Intraparenchymal hemorrhage segmentation from clinical head CT of patients with traumatic brain injury

Snehashis Roy, Sean Wilkes, Ramon Diaz-Arrastia, John A. Butman, Dzung L. Pham

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Quantification of hemorrhages in head computed tomography (CT) images from patients with traumatic brain injury (TBI) has potential applications in monitoring disease progression and better understanding of the patho-physiology of TBI. Although manual segmentations can provide accurate measures of hemorrhages, the processing time and inter-rater variability make it infeasible for large studies. In this paper, we propose a fully automatic novel pipeline for segmenting intraparenchymal hemorrhages (IPH) from clinical head CT images. Unlike previous methods of model based segmentation or active contour techniques, we rely on relevant and matching examples from already segmented images by trained raters. The CT images are first skull-stripped. Then example patches from an "atlas" CT and its manual segmentation are used to learn a two-class sparse dictionary for hemorrhage and normal tissue. Next, for a given "subject" CT, a subject patch is modeled as a sparse convex combination of a few atlas patches from the dictionary. The same convex combination is applied to the atlas segmentation patches to generate a membership for the hemorrhages at each voxel. Hemorrhages are segmented from 25 subjects with various degrees of TBI. Results are compared with segmentations obtained from an expert rater. A median Dice coefficient of 0.85 between automated and manual segmentations is achieved. A linear fit between automated and manual volumes show a slope of 1.0047, indicating a negligible bias in volume estimation.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2015: Image Processing
PublisherSPIE
Volume9413
ISBN (Print)9781628415032
DOIs
StatePublished - 2015
Externally publishedYes
EventMedical Imaging 2015: Image Processing - Orlando, United States
Duration: Feb 24 2015Feb 26 2015

Other

OtherMedical Imaging 2015: Image Processing
CountryUnited States
CityOrlando
Period2/24/152/26/15

Fingerprint

brain damage
hemorrhages
Tomography
Brain
tomography
Head
Hemorrhage
Atlases
Glossaries
dictionaries
Physiology
skull
physiology
Skull
progressions
Pipelines
Disease Progression
Traumatic Brain Injury
Tissue
Monitoring

Keywords

  • brain
  • CT
  • intraparenchymal hemorrhage
  • sparsity
  • TBI

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Roy, S., Wilkes, S., Diaz-Arrastia, R., Butman, J. A., & Pham, D. L. (2015). Intraparenchymal hemorrhage segmentation from clinical head CT of patients with traumatic brain injury. In Medical Imaging 2015: Image Processing (Vol. 9413). [94130I] SPIE. https://doi.org/10.1117/12.2082199

Intraparenchymal hemorrhage segmentation from clinical head CT of patients with traumatic brain injury. / Roy, Snehashis; Wilkes, Sean; Diaz-Arrastia, Ramon; Butman, John A.; Pham, Dzung L.

Medical Imaging 2015: Image Processing. Vol. 9413 SPIE, 2015. 94130I.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Roy, S, Wilkes, S, Diaz-Arrastia, R, Butman, JA & Pham, DL 2015, Intraparenchymal hemorrhage segmentation from clinical head CT of patients with traumatic brain injury. in Medical Imaging 2015: Image Processing. vol. 9413, 94130I, SPIE, Medical Imaging 2015: Image Processing, Orlando, United States, 2/24/15. https://doi.org/10.1117/12.2082199
Roy S, Wilkes S, Diaz-Arrastia R, Butman JA, Pham DL. Intraparenchymal hemorrhage segmentation from clinical head CT of patients with traumatic brain injury. In Medical Imaging 2015: Image Processing. Vol. 9413. SPIE. 2015. 94130I https://doi.org/10.1117/12.2082199
Roy, Snehashis ; Wilkes, Sean ; Diaz-Arrastia, Ramon ; Butman, John A. ; Pham, Dzung L. / Intraparenchymal hemorrhage segmentation from clinical head CT of patients with traumatic brain injury. Medical Imaging 2015: Image Processing. Vol. 9413 SPIE, 2015.
@inproceedings{d3f09a4142e049c8a47061af73b0fa80,
title = "Intraparenchymal hemorrhage segmentation from clinical head CT of patients with traumatic brain injury",
abstract = "Quantification of hemorrhages in head computed tomography (CT) images from patients with traumatic brain injury (TBI) has potential applications in monitoring disease progression and better understanding of the patho-physiology of TBI. Although manual segmentations can provide accurate measures of hemorrhages, the processing time and inter-rater variability make it infeasible for large studies. In this paper, we propose a fully automatic novel pipeline for segmenting intraparenchymal hemorrhages (IPH) from clinical head CT images. Unlike previous methods of model based segmentation or active contour techniques, we rely on relevant and matching examples from already segmented images by trained raters. The CT images are first skull-stripped. Then example patches from an {"}atlas{"} CT and its manual segmentation are used to learn a two-class sparse dictionary for hemorrhage and normal tissue. Next, for a given {"}subject{"} CT, a subject patch is modeled as a sparse convex combination of a few atlas patches from the dictionary. The same convex combination is applied to the atlas segmentation patches to generate a membership for the hemorrhages at each voxel. Hemorrhages are segmented from 25 subjects with various degrees of TBI. Results are compared with segmentations obtained from an expert rater. A median Dice coefficient of 0.85 between automated and manual segmentations is achieved. A linear fit between automated and manual volumes show a slope of 1.0047, indicating a negligible bias in volume estimation.",
keywords = "brain, CT, intraparenchymal hemorrhage, sparsity, TBI",
author = "Snehashis Roy and Sean Wilkes and Ramon Diaz-Arrastia and Butman, {John A.} and Pham, {Dzung L.}",
year = "2015",
doi = "10.1117/12.2082199",
language = "English (US)",
isbn = "9781628415032",
volume = "9413",
booktitle = "Medical Imaging 2015: Image Processing",
publisher = "SPIE",

