Enhanced multi-protocol analysis via intelligent supervised embedding (EMPrAvISE): Detecting prostate cancer on multi-parametric MRI

Satish Viswanath, B. Nicholas Bloch, Jonathan Chappelow, Pratik Patel, Neil Rofsky, Robert Lenkinski, Elizabeth Genega, Anant Madabhushi

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

12 Citations (Scopus)

Abstract

Currently, there is significant interest in developing methods for quantitative integration of multi-parametric (structural, functional) imaging data with the objective of building automated meta-classifiers to improve disease detection, diagnosis, and prognosis. Such techniques are required to address the differences in dimensionalities and scales of individual protocols, while deriving an integrated multi-parametric data representation which best captures all disease-pertinent information available. In this paper, we present a scheme called Enhanced Multi-Protocol Analysis via Intelligent Supervised Embedding (EMPrAvISE); a powerful, generalizable framework applicable to a variety of domains for multi-parametric data representation and fusion. Our scheme utilizes an ensemble of embeddings (via dimensionality reduction, DR); thereby exploiting the variance amongst multiple uncorrelated embeddings in a manner similar to ensemble classifier schemes (e.g. Bagging, Boosting). We apply this framework to the problem of prostate cancer (CaP) detection on 12 3 Tesla pre-operative in vivo multi-parametric (T2-weighted, Dynamic Contrast Enhanced, and Diffusion-weighted) magnetic resonance imaging (MRI) studies, in turn comprising a total of 39 2D planar MR images. We first align the different imaging protocols via automated image registration, followed by quantification of image attributes from individual protocols. Multiple embeddings are generated from the resultant high-dimensional feature space which are then combined intelligently to yield a single stable solution. Our scheme is employed in conjunction with graph embedding (for DR) and probabilistic boosting trees (PBTs) to detect CaP on multi-parametric MRI. Finally, a probabilistic pairwise Markov Random Field algorithm is used to apply spatial constraints to the result of the PBT classifier, yielding a per-voxel classification of CaP presence. Per-voxel evaluation of detection results against ground truth for CaP extent on MRI (obtained by spatially registering pre-operative MRI with available whole-mount histological specimens) reveals that EMPrAvISE yields a statistically significant improvement (AUC=0.77) over classifiers constructed from individual protocols (AUC=0.62, 0.62, 0.65, for T2w, DCE, DWI respectively) as well as one trained using multi-parametric feature concatenation (AUC=0.67).

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7963
DOIs
StatePublished - 2011
EventMedical Imaging 2011: Computer-Aided Diagnosis - Lake Buena Vista, FL, United States
Duration: Feb 15 2011Feb 17 2011

Other

OtherMedical Imaging 2011: Computer-Aided Diagnosis
CountryUnited States
CityLake Buena Vista, FL
Period2/15/112/17/11

Fingerprint

Magnetic resonance
embedding
Area Under Curve
magnetic resonance
Prostatic Neoplasms
cancer
Magnetic Resonance Imaging
classifiers
Imaging techniques
Classifiers
Diffusion Magnetic Resonance Imaging
ground truth
prognosis
Image registration
Fusion reactions
fusion
evaluation

Keywords

  • 3 Tesla
  • CAD
  • DCE-MRI
  • DWI-MRI
  • ensemble embedding
  • multi-modal integration
  • multi-parametric
  • multi-protocol
  • non-rigid registration
  • probabilistic boosting trees
  • prostate cancer
  • supervised learning
  • T2w MRI

ASJC Scopus subject areas

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

Cite this

Viswanath, S., Bloch, B. N., Chappelow, J., Patel, P., Rofsky, N., Lenkinski, R., ... Madabhushi, A. (2011). Enhanced multi-protocol analysis via intelligent supervised embedding (EMPrAvISE): Detecting prostate cancer on multi-parametric MRI. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 7963). [79630U] https://doi.org/10.1117/12.878312

Enhanced multi-protocol analysis via intelligent supervised embedding (EMPrAvISE) : Detecting prostate cancer on multi-parametric MRI. / Viswanath, Satish; Bloch, B. Nicholas; Chappelow, Jonathan; Patel, Pratik; Rofsky, Neil; Lenkinski, Robert; Genega, Elizabeth; Madabhushi, Anant.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963 2011. 79630U.

