VAscular Lesions DetectiOn
- 1. School of Biomedical Engineering & Imaging Sciences - King's College London - London - United Kingdom / Dementia Research Centre University College London - London - United Kingdom
- 2. Biomedical Imaging Group - Erasmus Medical Center - Rotterdam - The Netherlands
- 3. GSK - London - United Kingdom
- 4. Biomedical Imaging Group - Erasmus Medical Center - Rotterdam - The Netherlands; Department of Computer Science - University of Copenhagen - Copenhagen - Denmark
Description
This is the challenge design document for the "VAscular Lesions DetectiOn" Challenge, accepted for MICCAI 2021.
Appropriate blood supply is essential to the healthy maintenance of brain tissue. With age, vascular changes are observed in the smallest vessels resulting in impaired function. Changes to the surrounding tissue can be observed using magnetic resonance imaging. White matter hyperintensities are one such prominent marker of cerebral small vessel disease and their automated segmentation has been the focus of a large body of research as well as of segmentation challenges. Other markers of CSVD exist and their quantification along with WMH is essential to grasp the overall picture of the vascular burden related to CSVD. They include notably lacunes, enlarged perivascular spaces and cerebral microbleeds. Manual annotations are extremely time-consuming and suffer greatly from inter- and intra-rater variability, due to their small size and the difficulty of distinguishing these markers from each other and similarly appearing structures as well as the lack of a way to uncover the "real" ground truth. However, many studies have hinted at their potential to become essential biomarkers. Automated methods are therefore required to make their quantification not only robust and reliable, but simply feasible. So far development of such methods has been impeded by the methodological issues related to their very small size and the sparsity in the data but also the absence of sufficient gold standard/and or evaluation of the labeling noise.
This challenge aims at promoting the development of new solutions for the automated detection, differentiation and segmentation of such very sparse and small objects while leveraging the presence of weak and noisy labels.
The challenge will have a technical impact in the following fields: use of weak labels, assessment of prediction uncertainty, object detection, class imbalance, multi-scale object detection. The biomedical impact will not only directly impact the field of cerebral small vessel disease research but also other brain pathologies such as multiple sclerosis where similar objects have recently been shown renewed interest. More broadly translation of developed techniques to other fields where sparse object detection is essential will be impacted (mammography, lung nodule detection...).
Files
VAscularLesionsDetectiOn-New_03-12-2021_09-52-53.pdf
Files
(7.2 MB)
Name | Size | Download all |
---|---|---|
md5:575e7545541527a8f6ec0e33bbd8e9e5
|
7.2 MB | Preview Download |