Accurate Prostate Volume Estimation Using Multifeature Active Shape Models on T2-weighted MRI

Robert Toth, B. Nicolas Bloch, Elizabeth M. Genega, Neil M. Rofsky, Robert E. Lenkinski, Mark A. Rosen, Arjun Kalyanpur, Sona Pungavkar, Anant Madabhushi

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

Rationale and Objectives: Accurate prostate volume estimation is useful for calculating prostate-specific antigen density and in evaluating posttreatment response. In the clinic, prostate volume estimation involves modeling the prostate as an ellipsoid or a spheroid from transrectal ultrasound, or T2-weighted magnetic resonance imaging (MRI). However, this requires some degree of manual intervention, and may not always yield accurate estimates. In this article, we present a multifeature active shape model (MFA) based segmentation scheme for estimating prostate volume from in vivo T2-weighted MRI. Materials and Methods: We aim to automatically determine the location of the prostate boundary on in vivo T2-weighted MRI, and subsequently determine the area of the prostate on each slice. The resulting planimetric areas are aggregated to yield the volume of the prostate for a given patient. Using a set of training images, the MFA learns the most discriminating statistical texture descriptors of the prostate boundary via a forward feature selection algorithm. After identification of the optimal image features, the MFA is deformed to accurately fit the prostate border. An expert radiologist segmented the prostate boundary on each slice and the planimetric aggregation of the enclosed areas yielded the ground truth prostate volume estimate. The volume estimation obtained via the MFA was then compared against volume estimations obtained via the ellipsoidal, Myschetzky, and prolated spheroids models. Results: We evaluated our MFA volume estimation method on a total 45 T2-weighted in vivo MRI studies, corresponding to both 1.5 Tesla and 3.0 Tesla field strengths. The results revealed that the ellipsoidal, Myschetzky, and prolate spheroid models overestimated prostate volumes, with volume fractions of 1.14, 1.53, and 1.96, respectively. By comparison, the MFA yielded a mean volume fraction of 1.05, evaluated using a fivefold cross-validation scheme. A correlation with the ground truth volume estimations showed that the MFA had an r2 value of 0.82, whereas the clinical volume estimation schemes had a maximum value of 0.70. Conclusions: Our MFA scheme involves minimal user intervention, is computationally efficient and results in volume estimations more accurate than state of the art clinical models.

Original languageEnglish (US)
Pages (from-to)745-754
Number of pages10
JournalAcademic Radiology
Volume18
Issue number6
DOIs
StatePublished - Jun 2011

Fingerprint

Prostate
Magnetic Resonance Imaging
Phosmet
Prostate-Specific Antigen

Keywords

  • Active shape models
  • Image processing
  • MRI
  • Prostate cancer
  • Prostate volume
  • Texture

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Toth, R., Bloch, B. N., Genega, E. M., Rofsky, N. M., Lenkinski, R. E., Rosen, M. A., ... Madabhushi, A. (2011). Accurate Prostate Volume Estimation Using Multifeature Active Shape Models on T2-weighted MRI. Academic Radiology, 18(6), 745-754. https://doi.org/10.1016/j.acra.2011.01.016

Accurate Prostate Volume Estimation Using Multifeature Active Shape Models on T2-weighted MRI. / Toth, Robert; Bloch, B. Nicolas; Genega, Elizabeth M.; Rofsky, Neil M.; Lenkinski, Robert E.; Rosen, Mark A.; Kalyanpur, Arjun; Pungavkar, Sona; Madabhushi, Anant.

In: Academic Radiology, Vol. 18, No. 6, 06.2011, p. 745-754.

