Can image analysis on high-resolution computed tomography predict non-invasive growth in adenocarcinoma of the lung?

Yukihiro Yoshida, Miki Sakamoto, Eriko Maeda, Hiroshi Ohtsu, Satoshi Ota, Hisao Asamura, Jun Nakajima

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Purpose: Preoperative radiological predictions of pathological invasiveness must be objective and reproducible in addition to being accurate when considering limited surgery for early lung cancer. Methods: Two cohorts were used for the analysis. Two independent observers traced lesion edges and measured areas and proportions of solid component on tumor images with the largest diameter by high resolution computed tomography images and “Image J” software. Results: The value of the intraclass correlation was 0.997 (95% confidence interval [CI], 0.996-0.998) for the area of solid component and 0.979 (95%CI, 0.958-0.986) for the proportion of solid component, suggesting such parameters were reliable in terms of reproducibility. Az value was 0.898 (95%CI, 0.842-0.953) for the area of solid component and 0.882 (95%CI, 0.816-0.949) for the proportion of solid component, demonstrating 2 parameters were both highly predictive of non-invasive adenocarcinoma. The optimal prediction of non-invasive adenocarcinoma with a cut-off value of 7.5 mm2 for the area of solid component resulted in a sensitivity of 85.3% and specificity of 86.2% in Cohort 1 and a sensitivity of 66.7% and specificity of 88.5% in Cohort 2. Conclusion: Image analysis using “Image J” software was promising for predicting non-invasive adenocarcinoma with its limited inter-observer variability and high predictive performance.

Original languageEnglish
Pages (from-to)8-13
Number of pages6
JournalAnnals of Thoracic and Cardiovascular Surgery
Volume21
Issue number1
DOIs
Publication statusPublished - 2015
Externally publishedYes

Fingerprint

Tomography
Confidence Intervals
Adenocarcinoma
Growth
Software
Sensitivity and Specificity
Observer Variation
Lung Neoplasms
Adenocarcinoma of lung
Neoplasms

Keywords

  • Carcinoma
  • Non-small-cell lung
  • Pathology
  • Radiology
  • Tomography
  • X-ray computed

ASJC Scopus subject areas

  • Surgery
  • Cardiology and Cardiovascular Medicine
  • Pulmonary and Respiratory Medicine
  • Gastroenterology

Cite this

Can image analysis on high-resolution computed tomography predict non-invasive growth in adenocarcinoma of the lung? / Yoshida, Yukihiro; Sakamoto, Miki; Maeda, Eriko; Ohtsu, Hiroshi; Ota, Satoshi; Asamura, Hisao; Nakajima, Jun.

In: Annals of Thoracic and Cardiovascular Surgery, Vol. 21, No. 1, 2015, p. 8-13.

Research output: Contribution to journalArticle

Yoshida, Yukihiro ; Sakamoto, Miki ; Maeda, Eriko ; Ohtsu, Hiroshi ; Ota, Satoshi ; Asamura, Hisao ; Nakajima, Jun. / Can image analysis on high-resolution computed tomography predict non-invasive growth in adenocarcinoma of the lung?. In: Annals of Thoracic and Cardiovascular Surgery. 2015 ; Vol. 21, No. 1. pp. 8-13.
@article{406b172d00cf41e28c36cd636c7a81d6,
title = "Can image analysis on high-resolution computed tomography predict non-invasive growth in adenocarcinoma of the lung?",
abstract = "Purpose: Preoperative radiological predictions of pathological invasiveness must be objective and reproducible in addition to being accurate when considering limited surgery for early lung cancer. Methods: Two cohorts were used for the analysis. Two independent observers traced lesion edges and measured areas and proportions of solid component on tumor images with the largest diameter by high resolution computed tomography images and “Image J” software. Results: The value of the intraclass correlation was 0.997 (95{\%} confidence interval [CI], 0.996-0.998) for the area of solid component and 0.979 (95{\%}CI, 0.958-0.986) for the proportion of solid component, suggesting such parameters were reliable in terms of reproducibility. Az value was 0.898 (95{\%}CI, 0.842-0.953) for the area of solid component and 0.882 (95{\%}CI, 0.816-0.949) for the proportion of solid component, demonstrating 2 parameters were both highly predictive of non-invasive adenocarcinoma. The optimal prediction of non-invasive adenocarcinoma with a cut-off value of 7.5 mm2 for the area of solid component resulted in a sensitivity of 85.3{\%} and specificity of 86.2{\%} in Cohort 1 and a sensitivity of 66.7{\%} and specificity of 88.5{\%} in Cohort 2. Conclusion: Image analysis using “Image J” software was promising for predicting non-invasive adenocarcinoma with its limited inter-observer variability and high predictive performance.",
keywords = "Carcinoma, Non-small-cell lung, Pathology, Radiology, Tomography, X-ray computed",
author = "Yukihiro Yoshida and Miki Sakamoto and Eriko Maeda and Hiroshi Ohtsu and Satoshi Ota and Hisao Asamura and Jun Nakajima",
year = "2015",
doi = "10.5761/atcs.oa.13-00252",
language = "English",
volume = "21",
pages = "8--13",
journal = "Annals of Thoracic and Cardiovascular Surgery",
issn = "1341-1098",
publisher = "Japanese Association for Coronary Artery Surgery",
number = "1",

