MS new lesions segmentation challenge using a data management and processing infrastructure
- Data access and challenge registration: https://project.inria.fr/fli/msseg-2/data/
- Pipeline integration and challenge timeline: https://project.inria.fr/fli/msseg-2/challenge-timeline-and-pipeline-integration/
- Evaluation strategy: https://project.inria.fr/fli/msseg-2/evaluation/
Conventional MRI is widely used for disease diagnosis, patient follow-up, monitoring of therapies, and more generally for the understanding of the natural history of MS. A growing literature is interested in the delineation of new MS lesions on T2/FLAIR by comparing one time point to another. This marker is even more crucial than the total number and volume of lesions as the accumulation of new lesions allows clinicians to know if a given anti-inflammatory DMD (disease modifying drug) works for the patient. The only indicator of drug efficacy is indeed the absence of new T2 lesions within the CNS. Automating the detection of these new lesions would therefore be a major advance for evaluating the patient disease activity.
Based on the success of the first MSSEG challenge, we organize a new MICCAI sponsored online challenge, this time on new MS lesions detection. Online and sponsored mean that this challenge will not take place at the exact time of MICCAI but rather a week before (date to be further precised but right before or right after MICCAI) and it will take place as an online only event. As for any MICCAI workshop, we will still gather the proceedings and keep them available after the challenge. We are also planning to open a special issue of a journal afterwards to allow challengers to further publish their results.
This challenge will allow to 1) estimate the progress performed during this period, 2) extend the number of patients, and 3) focus on this crucial clinical marker. We will perform the evaluation task on a large database (100 patients, each with two time points) compiled from the OFSEP cohort, the French MS registry, with 3D FLAIR images from different centers and scanners. As in our previous challenge, we propose to conduct the evaluation on a dedicated platform (FLI-IAM) to automate the evaluation and remove the potential biases.
You will find in related pages (under the MSSEG-2 menu) details on the challenge, the data, its evaluation framework, its timeline, etc. If you have any question on the challenge, please contact us at email@example.com.
We are thankful to our institutions, partners and sponsors to have made this challenge possible.