http://www.nitrc.org/project/showfiles.php?group_id=1520 Acute-stroke Detection Segmentation (ADS) Latest Releases en-us Copyright 2000-2026 NITRC OSI fariaav@www.nitrc.org (Andreia Faria) Fri, 15 May 2026 23:41:24 GMT http://blogs.law.harvard.edu/tech/rss http://www.nitrc.org/images/bflogo-88.png http://www.nitrc.org/ 124 32 http://www.nitrc.org/project/showfiles.php?group_id=1520&release_id=4673 <p>We provide a DL based tool for detection and segmentation of ischemic acute/sub-acute strokes, trained and tested in 2,628 brain MRIs (Liu et al. Nat Commun Med, 2021). Using the original DWI as input, this fully automated system outputs 3D digital infarct mask, volume, and the feature vectors of regions affected by the infarct in two parcellation schemes: structural anatomy and arterial territories. The method is fast (the lesion inference takes 20~30 seconds in CPU; the total processing, including image registration and generation of reports take 3-7 mins, depending on the choice for registration algorithm). ADSv1 includes outputs of the brains and infarct masks mapped to a common space (MNI), ASPECTS calculation, automated radiological reports, with interpretable descriptions of the models' predictions. This system is publicly available, real time, run on local computers, with minimal computational requirements, and is accessible to non-expert users</p> hubert_iu@www.nitrc.org (CHIN LIU) http://www.nitrc.org/project/shownotes.php?group_id=1520&release_id=4673 Mon, 25 Jul 2022 1:16:00 GMT http://www.nitrc.org/project/showfiles.php?group_id=1520&release_id=4673 http://www.nitrc.org/project/showfiles.php?group_id=1520&release_id=4638 <p>ADSv.1 is the updated version of ADS, a deep-learning based tool for detection and segmentation of ischemic acute and sub-acute strokes in brain diffusion weighted MRIs trained and tested in 2,628 images (Liu et al. Nat Commun Med 1, 61, 2021). Using the original DWI as input, this updated fully automated system outputs the 3D digital infarct mask, infarct volume, and the feature vectors of regions affected by the infarct two brain parcellation schemes: structural anatomy and arterial territories. New functions of ADSv1 also include outputs of the brains and masks mapped to a common space (MNI), ASPECTS calculation, generation of automated radiological reports, with interpretable descriptions of the features involved in the machine learning models' predictions. This system is publicly available, runs in real time, in local computers, with minimal computational requirements, and is accessible to non-expert users.</p> hubert_iu@www.nitrc.org (CHIN LIU) http://www.nitrc.org/project/shownotes.php?group_id=1520&release_id=4638 Thu, 26 May 2022 17:52:00 GMT http://www.nitrc.org/project/showfiles.php?group_id=1520&release_id=4638 http://www.nitrc.org/project/showfiles.php?group_id=1520&release_id=4481 hubert_iu@www.nitrc.org (CHIN LIU) http://www.nitrc.org/project/shownotes.php?group_id=1520&release_id=4481 Tue, 17 Aug 2021 15:23:00 GMT http://www.nitrc.org/project/showfiles.php?group_id=1520&release_id=4481