}

TY - JOUR

T1 - Can image analysis on high-resolution computed tomography predict non-invasive growth in adenocarcinoma of the lung?

AU - Yoshida, Yukihiro

AU - Sakamoto, Miki

AU - Maeda, Eriko

AU - Ohtsu, Hiroshi

AU - Ota, Satoshi

AU - Asamura, Hisao

AU - Nakajima, Jun

PY - 2015

Y1 - 2015

N2 - Purpose: Preoperative radiological predictions of pathological invasiveness must be objective and reproducible in addition to being accurate when considering limited surgery for early lung cancer. Methods: Two cohorts were used for the analysis. Two independent observers traced lesion edges and measured areas and proportions of solid component on tumor images with the largest diameter by high resolution computed tomography images and “Image J” software. Results: The value of the intraclass correlation was 0.997 (95% confidence interval [CI], 0.996-0.998) for the area of solid component and 0.979 (95%CI, 0.958-0.986) for the proportion of solid component, suggesting such parameters were reliable in terms of reproducibility. Az value was 0.898 (95%CI, 0.842-0.953) for the area of solid component and 0.882 (95%CI, 0.816-0.949) for the proportion of solid component, demonstrating 2 parameters were both highly predictive of non-invasive adenocarcinoma. The optimal prediction of non-invasive adenocarcinoma with a cut-off value of 7.5 mm2 for the area of solid component resulted in a sensitivity of 85.3% and specificity of 86.2% in Cohort 1 and a sensitivity of 66.7% and specificity of 88.5% in Cohort 2. Conclusion: Image analysis using “Image J” software was promising for predicting non-invasive adenocarcinoma with its limited inter-observer variability and high predictive performance.

AB - Purpose: Preoperative radiological predictions of pathological invasiveness must be objective and reproducible in addition to being accurate when considering limited surgery for early lung cancer. Methods: Two cohorts were used for the analysis. Two independent observers traced lesion edges and measured areas and proportions of solid component on tumor images with the largest diameter by high resolution computed tomography images and “Image J” software. Results: The value of the intraclass correlation was 0.997 (95% confidence interval [CI], 0.996-0.998) for the area of solid component and 0.979 (95%CI, 0.958-0.986) for the proportion of solid component, suggesting such parameters were reliable in terms of reproducibility. Az value was 0.898 (95%CI, 0.842-0.953) for the area of solid component and 0.882 (95%CI, 0.816-0.949) for the proportion of solid component, demonstrating 2 parameters were both highly predictive of non-invasive adenocarcinoma. The optimal prediction of non-invasive adenocarcinoma with a cut-off value of 7.5 mm2 for the area of solid component resulted in a sensitivity of 85.3% and specificity of 86.2% in Cohort 1 and a sensitivity of 66.7% and specificity of 88.5% in Cohort 2. Conclusion: Image analysis using “Image J” software was promising for predicting non-invasive adenocarcinoma with its limited inter-observer variability and high predictive performance.

KW - Carcinoma

KW - Non-small-cell lung

KW - Pathology

KW - Radiology

KW - Tomography

KW - X-ray computed

UR - http://www.scopus.com/inward/record.url?scp=84923096127&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923096127&partnerID=8YFLogxK

U2 - 10.5761/atcs.oa.13-00252

DO - 10.5761/atcs.oa.13-00252

M3 - Article

C2 - 24747544

AN - SCOPUS:84923096127

VL - 21

SP - 8

EP - 13

JO - Annals of Thoracic and Cardiovascular Surgery

JF - Annals of Thoracic and Cardiovascular Surgery

SN - 1341-1098

IS - 1

ER -