The PI-CAI Challenge Banner
Join

Announcements & News📣

📢 1 March 2024: Primary outcomes of the PI-CAI challenge and future follow-up projects were announced in oral presentations during the 2024 European Congress of Radiology (ECR 2024) in Vienna, Austria.



📢27 November 2023: Primary outcomes of the PI-CAI: Reader Study were presented in an oral presentation on 27 November, 8-9 AM CST (Session ID: M1-SSGU03), at this year's 109th Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA 2023) in Chicago, USA.


📢9 November 2023: The PI-CAI Challenge was presented, as an example of  how large-scale studies can benefit from crowdsourcing research products, at this year's Clinical Radiology Research Day of The Royal College of Radiologists, UK. 

📢11 October 2023: Intermediate findings from the PI-CAI challenge, comparing the performance of an ensemble of the top five AI models from the grand challenge in comparison to radiologists participating in the reader study, were presented in an oral presentation at the Annual Meeting of the Society for Advanced Body Imaging (SABI 2023) in Dallas, USA, where our abstract was awarded the "Resoundant Innovation Award".


📢10 July 2023: Diagnostic performance of all state-of-the-art AI solutions from the PI-CAI challenge, when trained using >9100 MRI exams and tested across 1000 multi-center, multi-vendor patient cases (including external data), was just announced in a plenary oral presentation at the Medical Imaging with Deep Learning conference (MIDL 2023) in Nashville, USA.


📢30 April 2023: Winners of the PI-CAI challenge and its post-challenge roadmap will be presented at the Medical Imaging with Deep Learning conference (MIDL 2023) in Nashville, USA from 10-12 July, 2023. See you there!


📢10 March 2023: Preliminary outcomes of the PI-CAI: Reader Study were presented at the 2023 European Congress of Radiology (ECR 2023) in Vienna, Austria, for which the abstract was awarded the "Best Research Presentation Abstract" in the topic of "Oncologic Imaging". Meanwhile, an overview of our study design, key outcomes reached thus far and the roadmap ahead, were presented in the plenary "Game Changing" session at the annual congress of the 38th Annual Congress of the European Association of Urology (EAU 23) in Milan, Italy. For a summary of this talk, you can check out its featured article on UroToday: http://bit.ly/3yuyql1.


📢11 February 2023: Preliminary results of the PI-CAI: Reader Study will be announced in our oral presentations at the 2023 European Congress of Radiology (ECR 2023) in Vienna, Austria and the 38th Annual Congress of the European Association of Urology (EAU 23) in Milan, Italy. See you there!


📢 8 December 2022: The PI-CAI challenge has been featured in the December 2022 issue of RSIP Vision - Computer Vision News  and the RSNA 2022: Daily Bulletin. Thanks to Ralph Anzarouth and Melissa Silverberg for the shout-out!


📢 29 November 2022: Open Development Phase of the PI-CAI challenge has now concluded! All teams can continue to make submissions to the Open Development Phase - Tuning Leaderboard, albeit at a reduced rate (once per week per verified user). Meanwhile, the Open Development Phase - Testing Leaderboard will reopen in early 2023 and accept submissions on a per-application basis to the PI-CAI consortium via e-mail. Please check out this forum thread for more details.

📢 20 October 2022: The PI-CAI challenge will be featured in an upcoming webinar from the MICCAI Special Interest Group for Challenges, titled "How to Run a Challenge?", on 25 October 2022. See you there!




📢 22 September 2022: Deadline for submissions to the Open Development Phase - Tuning Leaderboard has been extended to 20 November 2022 (from 20 October 2022, before). Preliminary results and the top 5 teams of the PI-CAI challenge will be announced in our oral presentation at this year's 108th Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA 2022) in Chicago, USA. 



📢 5 September 2022: Participants can now submit a maximum of 1 AI algorithm per day per verified user to the Open Development Phase - Tuning Leaderboard, instead of 1 AI algorithm per week per team like before. All participants must still form teams (even if the team is composed of a single participant), and each participant can only be a member of a single team. For the full list of participation rules, visit: https://pi-cai.grand-challenge.org/AIPR/ .

📢 8 August 2022: The PI-CAI challenge is now preregistered in compliance with NLM-NIH and BIAS reporting guidelines! To learn more about our end-to-end study design, visit: 

📢 16 June 2022: GitHub repos with our source code for preprocessing prostate MRI data archives, training baseline diagnostic AI models, and evaluating lesion detection and diagnosis performance are now live!

📢 12 June 2022: Open Development Phase - Tuning Leaderboard is now open for AI algorithm submissions! Public Training and Development Dataset v2.0 is now online! Learn more about all the considerations that we've made to curate and release the all-new largest public training dataset (1500 cases) for prostate cancer detection in MRI: pi-cai.grand-challenge.org/DATA/. For all updates/fixes regarding this dataset, please join the challenge and check out our dedicated forum post on this topic.