Selecting and assessing quantitative early ultrasound texture measures for their association with cerebral palsy

Tyna A. Hope; Peter H. Gregson; Norma C. Linney; Matthias H. Schmidt; Mohamed Abdolell

doi:10.1109/TMI.2007.906089

Selecting and assessing quantitative early ultrasound texture measures for their association with cerebral palsy

Tyna A. Hope, Peter H. Gregson, Norma C. Linney, Matthias H. Schmidt, Mohamed Abdolell

Medicine

Research output: Contribution to journal › Article › peer-review

12 Citations (Scopus)

Abstract

Cerebral palsy (CP) develops as a consequence of white matter damage (WMD) in approximately one out of every 10 very preterm infants. Ultrasound (US) is widely used to screen for a variety of brain injuries in this patient population, but early US often fails to detect WMD. We hypothesized that quantitative texture measures on US images obtained within one week of birth are associated with the subsequent development of CP. In this retrospective study, using images from a variety of US machines, we extracted unique texture measures by means of adaptive processing and high resolution feature enhancement. We did not standardize the images, but used patients as their own controls. We did not remove speckle, as it may contain information. To test our hypothesis, we used the "random forest" algorithm to create a model. The random forest classifier achieved a 72% match to the health outcome of the patients (CP versus no CP), whereas designating all patients as having CP would have resulted in 53% error. This suggests that quantitative early texture measures contain diagnostic information relevant to the development of CP.

Original language	English
Article number	4359054
Pages (from-to)	228-236
Number of pages	9
Journal	IEEE Transactions on Medical Imaging
Volume	27
Issue number	2
DOIs	https://doi.org/10.1109/TMI.2007.906089
Publication status	Published - 2008

Bibliographical note

Funding Information:
Manuscript received May 22, 2007; revised July 26,2007. This work was supported in part by the Natural Sciences and Engineering Research Council, in part by the Nova Scotia Health Research Foundation, and in part by the IWK Health Centre. Asterisk indicates corresponding author. *T. A. Hope is with Cambridge Research and Instrumentation, Boston, MA 01801 USA (e-mail: tyna.hope@gmail.com). P. H. Gregson is with the Electrical and Computer Engineering Department, Dalhousie University, Halifax, NS, B3J 2X4, Canada. N. C. Linney is with the Mathematics and Computer Science Department, Saint Mary’s University, Halifax, NS, B3H 3C3 , Canada. M. Schmidt is with the Department of Radiology, Dalhousie University, Halifax, NS, B3H 2Y9 Canada. M. Abdolell is with the Department of Diagnostic Radiology, Dalhousie University, Halifax, NS, B3H 2Y9 Canada. Digital Object Identifier 10.1109/TMI.2007.906089

ASJC Scopus Subject Areas

Software
Radiological and Ultrasound Technology
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/TMI.2007.906089

Cite this

@article{b8fa707b29e94ccb87e7615baae9cd67,

title = "Selecting and assessing quantitative early ultrasound texture measures for their association with cerebral palsy",

abstract = "Cerebral palsy (CP) develops as a consequence of white matter damage (WMD) in approximately one out of every 10 very preterm infants. Ultrasound (US) is widely used to screen for a variety of brain injuries in this patient population, but early US often fails to detect WMD. We hypothesized that quantitative texture measures on US images obtained within one week of birth are associated with the subsequent development of CP. In this retrospective study, using images from a variety of US machines, we extracted unique texture measures by means of adaptive processing and high resolution feature enhancement. We did not standardize the images, but used patients as their own controls. We did not remove speckle, as it may contain information. To test our hypothesis, we used the {"}random forest{"} algorithm to create a model. The random forest classifier achieved a 72% match to the health outcome of the patients (CP versus no CP), whereas designating all patients as having CP would have resulted in 53% error. This suggests that quantitative early texture measures contain diagnostic information relevant to the development of CP.",

author = "Hope, {Tyna A.} and Gregson, {Peter H.} and Linney, {Norma C.} and Schmidt, {Matthias H.} and Mohamed Abdolell",

