Generalizable spinal cord multiple sclerosis lesion segmentation across MRI contrasts, protocols, and centers.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Benveniste Pierre-Louis, Létourneau-Guillon Laurent, Araujo David, Chougar Lydia, Fetco Dumitru, Hori Masaaki, Kamiya Kouhei, Messina Steven, Tsagkas Charidimos, Audoin Bertrand, Bakshi Rohit, Bannier Elise, Blezek Daniel, Brisset Jean-Christophe, Callot Virginie, Charlson Erik, Chen Michelle, Ciccarelli Olga, Demortière Sarah, Edan Gilles, Filippi Massimo, Granberg Tobias, Granziera Cristina, Hemond Christopher C, Keegan B Mark, Kerbrat Anne, Kirschke Jan, Kolind Shannon, Labauge Pierre, Lee Lisa Eunyoung, Liu Yaou, Mainero Caterina, McGinnis Julian, Laines Medina Nilser, Mühlau Mark, Nair Govind, O'Grady Kristin P, Oh Jiwon, Ouellette Russell, Prat Alexandre, Reich Daniel S, Rocca Maria A, Shepherd Timothy M, Smith Seth A, Stawiarz Leszek, Talbott Jason, Tam Roger, Tauhid Shahamat, Traboulsee Anthony, Treaba Constantina Andrada, Valsasina Paola, Vavasour Zachary, Yiannakas Marios, Lombaert Hervé, Cohen-Adad Julien
Аннотация
METHODS: The segmentation model was trained and evaluated on a large-scale dataset comprising 4428 annotated images from 1849 persons with MS across 23 imaging centers, encompassing six MRI contrasts (T1w, T2w, T2*w, PSIR, STIR, and UNIT1) acquired at 1.5 tesla (T), 3 T, and 7 T.
RESULTS: Likert-type assessment performed by neuroradiologist ratings demonstrated superior generalization of the model compared to existing contrast-specific pipelines (p < 0.01). Additional experiments evaluated robustness across spinal levels, acquisition resolutions, binarization thresholds, and quantitative evaluation on external labeled datasets.
CONCLUSIONS: The proposed model can achieve accurate and reliable spinal cord MS lesion segmentation across heterogeneous MRI data, addressing a key barrier to clinical translation. The model is available in the Spinal Cord Toolbox v7.2 and higher.Code repository: https://github.com/ivadomed/seg-sc-ms-lesion-multicontrast.