SU‐GG‐I‐04: Grid‐Computing for Optimization of CAD

A. Jamieson, M. Giger, M. Wilde, L. Pesce, I. Foster

Research output: Contribution to journalArticle

Abstract

Purpose: Pilot study to utilize large scale parallel grid computing to harness the nationwide cluster infrastructure for optimization of medical image analysis parameters. Method and Materials: A previously developed CAD scheme for mass lesions in mammography was ported onto the grid computing environment by wrapping the algorithm code with the virtual data language (VDL). The CAD scheme was then configured into a parallelizable workflow by the grid‐software. The workflows were executed using two test clusters (in Santa Monica, CA and Chicago, IL) consisting of over 220 dual‐CPU nodes combined. Using the grid‐environment workflow, parameter sweeps were conducted for lesion segmentation settings based on radial‐gradient‐index (RGI) methods. Specifically, the Gaussian width (GW) used in initially filtering lesion images for segmentation was varied by increments of 1 mm from 1 to 60 mm. For each GW sweep the entire 850 biopsy‐proven mass lesion database (411 benign, 439 malignant) was analyzed. In each, 29 different mathematical descriptor features were calculated, followed by feature selection and merging with linear discriminate analysis. Diagnostic performance was estimated by ROC analysis by calculating AUC (from PROPROC) values based on both individual features alone, and merged. For merged classifiers, AUC values were found using round‐robin case‐by‐case removal and replacement. Results: Computation jobs requiring over 30 CPU hours on a single lab computer were completed in approximately 35 minutes in this preliminary study. Merged AUC values increased from 0.50 (std.err.=0.018) at GW of 1mm with, to 0.81 (std.err.=0.015) at 10mm GW, with relative plateaus across the rest of the parameter space to 60mm. Conclusion: The parameter space sweep in GW identified trends in individual feature performance as well as merged results. Large scale, computationally intensive image analysis can be carried out in a timely fashion, feasible for expedited experimental discovery, as well as for more thorough future statistical analysis.

Original languageEnglish (US)
Number of pages1
JournalMedical physics
Volume35
Issue number6
DOIs
StatePublished - Jun 2008
Externally publishedYes

Fingerprint

Workflow
Area Under Curve
Mammography
ROC Curve
Language
Databases

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

SU‐GG‐I‐04 : Grid‐Computing for Optimization of CAD. / Jamieson, A.; Giger, M.; Wilde, M.; Pesce, L.; Foster, I.

In: Medical physics, Vol. 35, No. 6, 06.2008.

Research output: Contribution to journalArticle

Jamieson, A. ; Giger, M. ; Wilde, M. ; Pesce, L. ; Foster, I. / SU‐GG‐I‐04 : Grid‐Computing for Optimization of CAD. In: Medical physics. 2008 ; Vol. 35, No. 6.
@article{84e4d1adb8784bdead7d45197f240a9c,
title = "SU‐GG‐I‐04: Grid‐Computing for Optimization of CAD",
abstract = "Purpose: Pilot study to utilize large scale parallel grid computing to harness the nationwide cluster infrastructure for optimization of medical image analysis parameters. Method and Materials: A previously developed CAD scheme for mass lesions in mammography was ported onto the grid computing environment by wrapping the algorithm code with the virtual data language (VDL). The CAD scheme was then configured into a parallelizable workflow by the grid‐software. The workflows were executed using two test clusters (in Santa Monica, CA and Chicago, IL) consisting of over 220 dual‐CPU nodes combined. Using the grid‐environment workflow, parameter sweeps were conducted for lesion segmentation settings based on radial‐gradient‐index (RGI) methods. Specifically, the Gaussian width (GW) used in initially filtering lesion images for segmentation was varied by increments of 1 mm from 1 to 60 mm. For each GW sweep the entire 850 biopsy‐proven mass lesion database (411 benign, 439 malignant) was analyzed. In each, 29 different mathematical descriptor features were calculated, followed by feature selection and merging with linear discriminate analysis. Diagnostic performance was estimated by ROC analysis by calculating AUC (from PROPROC) values based on both individual features alone, and merged. For merged classifiers, AUC values were found using round‐robin case‐by‐case removal and replacement. Results: Computation jobs requiring over 30 CPU hours on a single lab computer were completed in approximately 35 minutes in this preliminary study. Merged AUC values increased from 0.50 (std.err.=0.018) at GW of 1mm with, to 0.81 (std.err.=0.015) at 10mm GW, with relative plateaus across the rest of the parameter space to 60mm. Conclusion: The parameter space sweep in GW identified trends in individual feature performance as well as merged results. Large scale, computationally intensive image analysis can be carried out in a timely fashion, feasible for expedited experimental discovery, as well as for more thorough future statistical analysis.",
author = "A. Jamieson and M. Giger and M. Wilde and L. Pesce and I. Foster",
year = "2008",
month = "6",
doi = "10.1118/1.2961402",
language = "English (US)",
volume = "35",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "6",

}

TY - JOUR

T1 - SU‐GG‐I‐04

T2 - Grid‐Computing for Optimization of CAD

AU - Jamieson, A.

