PI-CAI
PI-CAI (Prostate Imaging: Cancer AI) Public Training and Development Dataset
1500 biparametric prostate MRI exams (T2w, high b-value DWI, ADC) of 1476 men from three Dutch centers, with clinically significant prostate cancer labels, lesion delineations and clinical variables, for csPCa detection.
Overview
PI-CAI is a grand challenge on detecting clinically significant prostate cancer (csPCa, ISUP grade group 2 or higher) in prostate MRI, comparing AI systems with radiologists. Its Public Training and Development Dataset was released in 2022 by the Diagnostic Image Analysis Group at Radboud University Medical Center with partners in Groningen and Twente. This entry covers that public part only. The private training data and the hidden validation and testing cohorts are not released.
Composition
The public set holds 1500 MRI studies from 1476 patients, scanned between 2012 and 2021. 425 studies are labelled csPCa and 1075 contain benign tissue or indolent cancer. 328 cases come from the earlier ProstateX challenge, so the two should not be combined. Each study has an axial T2-weighted image, an axial high b-value diffusion image and an ADC map, and some also have sagittal or coronal T2-weighted images. No contrast-enhanced sequences are included. Images are MHA files, distributed as five zip archives named fold0 to fold4.
Acquisition
Exams were acquired at Radboud University Medical Center, University Medical Center Groningen (the clinical table lists this center as PCNN, Prostaat Centrum Noord-Nederland) and Ziekenhuisgroep Twente. The study protocol reports 1.5T and 3T scanners from Siemens and Philips with surface coils: five Siemens and two Philips scanners in the public set.
Annotations
Labels are maintained in the separate picai_labels repository. Positives are histologically confirmed ISUP 2 or higher; negatives are confirmed by histology (ISUP 1 or lower) or by MRI (PI-RADS 2 or lower), without follow-up. Lesions were delineated in ITK-SNAP by trained investigators supervised by expert radiologists. The original expert masks carry the ISUP grade, while the AI-derived and follow-up masks are binary. Expert masks cover 1295 cases; the remaining 205 positives first had only AI-derived masks and later received expert masks from a follow-up study. AI-derived whole-gland masks and a per-study clinical table (age, PSA, PSA density, prostate volume, biopsy type, PI-RADS and Gleason scores per lesion, center) are included.
Known limitations
- Cases were selected by convenience sampling, so the case mix does not reflect routine care.
- Some patients have several studies with different outcomes, each labelled on its own.
- The README on Zenodo and the study protocol differ slightly on median age and lesion counts.
- The whole-gland masks are automatic and contain known errors.
Cohort
Aggregate numbers from the sources below. Bars are relative to the 1,476 subjects.
Sex
- Male 1,476 100%
Age
mean 65.6± 7.2 · range 35 to 92No age bins reported.
Contrast / sequence
studies, values can overlap
- T2-weighted 1,500 100%
- Diffusion-weighted 1,500 100%
- ADC map 1,500 100%
Condition
studies, values can overlap
- Prostate cancer 653 44%
Country
studies
- Netherlands 1,500 100%
License and access
Our reading of the license, not legal advice. Before you use the data, read the original license and confirm that your use is allowed. We take no responsibility for how you use a dataset. Full disclaimer
Download without an account
Creative Commons Attribution-NonCommercial 4.0 International
Use, share and adapt the data with credit, but only for non-commercial purposes.
What you can do
- No
- Conditional
- Yes
- Yes
What you can share
- Conditional
- Conditional
- Conditional
What you must do
- Yes
- Share alike No
- No
- No
- Manuscript review No
- Release code No
- Return results No
- Delete after use No
Limits
- No
- Location limits No
Citation
Saha A, Bosma JS, Twilt JJ, et al. Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study. Lancet Oncol 2024; 25: 879-887. https://doi.org/10.1016/S1470-2045(24)00220-1
All numbers
Every number on this page, as stored in stats.csv, with its source.
| Measure | Breakdown | Value | Source |
|---|---|---|---|
| Subjects | total | 1,476 | zenodo-6624726 Dataset Characteristics |
| Studies | total one case is one MRI study; some patients have more than one study | 1,500 | zenodo-6624726 Dataset Characteristics |
| Subjects | sex=male all cases are prostate MRI of male patients | 1,476 | saha2022-protocol p. 9, Item 22a |
| Studies | contrast=T2w every case has axial T2w; sagittal and coronal T2w are optional | 1,500 | zenodo-6624726 Imaging Files |
| Studies | contrast=dwi axial high b-value (>= 1000 s/mm2) DWI | 1,500 | zenodo-6624726 Imaging Files |
| Studies | contrast=ADC | 1,500 | zenodo-6624726 Imaging Files |
| Studies | contrast_set=ADC+dwi+T2w | 1,500 | zenodo-6624726 Imaging Files |
| Studies | condition=prostate_cancer studies with case_ISUP >= 1 (any histopathologically confirmed cancer); 425 of them are csPCa (ISUP >= 2) per the Zenodo README | 653 | picai-marksheet case_ISUP |
| Studies | country=NL three centers in the Netherlands | 1,500 | zenodo-6624726 Dataset Characteristics |
| Studies | age=30-49 age at the time of each study | 31 | picai-marksheet patient_age |
| Studies | age=50-59 age at the time of each study | 253 | picai-marksheet patient_age |
| Studies | age=60-69 age at the time of each study | 770 | picai-marksheet patient_age |
| Studies | age=70-79 age at the time of each study | 421 | picai-marksheet patient_age |
| Studies | age=80+ age at the time of each study | 25 | picai-marksheet patient_age |
| Median age | total IQR 61-70; the study protocol Table 1 gives 67 (IQR 61-71) | 66 | zenodo-6624726 Dataset Characteristics |
| Mean age | total over 1500 studies | 65.6 | picai-marksheet patient_age |
| Age SD | total over 1500 studies | 7.2 | picai-marksheet patient_age |
| Minimum age | total over 1500 studies | 35 | picai-marksheet patient_age |
| Maximum age | total over 1500 studies | 92 | picai-marksheet patient_age |
Sources
The keys used in the table above.
- zenodo-6624726 Zenodo record 6624726 v2.0, PI-CAI Public Training and Development Dataset, README.md data
- saha2022-protocol Saha et al. 2022, PI-CAI challenge study protocol (BIAS), Zenodo 6522364 paper
- pi-cai-data-page PI-CAI challenge data page website
- picai-marksheet picai_labels clinical_information/marksheet.csv (CC BY-NC 4.0), one row per study computed
- saha2024 Saha et al. 2024, The Lancet Oncology paper