Prostate Cancer (Diagnosis)NCT07760857
Investigation of an Intelligent Centre-adaptive Multi-modal Fusion Framework (Cad- MMFF) to Overcome Unnecessary Prostate Biopsies and Optimize MRI Utilization
An observational study of Prostate Cancer (Diagnosis), run by Chinese University of Hong Kong at 2 sites in Hong Kong.
Trial summary
This study aims to investigate a novel Centre-Adaptive Multi-Modal Fusion Framework (Cad-MMFF) that integrates clinical, ultrasound, and MRI data to improve the detection of clinically significant prostate cancer (csPCa), reduce unnecessary biopsies, and optimize MRI utilization. Read more about this study
- Who is it for?
- Ages 45 years and older, men only
- Conditions the study is for
- Prostate Cancer (Diagnosis)
- How many people
- 400 participants
- Where
- 2 sitesHong Kong
- Study dates
- 1 Jan 2027to 31 Mar 2030
- Phase
- Observational
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 45 years and older
- Men only
- No healthy volunteers
- Adult, Older adult
Study population: The entire cohort of this study will be targeted at patients who are suspected of PCa and indicated for ultrasound-guided and/or MRI-guided targeted prostate biopsy. Brightness-modulated ultrasound data (longitudinal and transverse views with full prostate coverage), pathological outcomes (Gleason score, ISUP GG), pre-biopsy multi-parametric MRI scans, PI-RADS scores, patients demographics and clinical data, will be acquired from January 2023 to August 2026 retrospectively, and from September 2026 to March 2028 prospectively, from the existing database of the Picture Archiving and Communication System (PACS). Informed consent from subjects will be sought only for prospectively enrolled patients, while there will be no interventions involved given its nature of retrospective analysis
Who may be able to join
- Ethnically Chinese men aged ≥ 50
- Suspicion of PCa [elevated PSA (>4-ng/ml) or abnormal DRE/PHI] and indicated for prostate biopsy
- Obtained clinical consent (for prospectively enrolled patients only)
Who cannot join
- Prior biopsy/treatments for PCa
- History of genitourinary cancer
- Poor image quality
- Incomplete imaging scans/clinical data/pathological results
Trial locations and contacts
2 sites in 1 country. Contact the study team or a site near you to ask about taking part.
Hong Kong2 sites
Prince of Wales Hospital
Hong Kong
North District Hospital
Sheung Shui
About this study
Official title: Investigation of an Intelligent Centre-adaptive Multi-modal Fusion Framework (Cad- MMFF) to Overcome Unnecessary Prostate Biopsies and Optimize MRI Utilization: a Hybrid Retrospective-prospective Study
This study aims to investigate a novel Centre-Adaptive Multi-Modal Fusion Framework (Cad-MMFF) that integrates clinical, ultrasound, and MRI data to improve the detection of clinically significant prostate cancer (csPCa), reduce unnecessary biopsies, and optimize MRI utilization.
Read the detailed description
Approximately 400 Chinese men aged 50 years or above with suspected prostate cancer will be included.The study consists of retrospective model development and prospective model optimization and validation. Two AI models will be developed: a Clinical-US model using clinical and ultrasound data, and a Clinical-US-MRI model incorporating MRI information. The optimized models will subsequently be validated in an independent cohort.
- Conditions
- Prostate Cancer (Diagnosis)
- Keywords
- Modelling
- Medical subject headings
- Prostatic Neoplasms, Disease
What is being measured
The primary outcome is the main question the study is designed to answer.
Area under Receiver-Operating-Curve of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Measured: Through study completion, an average of 1 year
The number of unnecessary biopsy rate decreased of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Measured: Through study completion, an average of 1 year
Proportion of MRI safely saved of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Measured: Through study completion, an average of 1 year
Net-Benefit of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
By Decision Curve analysis
Measured: Through study completion, an average of 1 year
Missed rate of clinically significant prostate cancer of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Measured: Through study completion, an average of 1 year
Detection rate of indolent prostate cancer of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Measured: Through study completion, an average of 1 year
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted12 Aug 2026
- Study start1 Jan 2027 (estimated)
- Primary completion31 Dec 2029 (estimated)
- Study completion31 Mar 2030 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (26)Papers the sponsor has linked to this study.
