair Gradient Clipping
Byzantine-robust distributed or federated learning (FL) refers to providing reliable performance under Byzantine attacks, which violate the prescribed protocols and transmit arbitrary information to the server to hamper the convergence of machine learning (ML) algorithms, via designing resilient aggregation rules to combat attacks. Although numerous robust rules have been suggested, their performance degrades for heterogeneous data. A few techniques have been exploited to handle this problem, but they either require preaggregation operations, hence increasing the computational load, or lack breakdown point analysis of their rules. This article proposes a new aggregation rule, which clips the gradients received from all workers according to the distance between the gradient and the aggregation center. That is, when the distance is larger than the radius $\gamma $ , the gradient will be clipped, and the longer the distance, the closer the clipped gradient is to the center. We theoretically analyze that the breakdown point of the developed rule is 0.5, the maximum value for robust aggregators. Moreover, our rule achieves order-optimal Byzantine-robust training error under data heterogeneity, while the median-based schemes, such as coordinate-wise median (CM) and geometric median (GM), are suboptimal. Experimental results demonstrate that the devised aggregation mechanism can handle different attacks well and outperforms the existing rules.
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (3) , 1503-1514
Order-Optimal Byzantine-Robust Learning Under Heterogeneity via Fair Gradient Clipping
Byzantine-robust distributed or federated learning (FL) refers to providing reliable performance under Byzantine attacks, which violate the prescribed protocols and transmit arbitrary information to the server to hamper the convergence of machine learning (ML) algorithms, via designing resilient aggregation rules to combat attacks. Although numerous robust rules have been suggested, their performance degrades for heterogeneous data. A few techniques have been exploited to handle this problem, but they either require preaggregation operations, hence increasing the computational load, or lack breakdown point analysis of their rules. This article proposes a new aggregation rule, which clips the gradients received from all workers according to the distance between the gradient and the aggregation center. That is, when the distance is larger than the radius $\gamma $ , the gradient will be clipped, and the longer the distance, the closer the clipped gradient is to the center. We theoretically analyze that the breakdown point of the developed rule is 0.5, the maximum value for robust aggregators. Moreover, our rule achieves order-optimal Byzantine-robust training error under data heterogeneity, while the median-based schemes, such as coordinate-wise median (CM) and geometric median (GM), are suboptimal. Experimental results demonstrate that the devised aggregation mechanism can handle different attacks well and outperforms the existing rules.
- 7 March 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 102, 103524
FedBM: Stealing knowledge from pre-trained language models for heterogeneous federated learning
- 7 March 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 102, 103524
FedBM: Stealing knowledge from pre-trained language models for heterogeneous federated learning
- 19 February 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 188, 109772
Long-tailed medical diagnosis with relation-aware representation learning and iterative classifier calibration
- 19 February 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 188, 109772
Long-tailed medical diagnosis with relation-aware representation learning and iterative classifier calibration
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (5) , 3159-3170
Progressive Distillation With Optimal Transport for Federated Incomplete Multi-Modal Learning of Brain Tumor Segmentation
Multi-modal Magnetic Resonance Imaging (MRI) provide sufficient complementary information for brain tumor segmentation, however, most current approaches rely on complete modalities and may collapse with incomplete modalities. Moreover, most existing endeavors focus on training with centralized databases, failing to make full use of distributed multi-silo datasets with rich patient data to learn a more robust brain tumor segmentation model. In this paper, considering the distributed training scenarios, we formulate Federated Incomplete Multi-modal Learning (FedIML) for brain tumor segmentation, and propose Progressive distiLlation with Optimal Transport (PLOT) framework to gradually train a modality robust segmentation model at each client and achieve compatible model aggregation at the server. Specifically, to remedy the issue of unstable local training caused by the random modality input, we present Modality Progressive Distillation (MPD), a multi-level knowledge distillation strategy guided by a modality routing mechanism. At each client, MPD provides a gradually learning course for a student model in an easy-to-hard manner to achieve a stable local training process. Moreover, to address the problem that the layer-wise knowledge from different models may contradict, at the server, we design Optimal Transport-guided Model Aggregation (OTMA) strategy, which yields a global alignment solution for model parameters via solving an optimal transport problem. OTMA can achieve a compatible parameter aggregation and boost the distributed training. Extensive experiments on the BraTS-2021 dataset demonstrate the effectiveness of the proposed framework over state-of-the-art methods.