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

Viswanath, S, Bloch, BN, Chappelow, J, Patel, P, Rofsky, N, Lenkinski, R, Genega, E & Madabhushi, A 2011, Enhanced multi-protocol analysis via intelligent supervised embedding (EMPrAvISE): Detecting prostate cancer on multi-parametric MRI. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 7963, 79630U, Medical Imaging 2011: Computer-Aided Diagnosis, Lake Buena Vista, FL, United States, 2/15/11. https://doi.org/10.1117/12.878312
Viswanath S, Bloch BN, Chappelow J, Patel P, Rofsky N, Lenkinski R et al. Enhanced multi-protocol analysis via intelligent supervised embedding (EMPrAvISE): Detecting prostate cancer on multi-parametric MRI. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963. 2011. 79630U https://doi.org/10.1117/12.878312
Viswanath, Satish ; Bloch, B. Nicholas ; Chappelow, Jonathan ; Patel, Pratik ; Rofsky, Neil ; Lenkinski, Robert ; Genega, Elizabeth ; Madabhushi, Anant. / Enhanced multi-protocol analysis via intelligent supervised embedding (EMPrAvISE) : Detecting prostate cancer on multi-parametric MRI. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963 2011.
@inproceedings{7326ecdc83da45baa24b2a0243f09250,
title = "Enhanced multi-protocol analysis via intelligent supervised embedding (EMPrAvISE): Detecting prostate cancer on multi-parametric MRI",
abstract = "Currently, there is significant interest in developing methods for quantitative integration of multi-parametric (structural, functional) imaging data with the objective of building automated meta-classifiers to improve disease detection, diagnosis, and prognosis. Such techniques are required to address the differences in dimensionalities and scales of individual protocols, while deriving an integrated multi-parametric data representation which best captures all disease-pertinent information available. In this paper, we present a scheme called Enhanced Multi-Protocol Analysis via Intelligent Supervised Embedding (EMPrAvISE); a powerful, generalizable framework applicable to a variety of domains for multi-parametric data representation and fusion. Our scheme utilizes an ensemble of embeddings (via dimensionality reduction, DR); thereby exploiting the variance amongst multiple uncorrelated embeddings in a manner similar to ensemble classifier schemes (e.g. Bagging, Boosting). We apply this framework to the problem of prostate cancer (CaP) detection on 12 3 Tesla pre-operative in vivo multi-parametric (T2-weighted, Dynamic Contrast Enhanced, and Diffusion-weighted) magnetic resonance imaging (MRI) studies, in turn comprising a total of 39 2D planar MR images. We first align the different imaging protocols via automated image registration, followed by quantification of image attributes from individual protocols. Multiple embeddings are generated from the resultant high-dimensional feature space which are then combined intelligently to yield a single stable solution. Our scheme is employed in conjunction with graph embedding (for DR) and probabilistic boosting trees (PBTs) to detect CaP on multi-parametric MRI. Finally, a probabilistic pairwise Markov Random Field algorithm is used to apply spatial constraints to the result of the PBT classifier, yielding a per-voxel classification of CaP presence. Per-voxel evaluation of detection results against ground truth for CaP extent on MRI (obtained by spatially registering pre-operative MRI with available whole-mount histological specimens) reveals that EMPrAvISE yields a statistically significant improvement (AUC=0.77) over classifiers constructed from individual protocols (AUC=0.62, 0.62, 0.65, for T2w, DCE, DWI respectively) as well as one trained using multi-parametric feature concatenation (AUC=0.67).",
keywords = "3 Tesla, CAD, DCE-MRI, DWI-MRI, ensemble embedding, multi-modal integration, multi-parametric, multi-protocol, non-rigid registration, probabilistic boosting trees, prostate cancer, supervised learning, T2w MRI",
author = "Satish Viswanath and Bloch, {B. Nicholas} and Jonathan Chappelow and Pratik Patel and Neil Rofsky and Robert Lenkinski and Elizabeth Genega and Anant Madabhushi",
year = "2011",
doi = "10.1117/12.878312",
language = "English (US)",
isbn = "9780819485052",
volume = "7963",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Enhanced multi-protocol analysis via intelligent supervised embedding (EMPrAvISE)

