| 1. |
- Commowick, Olivier, et al.
(författare)
-
Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure
- 2018
-
Ingår i: Scientific Reports. - : Nature Publishing Group. - 2045-2322. ; 8
-
Tidskriftsartikel (refereegranskat)abstract
- We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using a new open-science computing infrastructure. This allowed for the automatic and independent evaluation of a large range of algorithms in a fair and completely automatic manner. This computing infrastructure was used to evaluate thirteen methods of MS lesions segmentation, exploring a broad range of state-of-theart algorithms, against a high-quality database of 53 MS cases coming from four centers following a common definition of the acquisition protocol. Each case was annotated manually by an unprecedented number of seven different experts. Results of the challenge highlighted that automatic algorithms, including the recent machine learning methods (random forests, deep learning,.), are still trailing human expertise on both detection and delineation criteria. In addition, we demonstrate that computing a statistically robust consensus of the algorithms performs closer to human expertise on one score (segmentation) although still trailing on detection scores.
|
|
| 2. |
- Hansen, Björn M., et al.
(författare)
-
Relationship of White Matter Lesions with Intracerebral Hemorrhage Expansion and Functional Outcome : MISTIE II and CLEAR III
- 2020
-
Ingår i: Neurocritical Care. - : Springer Science and Business Media LLC. - 1541-6933 .- 1556-0961. ; 33:2, s. 516-524
-
Tidskriftsartikel (refereegranskat)abstract
- Background/Objective: Intracerebral hemorrhage (ICH) patients commonly have concomitant white matter lesions (WML) which may be associated with poor outcome. We studied if WML affects hematoma expansion (HE) and post-stroke functional outcome in a post hoc analysis of patients from randomized controlled trials. Methods: In ICH patients from the clinical trials MISTIE II and CLEAR III, WML grade on diagnostic computed tomography (dCT) scan (dCT, < 24 h after ictus) was assessed using the van Swieten scale (vSS, range 0–4). The primary outcome for HE was > 33% or > 6 mL ICH volume increase from dCT to the last pre-randomization CT (< 72 h of dCT). Secondary HE outcomes were: absolute ICH expansion, > 10.4 mL total clot volume increase, and a subgroup analysis including patients with dCT < 6 h after ictus using the primary HE definition of > 33% or > 6 mL ICH volume increase. Poor functional outcome was assessed at 180 days and defined as modified Rankin Scale (mRS) ≥ 4, with ordinal mRS as a secondary endpoint. Results: Of 635 patients, 55% had WML grade 1–4 at dCT (median 2.2 h from ictus) and 13% had subsequent HE. WML at dCT did not increase the odds for primary or secondary HE endpoints (P ≥ 0.05) after adjustment for ICH volume, intraventricular hemorrhage volume, warfarin/INR > 1.5, ictus to dCT time in hours, age, diabetes mellitus, and thalamic ICH location. WML increased the odds for having poor functional outcome (mRS ≥ 4) in univariate analyses (vSS 4; OR 4.16; 95% CI 2.54–6.83; P < 0.001) which persisted in multivariable analyses after adjustment for HE and other outcome risk factors. Conclusions: Concomitant WML does not increase the odds for HE in patients with ICH but increases the odds for poor functional outcome. Clinical Trial Registration: http://www.clinicaltrials.gov trial-identifers: NCT00224770 and NCT00784134.
|
|
| 3. |
- Tustison, Nicholas J., et al.
(författare)
-
The ANTsX ecosystem for quantitative biological and medical imaging
- 2021
-
Ingår i: Scientific Reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 11:1, s. 9068-9068
-
Tidskriftsartikel (refereegranskat)abstract
- The Advanced Normalizations Tools ecosystem, known as ANTsX, consists of multiple open-source software libraries which house top-performing algorithms used worldwide by scientific and research communities for processing and analyzing biological and medical imaging data. The base software library, ANTs, is built upon, and contributes to, the NIH-sponsored Insight Toolkit. Founded in 2008 with the highly regarded Symmetric Normalization image registration framework, the ANTs library has since grown to include additional functionality. Recent enhancements include statistical, visualization, and deep learning capabilities through interfacing with both the R statistical project (ANTsR) and Python (ANTsPy). Additionally, the corresponding deep learning extensions ANTsRNet and ANTsPyNet (built on the popular TensorFlow/Keras libraries) contain several popular network architectures and trained models for specific applications. One such comprehensive application is a deep learning analog for generating cortical thickness data from structural T1-weighted brain MRI, both cross-sectionally and longitudinally. These pipelines significantly improve computational efficiency and provide comparable-to-superior accuracy over multiple criteria relative to the existing ANTs workflows and simultaneously illustrate the importance of the comprehensive ANTsX approach as a framework for medical image analysis.
|
|