- Other trials for Prostate Cancer (Diagnosis)Studies of the same condition, open and under way.
- More trials run by Chinese University of Hong KongThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Cohort
- Time perspective
- Prospective
- Enrolment
- 400 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Chinese University of Hong Kong
- Sponsor type
- University, hospital or other
- Collaborators
- The Hong Kong Polytechnic University
- Responsible party
- Principal investigator, NG Chi Fai, Chinese University of Hong Kong
- Investigators
- Chi Fai NG, MBChB, FRCS(Ed), MD, Principal investigator, Chinese University of Hong KongEdmond Sai Kit LAM, PhD, Principal investigator, The Hong Kong Polytechnic University
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07760857
- Sponsor's protocol ID
- CRE-2026.384
- Status last verified
- Oct 2026
- First submitted
- 2 Aug 2026
- Last updated
- 22 Oct 2026
- Results posted
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Publications
TRANSFORM Trial: Trial of Randomised Approaches for National Screening FOR Men (TRANSFORM) [Internet]. ISRCTN registry; 2025 [cited 2026 Mar 28]. ISRCTN13801649.
Centre for Health Protection. Prostate cancer [Internet]. Hong Kong: Department of Health; 2026 [cited 2026 Mar 28]. Available from: https://www.chp.gov.hk/en/healthtopics/content/25/5781.html
Chiu PK, Roobol MJ, Nieboer D, Teoh JY, Yuen SK, Hou SM, Yiu MK, Ng CF. Adaptation and external validation of the European randomised study of screening for prostate cancer risk calculator for the Chinese population. Prostate Cancer Prostatic Dis. 2017 Mar;20(1):99-104. doi: 10.1038/pcan.2016.57. Epub 2016 Nov 29.
PubMed 27897172Hajian-Tilaki K. Sample size estimation in diagnostic test studies of biomedical informatics. J Biomed Inform. 2014 Apr;48:193-204. doi: 10.1016/j.jbi.2014.02.013. Epub 2014 Feb 26.
PubMed 24582925Wu D, Lawhern VJ, Gordon S, Lance BJ, Lin C. Driver Drowsiness Estimation From EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR). IEEE Trans Fuzzy Syst. 2017;25(6):1522-35. doi:10.1109/TFUZZ.2016.2633379
Yue G, Wei P, Zhou T, Song Y, Zhao C, Wang T, Lei B. Specificity-Aware Federated Learning With Dynamic Feature Fusion Network for Imbalanced Medical Image Classification. IEEE J Biomed Health Inform. 2024 Nov;28(11):6373-6383. doi: 10.1109/JBHI.2023.3319516. Epub 2024 Nov 6.
PubMed 37751333Jahanandish H, Sang S, Li CX, Vesal S, Bhattacharya I, Lee JH, et al. Multimodal MRI-Ultrasound AI for Prostate Cancer Detection Outperforms Radiologist MRI Interpretation: A Multi-Center Study [Preprint]. arXiv:2502.00146v1. 2025. doi:10.48550/arXiv.2502.00146
Wei P, Zhou T, Liu W, et al. FedPDN: Personalized federated learning with inter-class similarity constraint for medical image classification through parameter decoupling. IEEE Trans Instrum Meas. 2025; 74:1-13, Art no. 4001213, doi: 10.1109/TIM.2025.3527597
Hao Y, Qiu Z, Holmes J, Lockenhoff CE, Liu W, Ghassemi M, Kalantari S. Large language model integrations in cancer decision-making: a systematic review and meta-analysis. NPJ Digit Med. 2025 Jul 17;8(1):450. doi: 10.1038/s41746-025-01824-7.