Research output: Contribution to journalArticle

Toth, R, Bloch, BN, Genega, EM, Rofsky, NM, Lenkinski, RE, Rosen, MA, Kalyanpur, A, Pungavkar, S & Madabhushi, A 2011, 'Accurate Prostate Volume Estimation Using Multifeature Active Shape Models on T2-weighted MRI', Academic Radiology, vol. 18, no. 6, pp. 745-754. https://doi.org/10.1016/j.acra.2011.01.016
Toth, Robert ; Bloch, B. Nicolas ; Genega, Elizabeth M. ; Rofsky, Neil M. ; Lenkinski, Robert E. ; Rosen, Mark A. ; Kalyanpur, Arjun ; Pungavkar, Sona ; Madabhushi, Anant. / Accurate Prostate Volume Estimation Using Multifeature Active Shape Models on T2-weighted MRI. In: Academic Radiology. 2011 ; Vol. 18, No. 6. pp. 745-754.
@article{213adecddcbc4f9d933b700565852277,
title = "Accurate Prostate Volume Estimation Using Multifeature Active Shape Models on T2-weighted MRI",
abstract = "Rationale and Objectives: Accurate prostate volume estimation is useful for calculating prostate-specific antigen density and in evaluating posttreatment response. In the clinic, prostate volume estimation involves modeling the prostate as an ellipsoid or a spheroid from transrectal ultrasound, or T2-weighted magnetic resonance imaging (MRI). However, this requires some degree of manual intervention, and may not always yield accurate estimates. In this article, we present a multifeature active shape model (MFA) based segmentation scheme for estimating prostate volume from in vivo T2-weighted MRI. Materials and Methods: We aim to automatically determine the location of the prostate boundary on in vivo T2-weighted MRI, and subsequently determine the area of the prostate on each slice. The resulting planimetric areas are aggregated to yield the volume of the prostate for a given patient. Using a set of training images, the MFA learns the most discriminating statistical texture descriptors of the prostate boundary via a forward feature selection algorithm. After identification of the optimal image features, the MFA is deformed to accurately fit the prostate border. An expert radiologist segmented the prostate boundary on each slice and the planimetric aggregation of the enclosed areas yielded the ground truth prostate volume estimate. The volume estimation obtained via the MFA was then compared against volume estimations obtained via the ellipsoidal, Myschetzky, and prolated spheroids models. Results: We evaluated our MFA volume estimation method on a total 45 T2-weighted in vivo MRI studies, corresponding to both 1.5 Tesla and 3.0 Tesla field strengths. The results revealed that the ellipsoidal, Myschetzky, and prolate spheroid models overestimated prostate volumes, with volume fractions of 1.14, 1.53, and 1.96, respectively. By comparison, the MFA yielded a mean volume fraction of 1.05, evaluated using a fivefold cross-validation scheme. A correlation with the ground truth volume estimations showed that the MFA had an r2 value of 0.82, whereas the clinical volume estimation schemes had a maximum value of 0.70. Conclusions: Our MFA scheme involves minimal user intervention, is computationally efficient and results in volume estimations more accurate than state of the art clinical models.",
keywords = "Active shape models, Image processing, MRI, Prostate cancer, Prostate volume, Texture",
author = "Robert Toth and Bloch, {B. Nicolas} and Genega, {Elizabeth M.} and Rofsky, {Neil M.} and Lenkinski, {Robert E.} and Rosen, {Mark A.} and Arjun Kalyanpur and Sona Pungavkar and Anant Madabhushi",
year = "2011",
month = "6",
doi = "10.1016/j.acra.2011.01.016",
language = "English (US)",
volume = "18",
pages = "745--754",
journal = "Academic Radiology",
issn = "1076-6332",
publisher = "Elsevier USA",
number = "6",

}

TY - JOUR

T1 - Accurate Prostate Volume Estimation Using Multifeature Active Shape Models on T2-weighted MRI

AU - Toth, Robert

AU - Bloch, B. Nicolas

AU - Genega, Elizabeth M.

AU - Rofsky, Neil M.

AU - Lenkinski, Robert E.

AU - Rosen, Mark A.

