Winter newsletter 2023
Published 21 Dec. 2023
🛠️ New features of Grand Challenge
Step into the winter enchantment of the Grand Challenge Platform! Our latest newsletter is a snow globe of excitement, swirling with new platform developments that promise to elevate your experience. Glide through the freshly unveiled features, as our platform transforms into a winter wonderland of innovation.
MICCAI 2023 Presence
Grand Challenge took center stage at MICCAI 2023, hosting 13 challenges that garnered attention. Your feedback is valuable; connect with us at support@grand-challenge.org or share your thoughts through our survey on challenges and our viewer.
Enhanced Viewer Functionality
Explore the new ghosting slice depth settings in our viewer, allowing you to customize the visibility of annotations across adjacent slices. Easily track annotations made on previous or upcoming slides for a seamless understanding of the image.Dynamic 4D Image Analysis
Witness a breakthrough in 4D image interpretation. Now, our platform supports intensity-over-time charts for accurate insights into intensity changes over a specific region of interest. Uncover the temporal nuances within your 4D images effortlessly.
Automatic metadata updates on Open Challenges
OpenChallenges empowers participants with the most up-to-date information about relevant challenges, while providing organizers with standardized challenge event templates and intelligence. Open Challenges will regularly index the public Challenges on Grand Challenge so that the metadata will automatically be updated in both places.Direct messages from Challenge organizers
A much sought after feature for challenge organizers is the possibility to directly communicate with their participants. From now on, you can send a direct message to any participant that has submitted a solution to your challenge!
While snowflakes dance on the horizon, catch a glimpse of upcoming challenges, and relish the glow of completed leaderboards. Join us in celebrating the season of progress, where the Grand Challenge Platform evolves into a magical realm of endless possibilities. Let the winter adventure begin!
💡 Blogposts¶
"October 2023 Cycle Report"¶
Read all about the platform improvements from our RSE team in October, including a 50% boost in loading speed for reader studies and refined cost computations which offer challenge organizers a more accurate assessment of running costs based on actual expenses incurred during challenges.
"November 2023 Cycle Report"¶
In the November cycle, the RSE team worked on enhancing user experience by advancing viewer features such as ghosting slice depth settings and dynamic 4D image analysis capabilities. Read more about it in this blog post!
🔦 Highlighted algorithms¶
Lymphocytes detection in immunohistochemistry
With this algorithm an existing model that was able to detect lymphocytes in CD3 and CD8 stained slides of prostate cancer, was generalized to other types of immunohistochemical staining. This algorithm takes whole-slide-images for input and outputs a generic overlay of detected lymphocytes. Try out this algorithm with your own data!
Colon Budding in IHC
This algorithm automatically detects all tumor buds in colon whole-slide-images with a sensitivity of 0.91 using the developed Faster-RCNN network. The output of the algorithm is a generic overlay highlighting the detected tumor buds, which can be viewed online and downloaded. Try out this algorithm with your own data!🚀 Upcoming and running challenges¶
Grand Challenge currently offers two types of submissions: prediction submission and algorithm container submission. The algorithm container submission type has the advantage of producing reproducible algorithms that remain accessible to the research community long after the challenge has ended. This allows for continued use and exploration of the algorithms by the community. Therefore, it should be noted that we are phasing out the prediction submission procedure in favour of the algorithm submission procedure to ensure that challenges always produce reproducible algorithms. To learn more about hosting a challenge on our platform, go to our documentation!
🥅 Goal: The PANORAMA Challenge focuses on detecting pancreatic cancer in contrast-enhanced CT scans.
✍️ Register: Registration is now open!
⏰ Deadline: Accepting AI algorithm submissions for Open Development Phase from February, 2024.
🥅 Goal: The CHAIMELEON Challenges focuses on 5 types of cancer, with the first challenge phase focusing on prostate and lung cancer to predict different clinical endpoints such as disease staging, treatment response, or progression-free survival.
✍️ Register: Registration is now open!
⏰ Deadline 1: The Classification Phase will extend until to December 31st, 2023.
⏰ Deadline 2: The Championship Phase will extend from January 1st 2024 to February 29th, 2024.
🏆 Prize per cancer type:
1. €6.000,-
2. €5.000,-
3. €4.000,-
4. €3.000,-
5. €2.000,-
🏆 Leaderboard of finished challenges¶
The task for this challenge was to provide a comprehensive benchmark for cephalometric landmark detection methods. The winner of the testing set was Chenglong Ma. Congratulations! Top performing teams will be invited to contribute to a challenge overview paper, which will be submitted to a high impact journal (MedIA/TMI).
The task for this challenge was to detect cells from cell tissue interaction. The winner of the testing set was Li Wangkai. Congratulations! Top-performing teams in the test leaderboard will be invited as co-authors of the manuscript.
The task for this challenge was two-fold: to benchmark coronary artery segmentation as well as stenosis detection methods. The winning teams of the segmentation and stenosis challenges were Tidesing and Medipixel, respecitvely. Congratulations!
The task for this challenge was to extract the Circle of Willis angio-architecture from 3D angiographic imaging by segmentation of the vessel components. Participants could choose from two tracks (CTA or MRA modality) and consisted of 2 tasks (binary segmentation and multi-class vessel anatomical segmentation). The winning teams were Williwillswissen and Sjtu_Eiee_2-426lab. Congratulations! The challenge results will be summarized and published in a journal manuscript. All participants with a (reasonable) submission are invited to contribute to our challenge publication!
The task for this challenge was to automatically detect and track surgical instruments in endoscopic video. The winning team was Pumch. Congratulations!
Numerous successful MICCAI challenges have concluded on Grand Challenge, with winning algorithms and teams showcased on our Completed Challenge page. A great applause to all participating teams for their outstanding contributions and achievements!
