Prostate Cancer (Diagnosis)NCT07844304
CascadeDiagnose Prostate MRI
An observational study of Prostate Cancer (Diagnosis), run by First Affiliated Hospital of Guangxi Medical University at 6 sites in China.
Trial summary
This multicenter clinical study is evaluating CascadeDiagnose Prostate MRI, an artificial-intelligence software tool that analyzes standard prostate MRI scans-T2-weighted, diffusion-weighted, and ADC images-to help radiologists detect suspicious prostate lesions, estimate cancer risk, and distinguish prostate cancer… Read more about this study
- Who is it for?
- Ages 18 years and older, men only
- Conditions the study is for
- Prostate Cancer (Diagnosis)
- How many people
- 3,000 participants
- Where
- 6 sitesChina
- Study dates
- 1 Oct 2026to 31 Dec 2028
- Phase
- Observational
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 18 years and older
- Men only
- No healthy volunteers
- Adult, Older adult
Study population: The study will enroll at least 2,000 eligible men aged 18 years or older with complete prostate MRI (T2WI, DWI, ADC), definitive pathology with Gleason score, and full clinical data including PSA, age, and medical history-approximately 1,500 retrospectively and 500 prospectively. Key exclusions are severe image artifacts, prior prostate biopsy, surgery, radiotherapy or endocrine therapy, other malignancies, missing key MRI or reference-standard data, and severe systemic disease interfering with assessment. Written informed consent is required prospectively, with a possible waiver for retrospective data per local ethics committee.
Who may be able to join
- Male patients aged ≥ 18 years undergoing prostate MRI examination.
- Complete MRI sequences including at minimum T2WI, DWI, and ADC sequences.
- Definitive pathological diagnosis (prostate biopsy or post-surgical pathology) with complete Gleason-score information.
- Complete clinical data including serum PSA level, age, and prior medical history.
- Patient informed consent (written informed consent required for the prospective phase).
Who cannot join
- Substantial MRI image degradation caused by motion artifacts or metal artifacts that severely impair interpretation.
- Prior prostate biopsy, prostate surgery, radiotherapy, or endocrine therapy.
- Medical history of other malignant neoplasms.
- Missing key MRI data or reference-standard materials required for primary-endpoint evaluation, precluding assessment of primary study outcomes.
- Severe systemic diseases (e.g., heart failure, end-stage renal disease) interfering with imaging assessment or prognostic evaluation.
Trial locations and contacts
6 sites in 1 country. Contact the study team or a site near you to ask about taking part.
6 sites in 1 country
China6 sites
Guigang People's Hospital
Guigang, Guangxi, 537100
Guilin People's Hospital
Guilin, Guangxi, 541002
Liuzhou People's Hospital
Liuzhou, Guangxi, 545006
The First Affiliated Hospital of Guangxi Medical University
Nanning, Guangxi, 530021
The Second People's Hospital of Nanning
Nanning, Guangxi, 530031
Wuzhou Red Cross Hospital
Wuzhou, Guangxi, 543002
About this study
Official title: Evaluation of the Effectiveness and Safety of CascadeDiagnose Prostate MRI: A Multi-Center Clinical Study
This multicenter clinical study is evaluating CascadeDiagnose Prostate MRI, an artificial-intelligence software tool that analyzes standard prostate MRI scans-T2-weighted, diffusion-weighted, and ADC images-to help radiologists detect suspicious prostate lesions, estimate cancer risk, and distinguish prostate cancer from benign conditions. The study will take place at six hospitals in Guangxi and plans to enroll at least 2,000 eligible men aged 18 or older who have had prostate MRI and have confirmed pathology results. It includes a retrospective phase using existing records and a prospective phase in which participants provide written informed consent. The main goals are to measure the system's diagnostic accuracy (AUC, sensitivity, and specificity), compare it with readings by radiologists, assess safety and rates of rejected or indeterminate results, and see whether it improves reading efficiency or helps reduce unnecessary biopsies. To protect patient privacy, raw MRI, medical-record, and pathology data remain inside each hospital; only de-identified, encrypted intermediate results are shared through a secure distributed network. The study requires ethics approval and trial registration before enrollment, and its results may help determine whether this AI tool is safe and effective for clinical use.
