Testing an AI tool that reads prostate MRI scans to help find prostate cancer
Tests an AI software tool reading prostate MRI scans in men.
Plain-language title generated from the registry record
Registry title: CascadeDiagnose Prostate MRI
Key facts
- Where
- Guigang, Guilin, Liuzhou, Nanning, and Wuzhou, ChinaSee the 6 sites
AI summary: who the study is looking for
From the trial's eligibility criteria. Machine-read from the registry text on this page, so it can be wrong. The registry text below and the trial team decide who can take part.
The trial is looking for men aged 18 or older who had a prostate MRI and have a confirmed pathology result. It tests an AI tool that reads prostate MRI scans.
- Age
- 18 years or older
- Sex
- Men only
- Disease stage
- Not specified. A confirmed pathology diagnosis with a Gleason score is needed.
- Earlier treatment
- People who had a prostate biopsy, prostate surgery, radiotherapy or endocrine therapy before cannot join.
- Biomarker or test result
- Serum PSA level must be on record. The MRI must include T2WI, DWI and ADC sequences.
Main reasons for not taking part
- Poor MRI images because of motion or metal artifacts
- Prior prostate biopsy, prostate surgery, radiotherapy or endocrine therapy
- History of another cancer
- Missing key MRI data or reference-standard materials
- Severe systemic disease such as heart failure or end-stage renal disease
Read by machine on 12 November 2026.
Where in China
- Guigang People's HospitalGuigang, ChinaContact: Jiwen Cheng, MD.No longer taking part
- Guilin People's HospitalGuilin, ChinaContact: Jiwen Cheng, MD.No longer taking part
- Liuzhou People's HospitalLiuzhou, ChinaContact: Jiwen Cheng, MD.No longer taking part
- The First Affiliated Hospital of Guangxi Medical UniversityNanning, ChinaContact: Jiwen Cheng, MD.No longer taking part
- The Second People's Hospital of NanningNanning, ChinaContact: Jiwen Cheng, MD.No longer taking part
- Wuzhou Red Cross HospitalWuzhou, ChinaContact: Jiwen Cheng, MD.No longer taking part
Questions to ask the study team
- How often do I need to come in, and for how long each time?
- Are travel costs paid?
- Can I keep my own doctor?
- What happens if I want to stop?
Contact the study team: see the registry record → Contacts and Locations
Print a page for my doctorTrial details
- Who runs it
- First Affiliated Hospital of Guangxi Medical University
- Trial code
- NCT07844304
- Record updated
- 28 September 2026
- Original description
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 full original descriptionShow less
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.
Inclusion: 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).
Exclusion: Prior prostate biopsy, prostate surgery, radiotherapy, or endocrine therapy; Medical history of other malignant neoplasms; Severe systemic diseases (e.g., heart failure, end-stage renal disease) interfering with imaging assessment or prognostic evaluation; Substantial MRI image degradation caused by motion artifacts or metal artifacts that severely impair interpretation; Missing key MRI data or reference-standard materials required for primary-endpoint evaluation, precluding assessment of primary study outcomes.