Automating the expert consensus paradigm for robust lung tissue classification

Srinivasan Rajagopalan; Ronald A. Karwoski; Sushravya Raghunath; Brian J. Bartholmai; Richard A. Robb

doi:10.1117/12.912009

Automating the expert consensus paradigm for robust lung tissue classification

Srinivasan Rajagopalan, Ronald A. Karwoski, Sushravya Raghunath, Brian J. Bartholmai, Richard A. Robb

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Clinicians confirm the efficacy of dynamic multidisciplinary interactions in diagnosing Lung disease/wellness from CT scans. However, routine clinical practice cannot readily accomodate such interactions. Current schemes for automating lung tissue classification are based on a single elusive disease differentiating metric; this undermines their reliability in routine diagnosis. We propose a computational workflow that uses a collection (#: 15) of probability density functions (pdf)-based similarity metrics to automatically cluster pattern-specific (#patterns: 5) volumes of interest (#VOI: 976) extracted from the lung CT scans of 14 patients. The resultant clusters are refined for intra-partition compactness and subsequently aggregated into a super cluster using a cluster ensemble technique. The super clusters were validated against the consensus agreement of four clinical experts. The aggregations correlated strongly with expert consensus. By effectively mimicking the expertise of physicians, the proposed workflow could make automation of lung tissue classification a clinical reality.

Original language	English (US)
Title of host publication	Medical Imaging 2012
Subtitle of host publication	Computer-Aided Diagnosis
DOIs	https://doi.org/10.1117/12.912009
State	Published - Dec 1 2012
Event	Medical Imaging 2012: Computer-Aided Diagnosis - San Diego, CA, United States Duration: Feb 7 2012 → Feb 9 2012

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	8315
ISSN (Print)	1605-7422

Other

Other	Medical Imaging 2012: Computer-Aided Diagnosis
Country/Territory	United States
City	San Diego, CA
Period	2/7/12 → 2/9/12

ASJC Scopus subject areas

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

Access to Document

10.1117/12.912009

Cite this

Automating the expert consensus paradigm for robust lung tissue classification. / Rajagopalan, Srinivasan; Karwoski, Ronald A.; Raghunath, Sushravya et al.
Medical Imaging 2012: Computer-Aided Diagnosis. 2012. 831530 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 8315).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Rajagopalan, S, Karwoski, RA, Raghunath, S, Bartholmai, BJ & Robb, RA 2012, Automating the expert consensus paradigm for robust lung tissue classification. in Medical Imaging 2012: Computer-Aided Diagnosis., 831530, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 8315, Medical Imaging 2012: Computer-Aided Diagnosis, San Diego, CA, United States, 2/7/12. https://doi.org/10.1117/12.912009

@inproceedings{178bd9860e524bb18a6707837b3a142c,

title = "Automating the expert consensus paradigm for robust lung tissue classification",

abstract = "Clinicians confirm the efficacy of dynamic multidisciplinary interactions in diagnosing Lung disease/wellness from CT scans. However, routine clinical practice cannot readily accomodate such interactions. Current schemes for automating lung tissue classification are based on a single elusive disease differentiating metric; this undermines their reliability in routine diagnosis. We propose a computational workflow that uses a collection (#: 15) of probability density functions (pdf)-based similarity metrics to automatically cluster pattern-specific (#patterns: 5) volumes of interest (#VOI: 976) extracted from the lung CT scans of 14 patients. The resultant clusters are refined for intra-partition compactness and subsequently aggregated into a super cluster using a cluster ensemble technique. The super clusters were validated against the consensus agreement of four clinical experts. The aggregations correlated strongly with expert consensus. By effectively mimicking the expertise of physicians, the proposed workflow could make automation of lung tissue classification a clinical reality.",

author = "Srinivasan Rajagopalan and Karwoski, {Ronald A.} and Sushravya Raghunath and Bartholmai, {Brian J.} and Robb, {Richard A.}",

year = "2012",

month = dec,

day = "1",

doi = "10.1117/12.912009",

language = "English (US)",

isbn = "9780819489647",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

booktitle = "Medical Imaging 2012",

note = "Medical Imaging 2012: Computer-Aided Diagnosis ; Conference date: 07-02-2012 Through 09-02-2012",

}

TY - GEN

T1 - Automating the expert consensus paradigm for robust lung tissue classification

AU - Rajagopalan, Srinivasan

AU - Karwoski, Ronald A.

AU - Raghunath, Sushravya

AU - Bartholmai, Brian J.

AU - Robb, Richard A.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Clinicians confirm the efficacy of dynamic multidisciplinary interactions in diagnosing Lung disease/wellness from CT scans. However, routine clinical practice cannot readily accomodate such interactions. Current schemes for automating lung tissue classification are based on a single elusive disease differentiating metric; this undermines their reliability in routine diagnosis. We propose a computational workflow that uses a collection (#: 15) of probability density functions (pdf)-based similarity metrics to automatically cluster pattern-specific (#patterns: 5) volumes of interest (#VOI: 976) extracted from the lung CT scans of 14 patients. The resultant clusters are refined for intra-partition compactness and subsequently aggregated into a super cluster using a cluster ensemble technique. The super clusters were validated against the consensus agreement of four clinical experts. The aggregations correlated strongly with expert consensus. By effectively mimicking the expertise of physicians, the proposed workflow could make automation of lung tissue classification a clinical reality.

AB - Clinicians confirm the efficacy of dynamic multidisciplinary interactions in diagnosing Lung disease/wellness from CT scans. However, routine clinical practice cannot readily accomodate such interactions. Current schemes for automating lung tissue classification are based on a single elusive disease differentiating metric; this undermines their reliability in routine diagnosis. We propose a computational workflow that uses a collection (#: 15) of probability density functions (pdf)-based similarity metrics to automatically cluster pattern-specific (#patterns: 5) volumes of interest (#VOI: 976) extracted from the lung CT scans of 14 patients. The resultant clusters are refined for intra-partition compactness and subsequently aggregated into a super cluster using a cluster ensemble technique. The super clusters were validated against the consensus agreement of four clinical experts. The aggregations correlated strongly with expert consensus. By effectively mimicking the expertise of physicians, the proposed workflow could make automation of lung tissue classification a clinical reality.

UR - http://www.scopus.com/inward/record.url?scp=84874852543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874852543&partnerID=8YFLogxK

U2 - 10.1117/12.912009

DO - 10.1117/12.912009

M3 - Conference contribution

AN - SCOPUS:84874852543

SN - 9780819489647

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2012

T2 - Medical Imaging 2012: Computer-Aided Diagnosis

Y2 - 7 February 2012 through 9 February 2012

ER -

Automating the expert consensus paradigm for robust lung tissue classification

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this