PubMed 40676129Rusu M, Jahanandish H, Vesal S, Li CX, Bhattacharya I, Venkataraman R, Zhou SR, Kornberg Z, Sommer ER, Khandwala YS, Hockman L, Zhou Z, Choi MH, Ghanouni P, Fan RE, Sonn GA. ProCUSNet: Prostate Cancer Detection on B-mode Transrectal Ultrasound Using Artificial Intelligence for Targeting During Prostate Biopsies. Eur Urol Oncol. 2025 Apr;8(2):477-485. doi: 10.1016/j.euo.2024.12.012. Epub 2025 Jan 28.
PubMed 39880746Sun YK, Zhou BY, Miao Y, Shi YL, Xu SH, Wu DM, Zhang L, Xu G, Wu TF, Wang LF, Yin HH, Ye X, Lu D, Han H, Xiang LH, Zhu XX, Zhao CK, Xu HX; China Alliance of Multi-Center Clinical Study for Ultrasound (Ultra-Chance). Three-dimensional convolutional neural network model to identify clinically significant prostate cancer in transrectal ultrasound videos: a prospective, multi-institutional, diagnostic study. EClinicalMedicine. 2023 Jun 9;60:102027. doi: 10.1016/j.eclinm.2023.102027. eCollection 2023 Jun.
PubMed 37333662Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021 Feb;18(2):203-211. doi: 10.1038/s41592-020-01008-z. Epub 2020 Dec 7.
PubMed 33288961Correction: Prospective evaluation of artificial intelligence (AI) applications for use in cancer pathways following diagnosis: a systematic review. BMJ Oncol. 2025 May 15;4(1):e000255corr1. doi: 10.1136/bmjonc-2023-000255corr1. eCollection 2025.
PubMed 40519221Teoh JY, Leung CH, Wang MH, Chiu PK, Yee CH, Ng CF, Wong MC. The cost-effectiveness of prostate health index for prostate cancer detection in Chinese men. Prostate Cancer Prostatic Dis. 2020 Dec;23(4):615-621. doi: 10.1038/s41391-020-0243-1. Epub 2020 Jun 30.
PubMed 32606435Gomez Rivas J, Gomez Davila P, Tarrazo Antelo AM, Corujo Quinteiro M, Gomez Amorin A, Rodriguez Alonso A, Vilaseca JM, Lopez H, Salazar JP, Borque-Fernando A, Moreno-Sierra J, Collen S, Beyer K, Helleman J, Roobol MJ, van Poppel H; en representacion de PRAISE-U Consortium. The future of prostate cancer screening in the European Union: PRAISE-U project. Actas Urol Esp (Engl Ed). 2026 Apr;50(3):501919. doi: 10.1016/j.acuroe.2026.501919. Epub 2026 Jan 24. English, Spanish.
PubMed 41587605
Study at a glance
From the registry record, last updated by the sponsor on 22 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Investigation of an Intelligent Centre-adaptive Multi-modal Fusion Framework (Cad- MMFF) to Overcome Unnecessary Prostate Biopsies and Optimize MRI Utilization: a Hybrid Retrospective-prospective Study
- ClinicalTrials.gov ID
- NCT07760857
- Acronym / sponsor ID
- CRE-2026.384
- Conditions
- Prostate Cancer (Diagnosis)
- Keywords
- Modelling
- Study type
- Observational
- Recruitment status
- Not yet recruiting
- Enrolment
- 400 participants (estimated)
- Lead sponsor
- Chinese University of Hong KongUniversity, hospital or other
- Collaborators
- The Hong Kong Polytechnic University
- Study start
- 1 Jan 2027 (estimated)
- Primary completion
- 31 Dec 2029 (estimated)
- Study completion
- 31 Mar 2030 (estimated)
- First posted
- 12 Aug 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
This study aims to investigate a novel Centre-Adaptive Multi-Modal Fusion Framework (Cad-MMFF) that integrates clinical, ultrasound, and MRI data to improve the detection of clinically significant prostate cancer (csPCa), reduce unnecessary biopsies, and optimize MRI utilization.
Detailed description
Approximately 400 Chinese men aged 50 years or above with suspected prostate cancer will be included.The study consists of retrospective model development and prospective model optimization and validation. Two AI models will be developed: a Clinical-US model using clinical and ultrasound data, and a Clinical-US-MRI model incorporating MRI information. The optimized models will subsequently be validated in an independent cohort.