T2 - Detecting prostate cancer on multi-parametric MRI

AU - Viswanath, Satish

AU - Bloch, B. Nicholas

AU - Chappelow, Jonathan

AU - Patel, Pratik

AU - Rofsky, Neil

AU - Lenkinski, Robert

AU - Genega, Elizabeth

AU - Madabhushi, Anant

PY - 2011

Y1 - 2011

N2 - Currently, there is significant interest in developing methods for quantitative integration of multi-parametric (structural, functional) imaging data with the objective of building automated meta-classifiers to improve disease detection, diagnosis, and prognosis. Such techniques are required to address the differences in dimensionalities and scales of individual protocols, while deriving an integrated multi-parametric data representation which best captures all disease-pertinent information available. In this paper, we present a scheme called Enhanced Multi-Protocol Analysis via Intelligent Supervised Embedding (EMPrAvISE); a powerful, generalizable framework applicable to a variety of domains for multi-parametric data representation and fusion. Our scheme utilizes an ensemble of embeddings (via dimensionality reduction, DR); thereby exploiting the variance amongst multiple uncorrelated embeddings in a manner similar to ensemble classifier schemes (e.g. Bagging, Boosting). We apply this framework to the problem of prostate cancer (CaP) detection on 12 3 Tesla pre-operative in vivo multi-parametric (T2-weighted, Dynamic Contrast Enhanced, and Diffusion-weighted) magnetic resonance imaging (MRI) studies, in turn comprising a total of 39 2D planar MR images. We first align the different imaging protocols via automated image registration, followed by quantification of image attributes from individual protocols. Multiple embeddings are generated from the resultant high-dimensional feature space which are then combined intelligently to yield a single stable solution. Our scheme is employed in conjunction with graph embedding (for DR) and probabilistic boosting trees (PBTs) to detect CaP on multi-parametric MRI. Finally, a probabilistic pairwise Markov Random Field algorithm is used to apply spatial constraints to the result of the PBT classifier, yielding a per-voxel classification of CaP presence. Per-voxel evaluation of detection results against ground truth for CaP extent on MRI (obtained by spatially registering pre-operative MRI with available whole-mount histological specimens) reveals that EMPrAvISE yields a statistically significant improvement (AUC=0.77) over classifiers constructed from individual protocols (AUC=0.62, 0.62, 0.65, for T2w, DCE, DWI respectively) as well as one trained using multi-parametric feature concatenation (AUC=0.67).

AB - Currently, there is significant interest in developing methods for quantitative integration of multi-parametric (structural, functional) imaging data with the objective of building automated meta-classifiers to improve disease detection, diagnosis, and prognosis. Such techniques are required to address the differences in dimensionalities and scales of individual protocols, while deriving an integrated multi-parametric data representation which best captures all disease-pertinent information available. In this paper, we present a scheme called Enhanced Multi-Protocol Analysis via Intelligent Supervised Embedding (EMPrAvISE); a powerful, generalizable framework applicable to a variety of domains for multi-parametric data representation and fusion. Our scheme utilizes an ensemble of embeddings (via dimensionality reduction, DR); thereby exploiting the variance amongst multiple uncorrelated embeddings in a manner similar to ensemble classifier schemes (e.g. Bagging, Boosting). We apply this framework to the problem of prostate cancer (CaP) detection on 12 3 Tesla pre-operative in vivo multi-parametric (T2-weighted, Dynamic Contrast Enhanced, and Diffusion-weighted) magnetic resonance imaging (MRI) studies, in turn comprising a total of 39 2D planar MR images. We first align the different imaging protocols via automated image registration, followed by quantification of image attributes from individual protocols. Multiple embeddings are generated from the resultant high-dimensional feature space which are then combined intelligently to yield a single stable solution. Our scheme is employed in conjunction with graph embedding (for DR) and probabilistic boosting trees (PBTs) to detect CaP on multi-parametric MRI. Finally, a probabilistic pairwise Markov Random Field algorithm is used to apply spatial constraints to the result of the PBT classifier, yielding a per-voxel classification of CaP presence. Per-voxel evaluation of detection results against ground truth for CaP extent on MRI (obtained by spatially registering pre-operative MRI with available whole-mount histological specimens) reveals that EMPrAvISE yields a statistically significant improvement (AUC=0.77) over classifiers constructed from individual protocols (AUC=0.62, 0.62, 0.65, for T2w, DCE, DWI respectively) as well as one trained using multi-parametric feature concatenation (AUC=0.67).

KW - 3 Tesla

KW - CAD

KW - DCE-MRI

KW - DWI-MRI

KW - ensemble embedding

KW - multi-modal integration

KW - multi-parametric

KW - multi-protocol

KW - non-rigid registration

KW - probabilistic boosting trees

KW - prostate cancer

KW - supervised learning

KW - T2w MRI

UR - http://www.scopus.com/inward/record.url?scp=79955749335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955749335&partnerID=8YFLogxK

U2 - 10.1117/12.878312

DO - 10.1117/12.878312

M3 - Conference contribution

C2 - 25301991

AN - SCOPUS:79955749335

SN - 9780819485052

VL - 7963

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -