Atlas-based algorithm for automatic anatomical measurements in the knee

Michael Brehler, Gaurav Thawait, Jonathan Kaplan, John Ramsay, Miho Tanaka, Shadpour Demehri, Jeff Siewerdsen, Wojciech Zbijewski

Research output: Contribution to journalArticle

Abstract

We present an algorithm for automatic anatomical measurements in tomographic datasets of the knee. The algorithm uses a set of atlases, each consisting of a knee image, surface segmentations of the bones, and locations of landmarks required by the anatomical metrics. A multistage volume-to-volume and surface-to-volume registration is performed to transfer the landmarks from the atlases to the target volume. Manual segmentation of the target volume is not required in this approach. Metrics were computed from the transferred landmarks of a best-matching atlas member (different for each bone), identified based on a mutual information criterion. Leave-one-out validation of the algorithm was performed on 24 scans of the knee obtained using extremity cone-beam computed tomography. Intraclass correlation (ICC) between the algorithm and the expert who generated atlas landmarks was above 0.95 for all metrics. This compares favorably to inter-reader ICC, which varied from 0.19 to 0.95, depending on the metric. Absolute agreement with the expert was also good, with median errors below 0.25 deg for measurements of tibial slope and static alignment, and below 0.2 mm for tibial tuberosity-trochlear groove distance and medial tibial depth. The automatic approach is anticipated to improve measurement workflow and mitigate the effects of operator experience and training on reliability of the metrics.

Original languageEnglish (US)
Article number026002
JournalJournal of Medical Imaging
Volume6
Issue number2
DOIs
StatePublished - Apr 1 2019

Fingerprint

Atlases
Knee
Bone and Bones
Cone-Beam Computed Tomography
Workflow
Extremities

Keywords

  • anatomical landmarks
  • anatomical measurements
  • atlas
  • automatic measurement
  • image analysis
  • image registration

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Atlas-based algorithm for automatic anatomical measurements in the knee. / Brehler, Michael; Thawait, Gaurav; Kaplan, Jonathan; Ramsay, John; Tanaka, Miho; Demehri, Shadpour; Siewerdsen, Jeff; Zbijewski, Wojciech.

In: Journal of Medical Imaging, Vol. 6, No. 2, 026002, 01.04.2019.

Research output: Contribution to journalArticle

Brehler, Michael ; Thawait, Gaurav ; Kaplan, Jonathan ; Ramsay, John ; Tanaka, Miho ; Demehri, Shadpour ; Siewerdsen, Jeff ; Zbijewski, Wojciech. / Atlas-based algorithm for automatic anatomical measurements in the knee. In: Journal of Medical Imaging. 2019 ; Vol. 6, No. 2.
@article{079e631e8e974a0cb76a3ba046e7574d,
title = "Atlas-based algorithm for automatic anatomical measurements in the knee",
abstract = "We present an algorithm for automatic anatomical measurements in tomographic datasets of the knee. The algorithm uses a set of atlases, each consisting of a knee image, surface segmentations of the bones, and locations of landmarks required by the anatomical metrics. A multistage volume-to-volume and surface-to-volume registration is performed to transfer the landmarks from the atlases to the target volume. Manual segmentation of the target volume is not required in this approach. Metrics were computed from the transferred landmarks of a best-matching atlas member (different for each bone), identified based on a mutual information criterion. Leave-one-out validation of the algorithm was performed on 24 scans of the knee obtained using extremity cone-beam computed tomography. Intraclass correlation (ICC) between the algorithm and the expert who generated atlas landmarks was above 0.95 for all metrics. This compares favorably to inter-reader ICC, which varied from 0.19 to 0.95, depending on the metric. Absolute agreement with the expert was also good, with median errors below 0.25 deg for measurements of tibial slope and static alignment, and below 0.2 mm for tibial tuberosity-trochlear groove distance and medial tibial depth. The automatic approach is anticipated to improve measurement workflow and mitigate the effects of operator experience and training on reliability of the metrics.",
keywords = "anatomical landmarks, anatomical measurements, atlas, automatic measurement, image analysis, image registration",
author = "Michael Brehler and Gaurav Thawait and Jonathan Kaplan and John Ramsay and Miho Tanaka and Shadpour Demehri and Jeff Siewerdsen and Wojciech Zbijewski",
year = "2019",
month = "4",
day = "1",
doi = "10.1117/1.JMI.6.2.026002",
language = "English (US)",
volume = "6",
journal = "Journal of Medical Imaging",
issn = "0720-048X",
publisher = "Elsevier Ireland Ltd",
number = "2",

