Search
What are you looking for?
Start main content

Press Releases

Press Releases

https://www.med.cuhk.edu.hk/press-releases/cuhk-research-team-develops-an-ai-system-for-detecting-covid-19-infections-in-ct-with-a-privacy-preserving-multinational-validation-study
https://www.med.cuhk.edu.hk/press-releases/cuhk-research-team-develops-an-ai-system-for-detecting-covid-19-infections-in-ct-with-a-privacy-preserving-multinational-validation-study

CUHK Research Team Develops an AI System for Detecting COVID-19 Infections in CT with a Privacy Preserving Multinational Validation Study

A multidisciplinary research team from The Chinese University of Hong Kong (CUHK) has developed an artificial intelligence (AI) system for the automated, rapid and accurate detection of COVID-19 infections in chest computed tomography (CT) images. The team was led by Professor Qi DOU and Professor Pheng Ann HENG from the Department of Computer Science and Engineering, Faculty of Engineering, Dr. Tiffany SO and Professor Simon YU from the Department of Imaging and Interventional Radiology, Faculty of Medicine.  

 

Using new federated learning techniques, the AI system is trained on multicentre data in Hong Kong without the need to centralise data in one place, thus protecting patient privacy. “The established AI system is validated on multiple, unseen, independent external cohorts from mainland China and Europe, showing the potential and feasibility to build large-scale medical datasets with privacy protection, so as to rapidly develop reliable AI models amidst a global disease outbreak such as the COVID-19 pandemic,” said Professor Qi DOU from the Department of Computer Science and Engineering. A recent research article describing the outcomes from the study has been published in the npj Digital Medicine, part of the Nature Partner Journals series.

 

Multidisciplinary research team from CUHK has developed an AI system for the detection of COVID-19 infections in chest CT images.

A multidisciplinary research team from CUHK has developed an artificial intelligence (AI) system for the automated, rapid and accurate detection of COVID-19 infections in chest computed tomography (CT) images.

The research team includes: Mr. Quande LIU (1st from right), PhD student, and Prof. Qi DOU (2nd from left), Assistant Professor, Department of Computer Science and Engineering; and Dr. Tiffany SO(1st from left), Assistant Professor, and Prof. Simon YU (2nd from right), Chairman, Department of Imaging and Interventional Radiology, Faculty of Medicine; CUHK.

Accurate COVID-19 CT lesion detection with federated deep learning 

 

COVID-19 has presented a public health crisis worldwide. In Hong Kong, even with advanced healthcare service systems, the rapidly evolving COVID-19 pandemic has been overwhelming the existing clinical systems and burdening frontline radiologists with an unprecedentedly large emergency workload for data analysis and medical image interpretation. Given this situation, automated diagnostic methods with AI are extremely helpful to facilitate effective management of COVID-19.  

 

Radiological imaging can play a complementary role together with clinical diagnostic testing in COVID-19 diagnosis, and can effectively assess the severity and progression in the course of disease. The team in close collaboration with engineering and clinical experts has developed an accurate AI system for automated detection of COVID-19 lesions from CT images, which can provide immediately available results, alleviating the burden of clinicians in interpreting images. Professor Pheng Ann HENG from the Department of Computer Science and Engineering said, “Making use of the cutting-edge federated learning techniques, the AI system can effectively coordinate the patient data across multiple clinical centres in Hong Kong, including Prince of Wales Hospital, for model development. Given the unavoidable challenge of data heterogeneity in medical images, multicentre collaborative effort is essential to capture diverse data distributions, which enhances model reliability for unleashing the potential of AI-powered medical image diagnosis in complex clinical practice.”

prof simon yu
Prof. Simon YU believes that AI, which protects patient privacy and achieves reliable generalisability in practice, has enormous potential to revolutionise smart hospitals and healthcare systems in Hong Kong and worldwide.
Dr Tiffany SO
Dr. Tiffany SO states that review and interpretation of a single chest CT takes at least 5-10 minutes for clinicians in traditional clinical diagnosis. In contrast, the AI system can accurately evaluate the same CT data in around 40 ms, showing immense potential to support real-time clinical practice.
prof qi dou
Professor Qi DOU states that the established AI system is validated on multiple independent cohorts, showing the potential and feasibility to build large-scale medical datasets with privacy protection, so as to rapidly develop reliable AI models amidst a global disease outbreak such as the COVID-19 pandemic.

Model robustness and generalisability on multi-national validation cohorts

 

The established AI model has been externally validated on multiple unseen cohorts from mainland China and Germany. Experimental outcomes revealed that the AI model yields a competitive performance in lesion detection in comparison with radiologist interpretation of chest CT across local, regional and global patients. This wide validation and applicability on cohorts with various imaging scanners and different demographics show outstanding robustness and generalisability of the established AI model in complex real-world situations. Dr. Tiffany SO, Assistant Professor from the Department of Imaging and Interventional Radiology at the Faculty of Medicine, stated, “Besides a high diagnostic accuracy, the AI system can also present a remarkable speed advantage to clinician interpretation. In traditional clinical diagnosis, review and interpretation of a single chest CT takes at least 5-10 minutes for clinicians. In contrast, the AI system can accurately evaluate the same CT data in around 40 ms, showing immense potential to support real-time clinical practice.”

 

Video introducing the multidisciplinary research team.

