CT texture analysis of histologically proven benign and malignant lung lesions

Subba R. Digumarthy, Atul M. Padole, Roberto Lo Gullo, Ramandeep Singh, Jo Anne O. Shepard, Mannudeep K. Kalra

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The purpose of our study was to determine accuracy of CT texture analysis (CTTA) for differentiating benign from malignant pulmonary nodules, and well-differentiated from poorly differentiated lung cancers, with histology as the standard of reference. In this IRB-Approved study, 175 adult patients (average age 66 ± 12 years; age range 27-89 years, male 82: female 93) who underwent a noncontrast chest CT examination prior to CT-guided biopsy of pulmonary nodules were included. There were 57 benign (24 tumors or tumor-like lesions; 33 inflammatory conditions) and 120 malignant (29 well-differentiated adenocarcinomas, 48 poorly differentiated adenocarcinomas, and 43 squamous cell carcinomas) diagnoses on pathology. CTTA was performed on the prebiopsy noncontrast CT images using a commercially available software (TexRAD limited, UK). The CTCA features analyzed included mean HU values, percent positive pixels (PPP), mean value of positive pixels (MPP), standard deviation (SD), normalized SD, skewness, kurtosis, and entropy. The ROC analyses showed that normalized SD [AUC: 0.63, (CI: 0.55-72), P = .003] had moderate accuracy for differentiating between benign and malignant lesions. For differentiating among well-differentiated and poorly differentiated tumors, the ROC analysis showed that except skewness all other parameters were statistically significant The AUC values of other CTTA parameters were: mean (AUC: 0.73-0.76, P = .001-< .0001). CT texture analyses can reliably predict well-and poorly differentiated lung malignancies. However, inflammatory lung lesions with tissue heterogeneity negatively affect the performance of CTTA when it comes to differentiation between benign and malignant pulmonary nodules.

Original languageEnglish
Article numbere11172
JournalMedicine (United States)
Volume97
Issue number26
DOIs
Publication statusPublished - Jun 1 2018

Fingerprint

Lung
Area Under Curve
ROC Curve
Neoplasms
Adenocarcinoma
Research Ethics Committees
Entropy
Squamous Cell Carcinoma
Lung Neoplasms
Histology
Thorax
Software
Pathology
Biopsy

Keywords

  • benign and malignant lung nodules
  • CT texture analysis
  • lung biopsy
  • well-and poorly differentiated lung malignancies

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Digumarthy, S. R., Padole, A. M., Lo Gullo, R., Singh, R., Shepard, J. A. O., & Kalra, M. K. (2018). CT texture analysis of histologically proven benign and malignant lung lesions. Medicine (United States), 97(26), [e11172]. https://doi.org/10.1097/MD.0000000000011172

CT texture analysis of histologically proven benign and malignant lung lesions. / Digumarthy, Subba R.; Padole, Atul M.; Lo Gullo, Roberto; Singh, Ramandeep; Shepard, Jo Anne O.; Kalra, Mannudeep K.

In: Medicine (United States), Vol. 97, No. 26, e11172, 01.06.2018.

Research output: Contribution to journalArticle

Digumarthy, Subba R. ; Padole, Atul M. ; Lo Gullo, Roberto ; Singh, Ramandeep ; Shepard, Jo Anne O. ; Kalra, Mannudeep K. / CT texture analysis of histologically proven benign and malignant lung lesions. In: Medicine (United States). 2018 ; Vol. 97, No. 26.
@article{9c3ee6d8a23a424d8be7413920414571,
title = "CT texture analysis of histologically proven benign and malignant lung lesions",
abstract = "The purpose of our study was to determine accuracy of CT texture analysis (CTTA) for differentiating benign from malignant pulmonary nodules, and well-differentiated from poorly differentiated lung cancers, with histology as the standard of reference. In this IRB-Approved study, 175 adult patients (average age 66 ± 12 years; age range 27-89 years, male 82: female 93) who underwent a noncontrast chest CT examination prior to CT-guided biopsy of pulmonary nodules were included. There were 57 benign (24 tumors or tumor-like lesions; 33 inflammatory conditions) and 120 malignant (29 well-differentiated adenocarcinomas, 48 poorly differentiated adenocarcinomas, and 43 squamous cell carcinomas) diagnoses on pathology. CTTA was performed on the prebiopsy noncontrast CT images using a commercially available software (TexRAD limited, UK). The CTCA features analyzed included mean HU values, percent positive pixels (PPP), mean value of positive pixels (MPP), standard deviation (SD), normalized SD, skewness, kurtosis, and entropy. The ROC analyses showed that normalized SD [AUC: 0.63, (CI: 0.55-72), P = .003] had moderate accuracy for differentiating between benign and malignant lesions. For differentiating among well-differentiated and poorly differentiated tumors, the ROC analysis showed that except skewness all other parameters were statistically significant The AUC values of other CTTA parameters were: mean (AUC: 0.73-0.76, P = .001-< .0001). CT texture analyses can reliably predict well-and poorly differentiated lung malignancies. However, inflammatory lung lesions with tissue heterogeneity negatively affect the performance of CTTA when it comes to differentiation between benign and malignant pulmonary nodules.",
keywords = "benign and malignant lung nodules, CT texture analysis, lung biopsy, well-and poorly differentiated lung malignancies",
author = "Digumarthy, {Subba R.} and Padole, {Atul M.} and {Lo Gullo}, Roberto and Ramandeep Singh and Shepard, {Jo Anne O.} and Kalra, {Mannudeep K.}",
year = "2018",
month = "6",
day = "1",
doi = "10.1097/MD.0000000000011172",
language = "English",
volume = "97",
journal = "Medicine; analytical reviews of general medicine, neurology, psychiatry, dermatology, and pediatries",
issn = "0025-7974",
publisher = "Lippincott Williams and Wilkins",
number = "26",

