Development and validation of an automatic segmentation algorithm for quantification of intracerebral hemorrhage

• Verfasst von: Scherer, Moritz [VerfasserIn]
• Verfasst von: Younsi, Alexander [VerfasserIn]
• Verfasst von: Möhlenbruch, Markus Alfred [VerfasserIn]
• Verfasst von: Stock, Christian [VerfasserIn]
• Verfasst von: Bösel, Julian [VerfasserIn]
• Verfasst von: Unterberg, Andreas [VerfasserIn]
• Verfasst von: Orakcioglu, Berk [VerfasserIn]
• Titel: Development and validation of an automatic segmentation algorithm for quantification of intracerebral hemorrhage
• Verf.angabe: Moritz Scherer, MD; Jonas Cordes, MSc; Alexander Younsi, MD; Yasemin-Aylin Sahin, MS; Michael Götz, MSc; Markus Möhlenbruch, MD; Christian Stock, MSc, PhD; Julian Bösel, MD; Andreas Unterberg, MD, PhD; Klaus Maier-Hein, MSc, PhD; Berk Orakcioglu, MD
• E-Jahr: 2016
• Jahr: August 29, 2016
• Umfang: 7 S.
• Fussnoten: Gesehen am 01.12.2017
• Titel Quelle: Enthalten in: Stroke
• Ort Quelle: New York, NY : Association, 1970
• Jahr Quelle: 2016
• Band/Heft Quelle: 47(2016), 11, Seite 2776-2782
• ISSN Quelle: 1524-4628
• DOI: doi:10.1161/STROKEAHA.116.013779
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: computed tomography
• Sach-SW: computer-assisted image analysis
• Sach-SW: intracerebral hemorrhage
• Sach-SW: machine learning
• Sach-SW: volumetric analysis
• K10plus-PPN: 1565949781

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.