AU - Kalyanpur, Arjun

AU - Pungavkar, Sona

AU - Madabhushi, Anant

PY - 2011/6

Y1 - 2011/6

N2 - Rationale and Objectives: Accurate prostate volume estimation is useful for calculating prostate-specific antigen density and in evaluating posttreatment response. In the clinic, prostate volume estimation involves modeling the prostate as an ellipsoid or a spheroid from transrectal ultrasound, or T2-weighted magnetic resonance imaging (MRI). However, this requires some degree of manual intervention, and may not always yield accurate estimates. In this article, we present a multifeature active shape model (MFA) based segmentation scheme for estimating prostate volume from in vivo T2-weighted MRI. Materials and Methods: We aim to automatically determine the location of the prostate boundary on in vivo T2-weighted MRI, and subsequently determine the area of the prostate on each slice. The resulting planimetric areas are aggregated to yield the volume of the prostate for a given patient. Using a set of training images, the MFA learns the most discriminating statistical texture descriptors of the prostate boundary via a forward feature selection algorithm. After identification of the optimal image features, the MFA is deformed to accurately fit the prostate border. An expert radiologist segmented the prostate boundary on each slice and the planimetric aggregation of the enclosed areas yielded the ground truth prostate volume estimate. The volume estimation obtained via the MFA was then compared against volume estimations obtained via the ellipsoidal, Myschetzky, and prolated spheroids models. Results: We evaluated our MFA volume estimation method on a total 45 T2-weighted in vivo MRI studies, corresponding to both 1.5 Tesla and 3.0 Tesla field strengths. The results revealed that the ellipsoidal, Myschetzky, and prolate spheroid models overestimated prostate volumes, with volume fractions of 1.14, 1.53, and 1.96, respectively. By comparison, the MFA yielded a mean volume fraction of 1.05, evaluated using a fivefold cross-validation scheme. A correlation with the ground truth volume estimations showed that the MFA had an r2 value of 0.82, whereas the clinical volume estimation schemes had a maximum value of 0.70. Conclusions: Our MFA scheme involves minimal user intervention, is computationally efficient and results in volume estimations more accurate than state of the art clinical models.

AB - Rationale and Objectives: Accurate prostate volume estimation is useful for calculating prostate-specific antigen density and in evaluating posttreatment response. In the clinic, prostate volume estimation involves modeling the prostate as an ellipsoid or a spheroid from transrectal ultrasound, or T2-weighted magnetic resonance imaging (MRI). However, this requires some degree of manual intervention, and may not always yield accurate estimates. In this article, we present a multifeature active shape model (MFA) based segmentation scheme for estimating prostate volume from in vivo T2-weighted MRI. Materials and Methods: We aim to automatically determine the location of the prostate boundary on in vivo T2-weighted MRI, and subsequently determine the area of the prostate on each slice. The resulting planimetric areas are aggregated to yield the volume of the prostate for a given patient. Using a set of training images, the MFA learns the most discriminating statistical texture descriptors of the prostate boundary via a forward feature selection algorithm. After identification of the optimal image features, the MFA is deformed to accurately fit the prostate border. An expert radiologist segmented the prostate boundary on each slice and the planimetric aggregation of the enclosed areas yielded the ground truth prostate volume estimate. The volume estimation obtained via the MFA was then compared against volume estimations obtained via the ellipsoidal, Myschetzky, and prolated spheroids models. Results: We evaluated our MFA volume estimation method on a total 45 T2-weighted in vivo MRI studies, corresponding to both 1.5 Tesla and 3.0 Tesla field strengths. The results revealed that the ellipsoidal, Myschetzky, and prolate spheroid models overestimated prostate volumes, with volume fractions of 1.14, 1.53, and 1.96, respectively. By comparison, the MFA yielded a mean volume fraction of 1.05, evaluated using a fivefold cross-validation scheme. A correlation with the ground truth volume estimations showed that the MFA had an r2 value of 0.82, whereas the clinical volume estimation schemes had a maximum value of 0.70. Conclusions: Our MFA scheme involves minimal user intervention, is computationally efficient and results in volume estimations more accurate than state of the art clinical models.

KW - Active shape models

KW - Image processing

KW - MRI

KW - Prostate cancer

KW - Prostate volume

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=79955598452&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955598452&partnerID=8YFLogxK

U2 - 10.1016/j.acra.2011.01.016

DO - 10.1016/j.acra.2011.01.016

M3 - Article

C2 - 21549962

AN - SCOPUS:79955598452

VL - 18

SP - 745

EP - 754

JO - Academic Radiology

JF - Academic Radiology

SN - 1076-6332

IS - 6

ER -