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (5) , 3159-3170
Progressive Distillation With Optimal Transport for Federated Incomplete Multi-Modal Learning of Brain Tumor Segmentation
Multi-modal Magnetic Resonance Imaging (MRI) provide sufficient complementary information for brain tumor segmentation, however, most current approaches rely on complete modalities and may collapse with incomplete modalities. Moreover, most existing endeavors focus on training with centralized databases, failing to make full use of distributed multi-silo datasets with rich patient data to learn a more robust brain tumor segmentation model. In this paper, considering the distributed training scenarios, we formulate Federated Incomplete Multi-modal Learning (FedIML) for brain tumor segmentation, and propose Progressive distiLlation with Optimal Transport (PLOT) framework to gradually train a modality robust segmentation model at each client and achieve compatible model aggregation at the server. Specifically, to remedy the issue of unstable local training caused by the random modality input, we present Modality Progressive Distillation (MPD), a multi-level knowledge distillation strategy guided by a modality routing mechanism. At each client, MPD provides a gradually learning course for a student model in an easy-to-hard manner to achieve a stable local training process. Moreover, to address the problem that the layer-wise knowledge from different models may contradict, at the server, we design Optimal Transport-guided Model Aggregation (OTMA) strategy, which yields a global alignment solution for model parameters via solving an optimal transport problem. OTMA can achieve a compatible parameter aggregation and boost the distributed training. Extensive experiments on the BraTS-2021 dataset demonstrate the effectiveness of the proposed framework over state-of-the-art methods.
- 2 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (5) , 3171-3183
Unified Multi-Modal Diagnostic Framework With Reconstruction Pre-Training and Heterogeneity-Combat Tuning
Medical multi-modal pre-training has revealed promise in computer-aided diagnosis by leveraging large-scale unlabeled datasets. However, existing methods based on masked autoencoders mainly rely on data-level reconstruction tasks, but lack high-level semantic information. Furthermore, two significant heterogeneity challenges hinder the transfer of pre-trained knowledge to downstream tasks, i.e. , the distribution heterogeneity between pre-training data and downstream data, and the modality heterogeneity within downstream data. To address these challenges, we propose a Unified Medical Multi-modal Diagnostic (UMD) framework with tailored pre-training and downstream tuning strategies. Specifically, to enhance the representation abilities of vision and language encoders, we propose the Multi-level Reconstruction Pre-training (MR-Pretrain) strategy, including a feature-level and data-level reconstruction, which guides models to capture the semantic information from masked inputs of different modalities. Moreover, to tackle two kinds of heterogeneities during the downstream tuning, we present the heterogeneity-combat downstream tuning strategy, which consists of a Task-oriented Distribution Calibration (TD-Calib) and a Gradient-guided Modality Coordination (GM-Coord). In particular, TD-Calib fine-tunes the pre-trained model regarding the distribution of downstream datasets, and GM-Coord adjusts the gradient weights according to the dynamic optimization status of different modalities. Extensive experiments on five public medical datasets demonstrate the effectiveness of our UMD framework, which remarkably outperforms existing approaches on three kinds of downstream tasks.
- 2 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (5) , 3171-3183
Unified Multi-Modal Diagnostic Framework With Reconstruction Pre-Training and Heterogeneity-Combat Tuning
Medical multi-modal pre-training has revealed promise in computer-aided diagnosis by leveraging large-scale unlabeled datasets. However, existing methods based on masked autoencoders mainly rely on data-level reconstruction tasks, but lack high-level semantic information. Furthermore, two significant heterogeneity challenges hinder the transfer of pre-trained knowledge to downstream tasks, i.e. , the distribution heterogeneity between pre-training data and downstream data, and the modality heterogeneity within downstream data. To address these challenges, we propose a Unified Medical Multi-modal Diagnostic (UMD) framework with tailored pre-training and downstream tuning strategies. Specifically, to enhance the representation abilities of vision and language encoders, we propose the Multi-level Reconstruction Pre-training (MR-Pretrain) strategy, including a feature-level and data-level reconstruction, which guides models to capture the semantic information from masked inputs of different modalities. Moreover, to tackle two kinds of heterogeneities during the downstream tuning, we present the heterogeneity-combat downstream tuning strategy, which consists of a Task-oriented Distribution Calibration (TD-Calib) and a Gradient-guided Modality Coordination (GM-Coord). In particular, TD-Calib fine-tunes the pre-trained model regarding the distribution of downstream datasets, and GM-Coord adjusts the gradient weights according to the dynamic optimization status of different modalities. Extensive experiments on five public medical datasets demonstrate the effectiveness of our UMD framework, which remarkably outperforms existing approaches on three kinds of downstream tasks.