}

TY - JOUR

T1 - CT texture analysis of histologically proven benign and malignant lung lesions

AU - Digumarthy, Subba R.

AU - Padole, Atul M.

AU - Lo Gullo, Roberto

AU - Singh, Ramandeep

AU - Shepard, Jo Anne O.

AU - Kalra, Mannudeep K.

PY - 2018/6/1

Y1 - 2018/6/1

N2 - The purpose of our study was to determine accuracy of CT texture analysis (CTTA) for differentiating benign from malignant pulmonary nodules, and well-differentiated from poorly differentiated lung cancers, with histology as the standard of reference. In this IRB-Approved study, 175 adult patients (average age 66 ± 12 years; age range 27-89 years, male 82: female 93) who underwent a noncontrast chest CT examination prior to CT-guided biopsy of pulmonary nodules were included. There were 57 benign (24 tumors or tumor-like lesions; 33 inflammatory conditions) and 120 malignant (29 well-differentiated adenocarcinomas, 48 poorly differentiated adenocarcinomas, and 43 squamous cell carcinomas) diagnoses on pathology. CTTA was performed on the prebiopsy noncontrast CT images using a commercially available software (TexRAD limited, UK). The CTCA features analyzed included mean HU values, percent positive pixels (PPP), mean value of positive pixels (MPP), standard deviation (SD), normalized SD, skewness, kurtosis, and entropy. The ROC analyses showed that normalized SD [AUC: 0.63, (CI: 0.55-72), P = .003] had moderate accuracy for differentiating between benign and malignant lesions. For differentiating among well-differentiated and poorly differentiated tumors, the ROC analysis showed that except skewness all other parameters were statistically significant The AUC values of other CTTA parameters were: mean (AUC: 0.73-0.76, P = .001-< .0001). CT texture analyses can reliably predict well-and poorly differentiated lung malignancies. However, inflammatory lung lesions with tissue heterogeneity negatively affect the performance of CTTA when it comes to differentiation between benign and malignant pulmonary nodules.

AB - The purpose of our study was to determine accuracy of CT texture analysis (CTTA) for differentiating benign from malignant pulmonary nodules, and well-differentiated from poorly differentiated lung cancers, with histology as the standard of reference. In this IRB-Approved study, 175 adult patients (average age 66 ± 12 years; age range 27-89 years, male 82: female 93) who underwent a noncontrast chest CT examination prior to CT-guided biopsy of pulmonary nodules were included. There were 57 benign (24 tumors or tumor-like lesions; 33 inflammatory conditions) and 120 malignant (29 well-differentiated adenocarcinomas, 48 poorly differentiated adenocarcinomas, and 43 squamous cell carcinomas) diagnoses on pathology. CTTA was performed on the prebiopsy noncontrast CT images using a commercially available software (TexRAD limited, UK). The CTCA features analyzed included mean HU values, percent positive pixels (PPP), mean value of positive pixels (MPP), standard deviation (SD), normalized SD, skewness, kurtosis, and entropy. The ROC analyses showed that normalized SD [AUC: 0.63, (CI: 0.55-72), P = .003] had moderate accuracy for differentiating between benign and malignant lesions. For differentiating among well-differentiated and poorly differentiated tumors, the ROC analysis showed that except skewness all other parameters were statistically significant The AUC values of other CTTA parameters were: mean (AUC: 0.73-0.76, P = .001-< .0001). CT texture analyses can reliably predict well-and poorly differentiated lung malignancies. However, inflammatory lung lesions with tissue heterogeneity negatively affect the performance of CTTA when it comes to differentiation between benign and malignant pulmonary nodules.

KW - benign and malignant lung nodules

KW - CT texture analysis

KW - lung biopsy

KW - well-and poorly differentiated lung malignancies

UR - http://www.scopus.com/inward/record.url?scp=85049391861&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049391861&partnerID=8YFLogxK

U2 - 10.1097/MD.0000000000011172

DO - 10.1097/MD.0000000000011172

M3 - Article

C2 - 29952966

AN - SCOPUS:85049391861

VL - 97

JO - Medicine; analytical reviews of general medicine, neurology, psychiatry, dermatology, and pediatries

JF - Medicine; analytical reviews of general medicine, neurology, psychiatry, dermatology, and pediatries

SN - 0025-7974

IS - 26

M1 - e11172

ER -