Study design
- Observational model
- Cohort
- Time perspective
- Prospective
Who may qualify
- Ages
- 45 years and older
- Sex
- Male only
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
- Study population
- The entire cohort of this study will be targeted at patients who are suspected of PCa and indicated for ultrasound-guided and/or MRI-guided targeted prostate biopsy. Brightness-modulated ultrasound data (longitudinal and transverse views with full prostate coverage), pathological outcomes (Gleason score, ISUP GG), pre-biopsy multi-parametric MRI scans, PI-RADS scores, patients demographics and clinical data, will be acquired from January 2023 to August 2026 retrospectively, and from September 2026 to March 2028 prospectively, from the existing database of the Picture Archiving and Communication System (PACS). Informed consent from subjects will be sought only for prospectively enrolled patients, while there will be no interventions involved given its nature of retrospective analysis
Key inclusion criteria (3 listed)
- Ethnically Chinese men aged ≥ 50
- Suspicion of PCa [elevated PSA (>4-ng/ml) or abnormal DRE/PHI] and indicated for prostate biopsy
- Obtained clinical consent (for prospectively enrolled patients only)
Key exclusion criteria (4 listed)
- Prior biopsy/treatments for PCa
- History of genitourinary cancer
- Poor image quality
- Incomplete imaging scans/clinical data/pathological results
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Primary outcome
Area under Receiver-Operating-Curve of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Time frame: Through study completion, an average of 1 year
The number of unnecessary biopsy rate decreased of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Time frame: Through study completion, an average of 1 year
Proportion of MRI safely saved of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Time frame: Through study completion, an average of 1 year
Net-Benefit of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Time frame: Through study completion, an average of 1 year
By Decision Curve analysis
Missed rate of clinically significant prostate cancer of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Time frame: Through study completion, an average of 1 year
Detection rate of indolent prostate cancer of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF)
Time frame: Through study completion, an average of 1 year
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 22 Oct 2026.
- BackgroundTRANSFORM Trial: Trial of Randomised Approaches for National Screening FOR Men (TRANSFORM) [Internet]. ISRCTN registry; 2025 [cited 2026 Mar 28]. ISRCTN13801649.
- BackgroundCentre for Health Protection. Prostate cancer [Internet]. Hong Kong: Department of Health; 2026 [cited 2026 Mar 28]. Available from: https://www.chp.gov.hk/en/healthtopics/content/25/5781.html
- Background: PubMed 27897172Chiu PK, Roobol MJ, Nieboer D, Teoh JY, Yuen SK, Hou SM, Yiu MK, Ng CF. Adaptation and external validation of the European randomised study of screening for prostate cancer risk calculator for the Chinese population. Prostate Cancer Prostatic Dis. 2017 Mar;20(1):99-104. doi: 10.1038/pcan.2016.57. Epub 2016 Nov 29.
- Background: PubMed 24582925Hajian-Tilaki K. Sample size estimation in diagnostic test studies of biomedical informatics. J Biomed Inform. 2014 Apr;48:193-204. doi: 10.1016/j.jbi.2014.02.013. Epub 2014 Feb 26.
- BackgroundWu D, Lawhern VJ, Gordon S, Lance BJ, Lin C. Driver Drowsiness Estimation From EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR). IEEE Trans Fuzzy Syst. 2017;25(6):1522-35. doi:10.1109/TFUZZ.2016.2633379
- Background: PubMed 37751333Yue G, Wei P, Zhou T, Song Y, Zhao C, Wang T, Lei B. Specificity-Aware Federated Learning With Dynamic Feature Fusion Network for Imbalanced Medical Image Classification. IEEE J Biomed Health Inform. 2024 Nov;28(11):6373-6383. doi: 10.1109/JBHI.2023.3319516. Epub 2024 Nov 6.
