Spring newsletter 2024
Published 8 April 2024
🛠️ New features of Grand Challenge
Welcome to the Spring Edition of Grand Challenge Insights!
Step into the warmth of Spring with our Grand Challenge Spring Newsletter. As nature awakens, so too do our endeavours to tackle the challenges that lie ahead. In this newsletter, we celebrate the blossoming ideas, collaborations, and achievements that define our community. Gear up for a season of growth and innovation!
Enhanced challenge participant logs
Firstly, participants can now access their logs on the hidden test set, enabling them to identify algorithm failures independently, thereby alleviating the burden on challenge administrators to rectify such issues.Enhanced algorithm performance transparency
Additionally, a new section displaying algorithm performance across various datasets has been integrated, enhancing transparency and facilitating informed decision-making among participants.
Improved user interaction with archives
Moreover, enhancements to user experience have been made, particularly around creating and updating archive items and display sets, ensuring smoother navigation and interaction within the platform.Direct messages from Reader study organizers
Furthermore, administrators conducting reader studies now have the capability to directly communicate with participants, fostering better engagement and facilitating seamless management of studies.
Meanwhile, the Grand Challenge Viewer Cirrus has undergone notable advancements to enhance its functionality and usability.
Three-point angle annotations
A new annotation tool allows users to perform three-point annotations, creating angles for more precise analysis and interpretation of data.Expanded Content Support
Furthermore, Cirrus now supports a diverse range of content types including text, video, static images, PDF reports, and Vega-Lite charts, expanding its utility and versatility for users.
As spring unfolds, let's anticipate a year of vibrant innovation, blossoming AI development, and creative growth in our Grand Challenge community. Let's embrace this season's renewal and look forward to a year filled with fresh ideas and fruitful collaborations!
💡 Blogposts¶
"March Cycle Report "¶
The RSE team introduced the ability for Reader study organizers to directly communicate with their reader participants. Check out this feature in more detail in the blog post!
"January Cycle Report"¶
In the January cycle, the RSE team worked on expanding accepted formats by the Cirrus viewer supporting now text, video, static images, PDF reports, and Vega-Lite charts, as well as improvement of user experience by advancing creating and updating archive items and display sets. Read more about it in this blog post!
"December 2023 Cycle Report"¶
Read all about the platform improvements from our RSE team in December, including new access for challenge participants to their logs on the hidden test sets in challenges and a new section per algorithm page to show its performance on datasets used in challenges.
"Organizing a medical imaging challenge in 2020s: practical considerations"¶
Organizing a deep learning challenge in medical imaging is a commendable initiative, as it can help drive advancements in the field and bring together researchers and practitioners to tackle important healthcare problems. In this blog post, key considerations are discussed to keep in mind to ensure the success and integrity of your challenge!
🔦 Highlighted algorithms¶
Universal Lesion Segmentation
This is the baseline algorithm for the ULS23 challenge, and can be used to 3D segment the various lesion types present in the thorax-abdomen area of CT scans. This algorithm takes volumes-of-interest of CT scans for input and outputs a binary segmentation mask (0 = background, 1 = lesion). Try out this algorithm with your own data!
PDAC Tumor Segmentation
This algorithm applies a three-steps pipeline for segmenting Pancreatic Ductal Adenocarcinoma in pancreatic whole-slide images. The output of this model consists of: a mask with the tissue (1), healthy epithelium (2), and tumor epithelium (3). 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 April.
🏆 Prizes:
1. €1.000,-
2. €500,-
3. €250,-
4. €150,-
5. €100,-
🥅 Goal: The Diminished Reality for Emerging Applications in Medicine through Inpainting (DREAMING) challenge seeks to pioneer the integration of Diminished Reality (DR) into oral and maxillofacial surgery. The challenge provides a dataset of synthetic yet photorealistic surgery scenes featuring humans, simulating an operating room setting. Participants are tasked with developing algorithms that seamlessly remove disruptions caused by medical instruments and hands, offering surgeons an unimpeded view of the operative site.
✍️ Register: Registration is now open!
⏰ Deadline: The submissions close on 27th of April, 2024.
🏆 Prizes:
- €500,- for the best paper.
- €500,- for the best-performing solution award.
🏆 Leaderboard of finished challenges¶
The task of the HaN-Seg (Head and Neck Segmentation) grand challenge is to automatically segment 30 organs-at-risk in the HaN region from CT images. The winner of the Final Test Phase was Elias Tappeiner. Congratulations! Two members of the HaN-Seg 2023 teams will have the option to qualify as co-authors on an upcoming high-impact journal paper summarizing the findings of this challenge.