}

TY - GEN

T1 - Intraparenchymal hemorrhage segmentation from clinical head CT of patients with traumatic brain injury

AU - Roy, Snehashis

AU - Wilkes, Sean

AU - Diaz-Arrastia, Ramon

AU - Butman, John A.

AU - Pham, Dzung L.

PY - 2015

Y1 - 2015

N2 - Quantification of hemorrhages in head computed tomography (CT) images from patients with traumatic brain injury (TBI) has potential applications in monitoring disease progression and better understanding of the patho-physiology of TBI. Although manual segmentations can provide accurate measures of hemorrhages, the processing time and inter-rater variability make it infeasible for large studies. In this paper, we propose a fully automatic novel pipeline for segmenting intraparenchymal hemorrhages (IPH) from clinical head CT images. Unlike previous methods of model based segmentation or active contour techniques, we rely on relevant and matching examples from already segmented images by trained raters. The CT images are first skull-stripped. Then example patches from an "atlas" CT and its manual segmentation are used to learn a two-class sparse dictionary for hemorrhage and normal tissue. Next, for a given "subject" CT, a subject patch is modeled as a sparse convex combination of a few atlas patches from the dictionary. The same convex combination is applied to the atlas segmentation patches to generate a membership for the hemorrhages at each voxel. Hemorrhages are segmented from 25 subjects with various degrees of TBI. Results are compared with segmentations obtained from an expert rater. A median Dice coefficient of 0.85 between automated and manual segmentations is achieved. A linear fit between automated and manual volumes show a slope of 1.0047, indicating a negligible bias in volume estimation.

AB - Quantification of hemorrhages in head computed tomography (CT) images from patients with traumatic brain injury (TBI) has potential applications in monitoring disease progression and better understanding of the patho-physiology of TBI. Although manual segmentations can provide accurate measures of hemorrhages, the processing time and inter-rater variability make it infeasible for large studies. In this paper, we propose a fully automatic novel pipeline for segmenting intraparenchymal hemorrhages (IPH) from clinical head CT images. Unlike previous methods of model based segmentation or active contour techniques, we rely on relevant and matching examples from already segmented images by trained raters. The CT images are first skull-stripped. Then example patches from an "atlas" CT and its manual segmentation are used to learn a two-class sparse dictionary for hemorrhage and normal tissue. Next, for a given "subject" CT, a subject patch is modeled as a sparse convex combination of a few atlas patches from the dictionary. The same convex combination is applied to the atlas segmentation patches to generate a membership for the hemorrhages at each voxel. Hemorrhages are segmented from 25 subjects with various degrees of TBI. Results are compared with segmentations obtained from an expert rater. A median Dice coefficient of 0.85 between automated and manual segmentations is achieved. A linear fit between automated and manual volumes show a slope of 1.0047, indicating a negligible bias in volume estimation.

KW - brain

KW - CT

KW - intraparenchymal hemorrhage

KW - sparsity

KW - TBI

UR - http://www.scopus.com/inward/record.url?scp=84943387449&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943387449&partnerID=8YFLogxK

U2 - 10.1117/12.2082199

DO - 10.1117/12.2082199

M3 - Conference contribution

SN - 9781628415032

VL - 9413

BT - Medical Imaging 2015: Image Processing

PB - SPIE

ER -