- BackgroundJahanandish H, Sang S, Li CX, Vesal S, Bhattacharya I, Lee JH, et al. Multimodal MRI-Ultrasound AI for Prostate Cancer Detection Outperforms Radiologist MRI Interpretation: A Multi-Center Study [Preprint]. arXiv:2502.00146v1. 2025. doi:10.48550/arXiv.2502.00146
- BackgroundWei P, Zhou T, Liu W, et al. FedPDN: Personalized federated learning with inter-class similarity constraint for medical image classification through parameter decoupling. IEEE Trans Instrum Meas. 2025; 74:1-13, Art no. 4001213, doi: 10.1109/TIM.2025.3527597
- Background: PubMed 40676129Hao Y, Qiu Z, Holmes J, Lockenhoff CE, Liu W, Ghassemi M, Kalantari S. Large language model integrations in cancer decision-making: a systematic review and meta-analysis. NPJ Digit Med. 2025 Jul 17;8(1):450. doi: 10.1038/s41746-025-01824-7.
- Background: PubMed 39880746Rusu M, Jahanandish H, Vesal S, Li CX, Bhattacharya I, Venkataraman R, Zhou SR, Kornberg Z, Sommer ER, Khandwala YS, Hockman L, Zhou Z, Choi MH, Ghanouni P, Fan RE, Sonn GA. ProCUSNet: Prostate Cancer Detection on B-mode Transrectal Ultrasound Using Artificial Intelligence for Targeting During Prostate Biopsies. Eur Urol Oncol. 2025 Apr;8(2):477-485. doi: 10.1016/j.euo.2024.12.012. Epub 2025 Jan 28.
- Background: PubMed 37333662Sun YK, Zhou BY, Miao Y, Shi YL, Xu SH, Wu DM, Zhang L, Xu G, Wu TF, Wang LF, Yin HH, Ye X, Lu D, Han H, Xiang LH, Zhu XX, Zhao CK, Xu HX; China Alliance of Multi-Center Clinical Study for Ultrasound (Ultra-Chance). Three-dimensional convolutional neural network model to identify clinically significant prostate cancer in transrectal ultrasound videos: a prospective, multi-institutional, diagnostic study. EClinicalMedicine. 2023 Jun 9;60:102027. doi: 10.1016/j.eclinm.2023.102027. eCollection 2023 Jun.
- Background: PubMed 33288961Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021 Feb;18(2):203-211. doi: 10.1038/s41592-020-01008-z. Epub 2020 Dec 7.
- Individual participant dataSharing planned: No
Related trials for Prostate Cancer (Diagnosis)
RecruitingPhase 1/2
Docetaxel and SX-682 in Recurrent/Metastatic Head and Neck Squamous Cell Carcinoma, Salivary Gland Carcinoma, and Advanced Prostate Cancer
Head and Neck Cancer, Head and Neck Squamous Cell Carcinoma
Active, not recruiting
Daily Adaptive Post-Prostatectomy With Stereotactic Ablative Radiotherapy in Patients With Prostate Cancer
Malignant Prostate Neoplasm
Enrolling by invitation
Use of Tracking Devices to Locate Abnormalities During Invasive Procedures
Adenocarcinoma, Prostate Neoplasms
RecruitingObservational study
Imaging Studies to Check the Local Response of Prostate Cancer to Radiation Therapy
Prostatic Neoplasms, Prostate Cancer
RecruitingPhase 1
A Study of LY4257496 in Participants With Cancer (OMNIRAY)
Breast Neoplasms, Colorectal Neoplasms
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Chi Fai NG, MBChB, FRCS(Ed), MD principal investigator
Chinese University of Hong Kong
Edmond Sai Kit LAM, PhD principal investigator
The Hong Kong Polytechnic University
2 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Prostate Cancer (Diagnosis), run by Chinese University of Hong Kong at 2 sites in Hong Kong.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 3 inclusion and 4 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 22 Oct 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 2 sites in Hong Kong. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Chi Fai NG, MBChB, FRCS (Surg), MD (852-3505-2625, ngcf@surgery.cuhk.edu.hk), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Area under Receiver-Operating-Curve of using the Centre-adaptive multi-modal fusion framework (Cad-MMFF) (time frame: Through study completion, an average of 1 year). The study lists 6 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07760857, which also lists 26 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 22 Oct 2026.