Pulmonary nodules: Improved detection with vascular segmentation and extraction with spiral CT - Work in progress

Pierre Croisille, Miguel Souto, Maria Cova, Susan Wood, Yohannes Afework, Janet E. Kuhlman, Elias A. Zerhouni

Research output: Contribution to journalArticle

Abstract

PURPOSE: To determine whether extraction of pulmonary vessels from computed tomographic (CT) images with automated segmentation improves the detection of pulmonary nodules. MATERIALS AND METHODS: Simulated nodules were superimposed on normal spiral CT images. Eight patients referred for CT assessment of pulmonary nodules were selected for clinical evaluation. Vessels were extracted from both the simulation and clinical study with a three-dimensional seeded region-growing algorithm. Three experienced radiologists were asked to locate the nodules and assign a level of confidence to their findings. Sensitivity and proportion of false-positive results per case (FPC) were calculated. Observer performance was evaluated by alternate free-response receiver operating characteristic analysis. RESULTS: Extraction of vascular structures from CT scans improved sensitivity from 63% to 84% in the simulation study and from 58% to 78% in the clinical study. The proportion of FPC decreased from 52% to 24% and from 55% to 12%, respectively. Radiologists performed consistently better with the segmented images than with the original images in both the simulation (P = .006) and the clinical (P = .0013) study. CONCLUSION: Automated vessel subtraction and extraction improves detection of pulmonary nodules.

LanguageEnglish (US)
Pages397-401
Number of pages5
JournalRadiology
Volume197
Issue number2
StatePublished - Nov 1995

Fingerprint

Blood Vessels
Lung
ROC Curve
Radiologists
Clinical Studies

Keywords

  • Lung neoplasms, 60.30
  • Lung neoplasms, diagnosis, 60.30
  • Lung, CT, 60.12115
  • Lung, nodule, 60.281

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology

Cite this

Pulmonary nodules : Improved detection with vascular segmentation and extraction with spiral CT - Work in progress. / Croisille, Pierre; Souto, Miguel; Cova, Maria; Wood, Susan; Afework, Yohannes; Kuhlman, Janet E.; Zerhouni, Elias A.

In: Radiology, Vol. 197, No. 2, 11.1995, p. 397-401.

Research output: Contribution to journalArticle

Croisille, Pierre ; Souto, Miguel ; Cova, Maria ; Wood, Susan ; Afework, Yohannes ; Kuhlman, Janet E. ; Zerhouni, Elias A./ Pulmonary nodules : Improved detection with vascular segmentation and extraction with spiral CT - Work in progress. In: Radiology. 1995 ; Vol. 197, No. 2. pp. 397-401
@article{dc88cb3da5d54fa98aed8587b3bd0451,
title = "Pulmonary nodules: Improved detection with vascular segmentation and extraction with spiral CT - Work in progress",
abstract = "PURPOSE: To determine whether extraction of pulmonary vessels from computed tomographic (CT) images with automated segmentation improves the detection of pulmonary nodules. MATERIALS AND METHODS: Simulated nodules were superimposed on normal spiral CT images. Eight patients referred for CT assessment of pulmonary nodules were selected for clinical evaluation. Vessels were extracted from both the simulation and clinical study with a three-dimensional seeded region-growing algorithm. Three experienced radiologists were asked to locate the nodules and assign a level of confidence to their findings. Sensitivity and proportion of false-positive results per case (FPC) were calculated. Observer performance was evaluated by alternate free-response receiver operating characteristic analysis. RESULTS: Extraction of vascular structures from CT scans improved sensitivity from 63{\%} to 84{\%} in the simulation study and from 58{\%} to 78{\%} in the clinical study. The proportion of FPC decreased from 52{\%} to 24{\%} and from 55{\%} to 12{\%}, respectively. Radiologists performed consistently better with the segmented images than with the original images in both the simulation (P = .006) and the clinical (P = .0013) study. CONCLUSION: Automated vessel subtraction and extraction improves detection of pulmonary nodules.",
keywords = "Lung neoplasms, 60.30, Lung neoplasms, diagnosis, 60.30, Lung, CT, 60.12115, Lung, nodule, 60.281",
author = "Pierre Croisille and Miguel Souto and Maria Cova and Susan Wood and Yohannes Afework and Kuhlman, {Janet E.} and Zerhouni, {Elias A.}",
year = "1995",
month = "11",
language = "English (US)",
volume = "197",
pages = "397--401",
journal = "Radiology",
issn = "0033-8419",
publisher = "Radiological Society of North America Inc.",
number = "2",

}

TY - JOUR

T1 - Pulmonary nodules

T2 - Radiology

AU - Croisille,Pierre

AU - Souto,Miguel

AU - Cova,Maria

AU - Wood,Susan

AU - Afework,Yohannes

AU - Kuhlman,Janet E.

AU - Zerhouni,Elias A.

PY - 1995/11

Y1 - 1995/11

N2 - PURPOSE: To determine whether extraction of pulmonary vessels from computed tomographic (CT) images with automated segmentation improves the detection of pulmonary nodules. MATERIALS AND METHODS: Simulated nodules were superimposed on normal spiral CT images. Eight patients referred for CT assessment of pulmonary nodules were selected for clinical evaluation. Vessels were extracted from both the simulation and clinical study with a three-dimensional seeded region-growing algorithm. Three experienced radiologists were asked to locate the nodules and assign a level of confidence to their findings. Sensitivity and proportion of false-positive results per case (FPC) were calculated. Observer performance was evaluated by alternate free-response receiver operating characteristic analysis. RESULTS: Extraction of vascular structures from CT scans improved sensitivity from 63% to 84% in the simulation study and from 58% to 78% in the clinical study. The proportion of FPC decreased from 52% to 24% and from 55% to 12%, respectively. Radiologists performed consistently better with the segmented images than with the original images in both the simulation (P = .006) and the clinical (P = .0013) study. CONCLUSION: Automated vessel subtraction and extraction improves detection of pulmonary nodules.

AB - PURPOSE: To determine whether extraction of pulmonary vessels from computed tomographic (CT) images with automated segmentation improves the detection of pulmonary nodules. MATERIALS AND METHODS: Simulated nodules were superimposed on normal spiral CT images. Eight patients referred for CT assessment of pulmonary nodules were selected for clinical evaluation. Vessels were extracted from both the simulation and clinical study with a three-dimensional seeded region-growing algorithm. Three experienced radiologists were asked to locate the nodules and assign a level of confidence to their findings. Sensitivity and proportion of false-positive results per case (FPC) were calculated. Observer performance was evaluated by alternate free-response receiver operating characteristic analysis. RESULTS: Extraction of vascular structures from CT scans improved sensitivity from 63% to 84% in the simulation study and from 58% to 78% in the clinical study. The proportion of FPC decreased from 52% to 24% and from 55% to 12%, respectively. Radiologists performed consistently better with the segmented images than with the original images in both the simulation (P = .006) and the clinical (P = .0013) study. CONCLUSION: Automated vessel subtraction and extraction improves detection of pulmonary nodules.

KW - Lung neoplasms, 60.30

KW - Lung neoplasms, diagnosis, 60.30

KW - Lung, CT, 60.12115

KW - Lung, nodule, 60.281

UR - http://www.scopus.com/inward/record.url?scp=0028787508&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028787508&partnerID=8YFLogxK

M3 - Article

VL - 197

SP - 397

EP - 401

JO - Radiology

JF - Radiology

SN - 0033-8419

IS - 2

ER -