Literature DB >> 27703089

Development and Validation of an Automatic Segmentation Algorithm for Quantification of Intracerebral Hemorrhage.

Moritz Scherer1, Jonas Cordes2, Alexander Younsi2, Yasemin-Aylin Sahin2, Michael Götz2, Markus Möhlenbruch2, Christian Stock2, Julian Bösel2, Andreas Unterberg2, Klaus Maier-Hein2, Berk Orakcioglu2.   

Abstract

BACKGROUND AND
PURPOSE: ABC/2 is still widely accepted for volume estimations in spontaneous intracerebral hemorrhage (ICH) despite known limitations, which potentially accounts for controversial outcome-study results. The aim of this study was to establish and validate an automatic segmentation algorithm, allowing for quick and accurate quantification of ICH.
METHODS: A segmentation algorithm implementing first- and second-order statistics, texture, and threshold features was trained on manual segmentations with a random-forest methodology. Quantitative data of the algorithm, manual segmentations, and ABC/2 were evaluated for agreement in a study sample (n=28) and validated in an independent sample not used for algorithm training (n=30).
RESULTS: ABC/2 volumes were significantly larger compared with either manual or algorithm values, whereas no significant differences were found between the latter (P<0.0001; Friedman+Dunn's multiple comparison). Algorithm agreement with the manual reference was strong (concordance correlation coefficient 0.95 [lower 95% confidence interval 0.91]) and superior to ABC/2 (concordance correlation coefficient 0.77 [95% confidence interval 0.64]). Validation confirmed agreement in an independent sample (algorithm concordance correlation coefficient 0.99 [95% confidence interval 0.98], ABC/2 concordance correlation coefficient 0.82 [95% confidence interval 0.72]). The algorithm was closer to respective manual segmentations than ABC/2 in 52/58 cases (89.7%).
CONCLUSIONS: An automatic segmentation algorithm for volumetric analysis of spontaneous ICH was developed and validated in this study. Algorithm measurements showed strong agreement with manual segmentations, whereas ABC/2 exhibited its limitations, yielding inaccurate overestimations of ICH volume. The refined, yet time-efficient, quantification of ICH by the algorithm may facilitate evaluation of clot volume as an outcome predictor and trigger for surgical interventions in the clinical setting.
© 2016 American Heart Association, Inc.

Entities:  

Keywords:  computed tomography; computer-assisted image analysis; intracerebral hemorrhage; machine learning; volumetric analysis

Mesh:

Year:  2016        PMID: 27703089     DOI: 10.1161/STROKEAHA.116.013779

Source DB:  PubMed          Journal:  Stroke        ISSN: 0039-2499            Impact factor:   7.914


  19 in total

1.  Deep Learning for Automated Measurement of Hemorrhage and Perihematomal Edema in Supratentorial Intracerebral Hemorrhage.

Authors:  Rajat Dhar; Guido J Falcone; Yasheng Chen; Ali Hamzehloo; Elayna P Kirsch; Rommell B Noche; Kilian Roth; Julian Acosta; Andres Ruiz; Chia-Ling Phuah; Daniel Woo; Thomas M Gill; Kevin N Sheth; Jin-Moo Lee
Journal:  Stroke       Date:  2019-12-06       Impact factor: 7.914

2.  Hybrid 3D/2D Convolutional Neural Network for Hemorrhage Evaluation on Head CT.

Authors:  P D Chang; E Kuoy; J Grinband; B D Weinberg; M Thompson; R Homo; J Chen; H Abcede; M Shafie; L Sugrue; C G Filippi; M-Y Su; W Yu; C Hess; D Chow
Journal:  AJNR Am J Neuroradiol       Date:  2018-07-26       Impact factor: 3.825

Review 3.  Prognostic factors in pontine haemorrhage: A systematic review.

Authors:  Réza Behrouz
Journal:  Eur Stroke J       Date:  2018-01-08

4.  Ruptured middle cerebral artery aneurysms with a concomitant intraparenchymal hematoma: the role of hematoma volume.

Authors:  I A Zijlstra; W E van der Steen; D Verbaan; C B Majoie; H A Marquering; B A Coert; W P Vandertop; R van den Berg
Journal:  Neuroradiology       Date:  2018-01-22       Impact factor: 2.804

Review 5.  Deep into the Brain: Artificial Intelligence in Stroke Imaging.

Authors:  Eun-Jae Lee; Yong-Hwan Kim; Namkug Kim; Dong-Wha Kang
Journal:  J Stroke       Date:  2017-09-29       Impact factor: 6.967

6.  Automation of CT-based haemorrhagic stroke assessment for improved clinical outcomes: study protocol and design.

Authors:  Betty Chinda; George Medvedev; William Siu; Martin Ester; Ali Arab; Tao Gu; Sylvain Moreno; Ryan C N D'Arcy; Xiaowei Song
Journal:  BMJ Open       Date:  2018-04-19       Impact factor: 2.692

7.  Neoplastic and Non-neoplastic Acute Intracerebral Hemorrhage in CT Brain Scans: Machine Learning-Based Prediction Using Radiomic Image Features.

Authors:  Jawed Nawabi; Helge Kniep; Reza Kabiri; Gabriel Broocks; Tobias D Faizy; Christian Thaler; Gerhard Schön; Jens Fiehler; Uta Hanning
Journal:  Front Neurol       Date:  2020-05-05       Impact factor: 4.003

8.  Accuracy of deep learning to differentiate the histopathological grading of meningiomas on MR images: A preliminary study.

Authors:  Tommaso Banzato; Francesco Causin; Alessandro Della Puppa; Giacomo Cester; Linda Mazzai; Alessandro Zotti
Journal:  J Magn Reson Imaging       Date:  2019-03-21       Impact factor: 4.813

9.  A fast and fully-automated deep-learning approach for accurate hemorrhage segmentation and volume quantification in non-contrast whole-head CT.

Authors:  Ali Arab; Betty Chinda; George Medvedev; William Siu; Hui Guo; Tao Gu; Sylvain Moreno; Ghassan Hamarneh; Martin Ester; Xiaowei Song
Journal:  Sci Rep       Date:  2020-11-09       Impact factor: 4.379

Review 10.  Automated Detection and Screening of Traumatic Brain Injury (TBI) Using Computed Tomography Images: A Comprehensive Review and Future Perspectives.

Authors:  Vidhya V; Anjan Gudigar; U Raghavendra; Ajay Hegde; Girish R Menon; Filippo Molinari; Edward J Ciaccio; U Rajendra Acharya
Journal:  Int J Environ Res Public Health       Date:  2021-06-16       Impact factor: 3.390

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.