note = "Funding Information: Manuscript received May 22, 2007; revised July 26,2007. This work was supported in part by the Natural Sciences and Engineering Research Council, in part by the Nova Scotia Health Research Foundation, and in part by the IWK Health Centre. Asterisk indicates corresponding author. *T. A. Hope is with Cambridge Research and Instrumentation, Boston, MA 01801 USA (e-mail: tyna.hope@gmail.com). P. H. Gregson is with the Electrical and Computer Engineering Department, Dalhousie University, Halifax, NS, B3J 2X4, Canada. N. C. Linney is with the Mathematics and Computer Science Department, Saint Mary{\textquoteright}s University, Halifax, NS, B3H 3C3 , Canada. M. Schmidt is with the Department of Radiology, Dalhousie University, Halifax, NS, B3H 2Y9 Canada. M. Abdolell is with the Department of Diagnostic Radiology, Dalhousie University, Halifax, NS, B3H 2Y9 Canada. Digital Object Identifier 10.1109/TMI.2007.906089",

year = "2008",

doi = "10.1109/TMI.2007.906089",

language = "English",

volume = "27",

pages = "228--236",

journal = "IEEE Transactions on Medical Imaging",

issn = "0278-0062",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - Selecting and assessing quantitative early ultrasound texture measures for their association with cerebral palsy

AU - Hope, Tyna A.

AU - Gregson, Peter H.

AU - Linney, Norma C.

AU - Schmidt, Matthias H.

AU - Abdolell, Mohamed

N1 - Funding Information: Manuscript received May 22, 2007; revised July 26,2007. This work was supported in part by the Natural Sciences and Engineering Research Council, in part by the Nova Scotia Health Research Foundation, and in part by the IWK Health Centre. Asterisk indicates corresponding author. *T. A. Hope is with Cambridge Research and Instrumentation, Boston, MA 01801 USA (e-mail: tyna.hope@gmail.com). P. H. Gregson is with the Electrical and Computer Engineering Department, Dalhousie University, Halifax, NS, B3J 2X4, Canada. N. C. Linney is with the Mathematics and Computer Science Department, Saint Mary’s University, Halifax, NS, B3H 3C3 , Canada. M. Schmidt is with the Department of Radiology, Dalhousie University, Halifax, NS, B3H 2Y9 Canada. M. Abdolell is with the Department of Diagnostic Radiology, Dalhousie University, Halifax, NS, B3H 2Y9 Canada. Digital Object Identifier 10.1109/TMI.2007.906089

PY - 2008

Y1 - 2008

N2 - Cerebral palsy (CP) develops as a consequence of white matter damage (WMD) in approximately one out of every 10 very preterm infants. Ultrasound (US) is widely used to screen for a variety of brain injuries in this patient population, but early US often fails to detect WMD. We hypothesized that quantitative texture measures on US images obtained within one week of birth are associated with the subsequent development of CP. In this retrospective study, using images from a variety of US machines, we extracted unique texture measures by means of adaptive processing and high resolution feature enhancement. We did not standardize the images, but used patients as their own controls. We did not remove speckle, as it may contain information. To test our hypothesis, we used the "random forest" algorithm to create a model. The random forest classifier achieved a 72% match to the health outcome of the patients (CP versus no CP), whereas designating all patients as having CP would have resulted in 53% error. This suggests that quantitative early texture measures contain diagnostic information relevant to the development of CP.

AB - Cerebral palsy (CP) develops as a consequence of white matter damage (WMD) in approximately one out of every 10 very preterm infants. Ultrasound (US) is widely used to screen for a variety of brain injuries in this patient population, but early US often fails to detect WMD. We hypothesized that quantitative texture measures on US images obtained within one week of birth are associated with the subsequent development of CP. In this retrospective study, using images from a variety of US machines, we extracted unique texture measures by means of adaptive processing and high resolution feature enhancement. We did not standardize the images, but used patients as their own controls. We did not remove speckle, as it may contain information. To test our hypothesis, we used the "random forest" algorithm to create a model. The random forest classifier achieved a 72% match to the health outcome of the patients (CP versus no CP), whereas designating all patients as having CP would have resulted in 53% error. This suggests that quantitative early texture measures contain diagnostic information relevant to the development of CP.

UR - http://www.scopus.com/inward/record.url?scp=41649104879&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41649104879&partnerID=8YFLogxK

U2 - 10.1109/TMI.2007.906089

DO - 10.1109/TMI.2007.906089

M3 - Article

C2 - 18334444

AN - SCOPUS:41649104879

SN - 0278-0062

VL - 27

SP - 228

EP - 236

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

IS - 2

M1 - 4359054

ER -

Selecting and assessing quantitative early ultrasound texture measures for their association with cerebral palsy

Abstract

Bibliographical note

ASJC Scopus Subject Areas

Access to Document

Other files and links

Fingerprint

Cite this