}

TY - JOUR

T1 - Atlas-based algorithm for automatic anatomical measurements in the knee

AU - Brehler, Michael

AU - Thawait, Gaurav

AU - Kaplan, Jonathan

AU - Ramsay, John

AU - Tanaka, Miho

AU - Demehri, Shadpour

AU - Siewerdsen, Jeff

AU - Zbijewski, Wojciech

PY - 2019/4/1

Y1 - 2019/4/1

N2 - We present an algorithm for automatic anatomical measurements in tomographic datasets of the knee. The algorithm uses a set of atlases, each consisting of a knee image, surface segmentations of the bones, and locations of landmarks required by the anatomical metrics. A multistage volume-to-volume and surface-to-volume registration is performed to transfer the landmarks from the atlases to the target volume. Manual segmentation of the target volume is not required in this approach. Metrics were computed from the transferred landmarks of a best-matching atlas member (different for each bone), identified based on a mutual information criterion. Leave-one-out validation of the algorithm was performed on 24 scans of the knee obtained using extremity cone-beam computed tomography. Intraclass correlation (ICC) between the algorithm and the expert who generated atlas landmarks was above 0.95 for all metrics. This compares favorably to inter-reader ICC, which varied from 0.19 to 0.95, depending on the metric. Absolute agreement with the expert was also good, with median errors below 0.25 deg for measurements of tibial slope and static alignment, and below 0.2 mm for tibial tuberosity-trochlear groove distance and medial tibial depth. The automatic approach is anticipated to improve measurement workflow and mitigate the effects of operator experience and training on reliability of the metrics.

AB - We present an algorithm for automatic anatomical measurements in tomographic datasets of the knee. The algorithm uses a set of atlases, each consisting of a knee image, surface segmentations of the bones, and locations of landmarks required by the anatomical metrics. A multistage volume-to-volume and surface-to-volume registration is performed to transfer the landmarks from the atlases to the target volume. Manual segmentation of the target volume is not required in this approach. Metrics were computed from the transferred landmarks of a best-matching atlas member (different for each bone), identified based on a mutual information criterion. Leave-one-out validation of the algorithm was performed on 24 scans of the knee obtained using extremity cone-beam computed tomography. Intraclass correlation (ICC) between the algorithm and the expert who generated atlas landmarks was above 0.95 for all metrics. This compares favorably to inter-reader ICC, which varied from 0.19 to 0.95, depending on the metric. Absolute agreement with the expert was also good, with median errors below 0.25 deg for measurements of tibial slope and static alignment, and below 0.2 mm for tibial tuberosity-trochlear groove distance and medial tibial depth. The automatic approach is anticipated to improve measurement workflow and mitigate the effects of operator experience and training on reliability of the metrics.

KW - anatomical landmarks

KW - anatomical measurements

KW - atlas

KW - automatic measurement

KW - image analysis

KW - image registration

UR - http://www.scopus.com/inward/record.url?scp=85069520860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069520860&partnerID=8YFLogxK

U2 - 10.1117/1.JMI.6.2.026002

DO - 10.1117/1.JMI.6.2.026002

M3 - Article

VL - 6

JO - Journal of Medical Imaging

JF - Journal of Medical Imaging

SN - 0720-048X

IS - 2

M1 - 026002

ER -