AU - Giger, M.

AU - Wilde, M.

AU - Pesce, L.

AU - Foster, I.

PY - 2008/6

Y1 - 2008/6

N2 - Purpose: Pilot study to utilize large scale parallel grid computing to harness the nationwide cluster infrastructure for optimization of medical image analysis parameters. Method and Materials: A previously developed CAD scheme for mass lesions in mammography was ported onto the grid computing environment by wrapping the algorithm code with the virtual data language (VDL). The CAD scheme was then configured into a parallelizable workflow by the grid‐software. The workflows were executed using two test clusters (in Santa Monica, CA and Chicago, IL) consisting of over 220 dual‐CPU nodes combined. Using the grid‐environment workflow, parameter sweeps were conducted for lesion segmentation settings based on radial‐gradient‐index (RGI) methods. Specifically, the Gaussian width (GW) used in initially filtering lesion images for segmentation was varied by increments of 1 mm from 1 to 60 mm. For each GW sweep the entire 850 biopsy‐proven mass lesion database (411 benign, 439 malignant) was analyzed. In each, 29 different mathematical descriptor features were calculated, followed by feature selection and merging with linear discriminate analysis. Diagnostic performance was estimated by ROC analysis by calculating AUC (from PROPROC) values based on both individual features alone, and merged. For merged classifiers, AUC values were found using round‐robin case‐by‐case removal and replacement. Results: Computation jobs requiring over 30 CPU hours on a single lab computer were completed in approximately 35 minutes in this preliminary study. Merged AUC values increased from 0.50 (std.err.=0.018) at GW of 1mm with, to 0.81 (std.err.=0.015) at 10mm GW, with relative plateaus across the rest of the parameter space to 60mm. Conclusion: The parameter space sweep in GW identified trends in individual feature performance as well as merged results. Large scale, computationally intensive image analysis can be carried out in a timely fashion, feasible for expedited experimental discovery, as well as for more thorough future statistical analysis.

AB - Purpose: Pilot study to utilize large scale parallel grid computing to harness the nationwide cluster infrastructure for optimization of medical image analysis parameters. Method and Materials: A previously developed CAD scheme for mass lesions in mammography was ported onto the grid computing environment by wrapping the algorithm code with the virtual data language (VDL). The CAD scheme was then configured into a parallelizable workflow by the grid‐software. The workflows were executed using two test clusters (in Santa Monica, CA and Chicago, IL) consisting of over 220 dual‐CPU nodes combined. Using the grid‐environment workflow, parameter sweeps were conducted for lesion segmentation settings based on radial‐gradient‐index (RGI) methods. Specifically, the Gaussian width (GW) used in initially filtering lesion images for segmentation was varied by increments of 1 mm from 1 to 60 mm. For each GW sweep the entire 850 biopsy‐proven mass lesion database (411 benign, 439 malignant) was analyzed. In each, 29 different mathematical descriptor features were calculated, followed by feature selection and merging with linear discriminate analysis. Diagnostic performance was estimated by ROC analysis by calculating AUC (from PROPROC) values based on both individual features alone, and merged. For merged classifiers, AUC values were found using round‐robin case‐by‐case removal and replacement. Results: Computation jobs requiring over 30 CPU hours on a single lab computer were completed in approximately 35 minutes in this preliminary study. Merged AUC values increased from 0.50 (std.err.=0.018) at GW of 1mm with, to 0.81 (std.err.=0.015) at 10mm GW, with relative plateaus across the rest of the parameter space to 60mm. Conclusion: The parameter space sweep in GW identified trends in individual feature performance as well as merged results. Large scale, computationally intensive image analysis can be carried out in a timely fashion, feasible for expedited experimental discovery, as well as for more thorough future statistical analysis.

UR - http://www.scopus.com/inward/record.url?scp=85024774895&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024774895&partnerID=8YFLogxK

U2 - 10.1118/1.2961402

DO - 10.1118/1.2961402

M3 - Article

AN - SCOPUS:85024774895

VL - 35

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 6

ER -