Read the detailed description
This study addresses a clinically important gap in prostate cancer diagnosis: although multiparametric MRI is central to detection, PI-RADS interpretation is subject to substantial inter-reader variability and often yields suboptimal discrimination between clinically significant cancer and benign mimics. CascadeDiagnose Prostate MRI is a cascaded deep-learning system that first detects and segments prostatic lesions on T2-weighted, diffusion-weighted, and apparent diffusion coefficient sequences, and then performs malignant-benign classification and Gleason-based risk stratification. The system is designed to provide interpretable, traceable outputs-including sequence and slice references, zonal localization, confidence scores, Grad-CAM heatmaps, and segmentation masks-and to return indeterminate or rejection results when image quality, data integrity, or model confidence is insufficient, rather than forcing a diagnosis. The study will evaluate this system across six tertiary hospitals with diverse MRI vendors, field strengths, and radiologist experience, using both retrospective and prospective validation. A central methodological feature is the Guangxi-wide medical-sharing distributed trusted computing network. Each hospital operates a local edge node; raw MRI, clinical, and pathological data remain within the hospital and are never centrally uploaded. Only de-identified, SM4-encrypted intermediate features and gradient parameters are transmitted to a regional aggregation node for federated model collaboration and multi-center statistical summarization, implementing the principle of "don't move data; move computing power." In the prospective phase, AI analysis and human reading are performed under a locked system version, with pre-specified rules for clinician access to AI outputs. Reading sessions include AI-alone, radiologist-alone, and AI-assisted interpretations to assess diagnostic performance, workflow efficiency, and safety in a real-world setting. The study incorporates rigorous quality control, including local image-quality review, anti-tampering receipts, cross-node audit trails, and full traceability of data, model, threshold, inference, and manual-review versions. It is intended to generate regulatory-grade evidence on diagnostic accuracy, generalization, rejection behavior, and clinical utility while demonstrating a compliant, privacy-preserving infrastructure for multi-center evaluation of healthcare AI.
- Conditions
- Prostate Cancer (Diagnosis)
- Keywords
- Prostate Cancer, MRI, Federated-learning
- Medical subject headings
- Prostatic Neoplasms, Disease
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
| Study group | Role | What they receive |
|---|---|---|
| Test group | Prostate cancer | |
| Control group | Benign prostatic hyperplasia |
What is being measured
The primary outcome is the main question the study is designed to answer.
Adverse Events
All adverse events associated with system usage are documented
Measured: up to 24 weeks
Area under the receiver operating characteristic curve (AUC)
overall diagnostic performance for discriminating prostate cancer from benign lesions
Measured: up to 24 weeks
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted28 Sep 2026
- Study start1 Oct 2026 (estimated)
- Primary completion31 Dec 2028 (estimated)
- Study completion31 Dec 2028 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (3)Papers the sponsor has linked to this study.
- Other trials for Prostate Cancer (Diagnosis)Studies of the same condition, open and under way.
- 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
- Case-control
- Time perspective
- Other
- Enrolment
- 3,000 participants (estimated)
Sponsor and investigators
- Lead sponsor
- First Affiliated Hospital of Guangxi Medical University
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Jiwen Cheng, First Affiliated Hospital of Guangxi Medical University
- Investigators
- Jiwen Cheng, Principal investigator, First Affiliated Hospital of Guangxi Medical University
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07844304
- Sponsor's protocol ID
- 2026-S061
- Status last verified
- Sep 2026
- First submitted
- 16 Sep 2026
- Last updated
- 28 Sep 2026
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: Individual participant data (IPD) will not be shared. This study is conducted under a distributed trusted computing network in which raw MRI, clinical, and pathological data remain stored and processed locally within each participating hospital and are never exported or centrally aggregated. Cross-institutional transmission is limited to de-identified, encrypted intermediate features and gradient parameters, and the aggregation node cannot reconstruct original patient images or personally identifiable information. Sharing IPD would therefore violate the study's data-sovereignty and privacy-protection framework, the requirements of China's Personal Information Protection Law and Data Security Law, and the terms of the multi-center ethics approvals. Only de-identified aggregated summary statistics and study-level results will be reported.
Publications
Heller N, Isensee F, Maier-Hein KH, Hou X, Xie C, Li F, Nan Y, Mu G, Lin Z, Han M, Yao G, Gao Y, Zhang Y, Wang Y, Hou F, Yang J, Xiong G, Tian J, Zhong C, Ma J, Rickman J, Dean J, Stai B, Tejpaul R, Oestreich M, Blake P, Kaluzniak H, Raza S, Rosenberg J, Moore K, Walczak E, Rengel Z, Edgerton Z, Vasdev R, Peterson M, McSweeney S, Peterson S, Kalapara A, Sathianathen N, Papanikolopoulos N, Weight C. The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge. Med Image Anal. 2021 Jan;67:101821. doi: 10.1016/j.media.2020.101821. Epub 2020 Oct 2.
PubMed 33049579Sun H, Qin J, Liu Z, Jia X, Yan K, Wang L, Liu Z, Gong S. Generation driven understanding of localized 3D scenes with 3D diffusion model. Sci Rep. 2025 Apr 24;15(1):14385. doi: 10.1038/s41598-025-98705-6.
PubMed 40274914Dai C, Xiong Y, Zhu P, Yao L, Lin J, Yao J, Zhang X, Huang R, Wang R, Hou J, Wang K, Shi Z, Chen F, Guo J, Zeng M, Zhou J, Wang S. Deep Learning Assessment of Small Renal Masses at Contrast-enhanced Multiphase CT. Radiology. 2024 May;311(2):e232178. doi: 10.1148/radiol.232178.
PubMed 38742970