 

This latest study demonstrates the use of privacy preserving AI in responding to a global disease outbreak. In the rapidly evolving pandemic of COVID-19, there is apparently no time to set up complicated data sharing agreements across institutions or even countries. Professor Simon YU, Professor and Chairman of the Department of Imaging and Interventional Radiology at the Faculty of Medicine, added, “Privacy preserving machine learning acts as an important enabler under such situations to gather efforts on digital medicine technology for providing reliable clinical assistance for timely patient care. This study demonstrates the feasibility and efficacy of federated learning for COVID-19 image analysis, where collaborative effort is especially valuable at a time of global crisis. More importantly, beyond assisting COVID-19 management, we believe that AI, which protects patient privacy and achieves reliable generalisability in practice, has enormous potential to revolutionise smart hospitals and healthcare systems in Hong Kong and worldwide.”

More Press Releases

CUHK Identifies Outcome Indicators for Benign Prostatic Hyperplasia Patients Receiving Prostatic Artery Embolisation

CUHK Identifies Outcome Indicators for Benign Prostatic Hyperplasia Patients Receiving Prostatic Artery Embolisation

Research
CUHK Proves Modified HIFU Treatment Effective for Treating Uterine Fibroids

CUHK Proves Modified HIFU Treatment Effective for Treating Uterine Fibroids

Research
CUHK Study Proves Ablative Chemoembolization Doubles the Progression-Free Survival for Liver Cancer Patients

CUHK Study Proves Ablative Chemoembolization Doubles the Progression-Free Survival for Liver Cancer Patients

Research
CUHK Proves Prostate Artery Embolization Effective for Benign Prostatic Hyperplasia

CUHK Proves Prostate Artery Embolization Effective for Benign Prostatic Hyperplasia

Research
CUHK’s New Prostatic Artery Embolization Shows 90% Success Rate in Relieving Symptoms of Benign Prostatic Hyperplasia

CUHK’s New Prostatic Artery Embolization Shows 90% Success Rate in Relieving Symptoms of Benign Prostatic Hyperplasia

Clinical service
CUHK Reveals Effectiveness of TEA for Treating Liver Cancer with a 70% Chance of Completely Destroying Tumor

CUHK Reveals Effectiveness of TEA for Treating Liver Cancer with a 70% Chance of Completely Destroying Tumor

Research
Radiotherapy to Head and Neck Raises Risk for Stroke CUHK Proved Effectiveness of Carotid Angioplasty and Stenting

Radiotherapy to Head and Neck Raises Risk for Stroke CUHK Proved Effectiveness of Carotid Angioplasty and Stenting

Research
CUHK Succeeded in Animal Study and Clinical Case of Percutaneous Nanoknife New Breakthrough in Cancer Treatment

CUHK Succeeded in Animal Study and Clinical Case of Percutaneous Nanoknife New Breakthrough in Cancer Treatment

Research
Good News for Asian Patients First Local Clinical Study Shows High Success Rate and Effectiveness of Stenting for Intracranial Stenosis in Preventing Ischaemic Stroke

Good News for Asian Patients First Local Clinical Study Shows High Success Rate and Effectiveness of Stenting for Intracranial Stenosis in Preventing Ischaemic Stroke

Research
CUHK Proves the Potent Efficacy of Stenting for Carotid Artery Narrowing and Cardiac Contractility Modulation for Heart Failure

CUHK Proves the Potent Efficacy of Stenting for Carotid Artery Narrowing and Cardiac Contractility Modulation for Heart Failure

Research
CU Medicine Study Proves Pocket-size Mobile Echocardiographic Screening Device Effective in Detecting Thoracic Aortic Aneurysm

CU Medicine Study Proves Pocket-size Mobile Echocardiographic Screening Device Effective in Detecting Thoracic Aortic Aneurysm

Research
CUHK Deepening Ties with World Leading Institutes for Transdisciplinary Medical Robotics Research to Reshape the Future of Diagnosis and Treatment

CUHK Deepening Ties with World Leading Institutes for Transdisciplinary Medical Robotics Research to Reshape the Future of Diagnosis and Treatment

International collaboration
CUHK Sets up the Global First Research Registry on Early Onset Dementia in Chinese Population

CUHK Sets up the Global First Research Registry on Early Onset Dementia in Chinese Population

Research
CUHK Screening Reveals 1 in 3 Older Adults in Community Suffer Brain Small Vessel Disease, Early Prevention Recommended

CUHK Screening Reveals 1 in 3 Older Adults in Community Suffer Brain Small Vessel Disease, Early Prevention Recommended

Clinical service
CUHK and PWH Introduce Leading 3D Imaging System which Reduces Radiation Dosage by 90%

CUHK and PWH Introduce Leading 3D Imaging System which Reduces Radiation Dosage by 90%

Clinical service
CUHK Establishes New Hybrid Cardiovascular Operating Theatre and Multidisciplinary Team Significantly Reducing Operation Time and Risk of Thoracic Aortic Surgery

CUHK Establishes New Hybrid Cardiovascular Operating Theatre and Multidisciplinary Team Significantly Reducing Operation Time and Risk of Thoracic Aortic Surgery

Clinical service
CUHK Discovers Innovative ‘Flow Diverters’ (Pipeline) as Effective Treatment for Cerebral Aneurysms in Asia’s First Clinical Study in Collaboration with Seven Medical Centres

CUHK Discovers Innovative ‘Flow Diverters’ (Pipeline) as Effective Treatment for Cerebral Aneurysms in Asia’s First Clinical Study in Collaboration with Seven Medical Centres

Research
CUHK Proves a Non-invasive Technology Can Successfully Cure Cerebral Arteriovenous Malformation

CUHK Proves a Non-invasive Technology Can Successfully Cure Cerebral Arteriovenous Malformation

Clinical service
CUHK Pioneers MRI Iron Assessment for Thalassemia Children in Southern China

CUHK Pioneers MRI Iron Assessment for Thalassemia Children in Southern China

Clinical service

Our Expert List

Many experts under the Faculty of Medicine are available for media interview.
Please click here for the expert list or contact us.