Ability of FDG PET and CT radiomics features to differentiate between primary and metastatic lung lesions

Margarita Kirienko, Luca Cozzi, Alexia Rossi, Emanuele Voulaz, Lidija Antunovic, Antonella Fogliata, Arturo Chiti, Martina Sollini

Research output: Contribution to journalArticle

Abstract

Purpose: To evaluate the ability of CT and PET radiomics features to classify lung lesions as primary or metastatic, and secondly to differentiate histological subtypes of primary lung cancers. Methods: A cohort of 534 patients with lung lesions were retrospectively studied. Radiomics texture features were extracted using the LIFEx package from semiautomatically segmented PET and CT images. Histology data were recorded in all patients. The patient cohort was divided into a training and a validation group and linear discriminant analysis (LDA) was performed to classify the lesions using both direct and backward stepwise methods. The robustness of the procedure was tested by repeating the entire process 100 times with different assignments to the training and validation groups. Scoring metrics included analysis of the receiver operating characteristic curves in terms of area under the curve (AUC), sensitivity, specificity and accuracy. Results: Radiomics features extracted from CT and PET datasets were able to differentiate primary tumours from metastases in both the training and the validation group (AUCs 0.79 ± 0.03 and 0.70 ± 0.04, respectively, from the CT dataset; AUCs 0.92 ± 0.01 and 0.91 ± 0.03, respectively, from the PET dataset). The AUC cut-off thresholds identified by LDA using direct and backward elimination strategies were −0.79 ± 0.06 and −0.81 ± 0.08, respectively (CT dataset) and −0.69 ± 0.05 and −0.68 ± 0.04, respectively (PET dataset). For differentiation between primary subgroups based on CT features, the AUCs in the training and validation groups were 0.81 ± 0.02 and 0.69 ± 0.04 for adenocarcinoma (Adc) vs. squamous cell carcinoma (Sqc) or “Other”, 0.85 ± 0.02 and 0.70 ± 0.05 for Sqc vs. Adc or Other, and 0.77 ± 0.03 and 0.57 ± 0.05 for Other vs. Adc or Sqc. The same analyses for the PET data revealed AUCs of 0.90 ± 0.10 and 0.80 ± 0.04, 0.80 ± 0.02 and 0.61 ± 0.06, and 0.97 ± 0.01 and 0.88 ± 0.04, respectively. Conclusion: PET radiomics features were able to differentiate between primary and metastatic lung lesions and showed the potential to identify primary lung cancer subtypes.

Original languageEnglish
Pages (from-to)1649-1660
Number of pages12
JournalEuropean Journal of Nuclear Medicine and Molecular Imaging
Volume45
Issue number10
DOIs
Publication statusPublished - Sep 1 2018

Fingerprint

Area Under Curve
Lung
Squamous Cell Carcinoma
Adenocarcinoma
Discriminant Analysis
Lung Neoplasms
ROC Curve
Histology
Datasets
Neoplasm Metastasis
Sensitivity and Specificity
Neoplasms
Positron Emission Tomography Computed Tomography

Keywords

  • CT
  • Lung adenocarcinoma, squamous cell carcinoma
  • Lung metastases
  • PET/CT
  • Radiomics
  • Solitary lung nodule
  • Texture analysis, lung cancer

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

@article{f5396da6107d46c39afe02813b111173,
title = "Ability of FDG PET and CT radiomics features to differentiate between primary and metastatic lung lesions",
abstract = "Purpose: To evaluate the ability of CT and PET radiomics features to classify lung lesions as primary or metastatic, and secondly to differentiate histological subtypes of primary lung cancers. Methods: A cohort of 534 patients with lung lesions were retrospectively studied. Radiomics texture features were extracted using the LIFEx package from semiautomatically segmented PET and CT images. Histology data were recorded in all patients. The patient cohort was divided into a training and a validation group and linear discriminant analysis (LDA) was performed to classify the lesions using both direct and backward stepwise methods. The robustness of the procedure was tested by repeating the entire process 100 times with different assignments to the training and validation groups. Scoring metrics included analysis of the receiver operating characteristic curves in terms of area under the curve (AUC), sensitivity, specificity and accuracy. Results: Radiomics features extracted from CT and PET datasets were able to differentiate primary tumours from metastases in both the training and the validation group (AUCs 0.79 ± 0.03 and 0.70 ± 0.04, respectively, from the CT dataset; AUCs 0.92 ± 0.01 and 0.91 ± 0.03, respectively, from the PET dataset). The AUC cut-off thresholds identified by LDA using direct and backward elimination strategies were −0.79 ± 0.06 and −0.81 ± 0.08, respectively (CT dataset) and −0.69 ± 0.05 and −0.68 ± 0.04, respectively (PET dataset). For differentiation between primary subgroups based on CT features, the AUCs in the training and validation groups were 0.81 ± 0.02 and 0.69 ± 0.04 for adenocarcinoma (Adc) vs. squamous cell carcinoma (Sqc) or “Other”, 0.85 ± 0.02 and 0.70 ± 0.05 for Sqc vs. Adc or Other, and 0.77 ± 0.03 and 0.57 ± 0.05 for Other vs. Adc or Sqc. The same analyses for the PET data revealed AUCs of 0.90 ± 0.10 and 0.80 ± 0.04, 0.80 ± 0.02 and 0.61 ± 0.06, and 0.97 ± 0.01 and 0.88 ± 0.04, respectively. Conclusion: PET radiomics features were able to differentiate between primary and metastatic lung lesions and showed the potential to identify primary lung cancer subtypes.",
keywords = "CT, Lung adenocarcinoma, squamous cell carcinoma, Lung metastases, PET/CT, Radiomics, Solitary lung nodule, Texture analysis, lung cancer",
author = "Margarita Kirienko and Luca Cozzi and Alexia Rossi and Emanuele Voulaz and Lidija Antunovic and Antonella Fogliata and Arturo Chiti and Martina Sollini",
year = "2018",
month = "9",
day = "1",
doi = "10.1007/s00259-018-3987-2",
language = "English",
volume = "45",
pages = "1649--1660",
journal = "European Journal of Pediatrics",
issn = "0340-6199",
publisher = "Springer Berlin Heidelberg",
number = "10",

}

TY - JOUR

T1 - Ability of FDG PET and CT radiomics features to differentiate between primary and metastatic lung lesions

AU - Kirienko, Margarita

AU - Cozzi, Luca

AU - Rossi, Alexia

AU - Voulaz, Emanuele

AU - Antunovic, Lidija

AU - Fogliata, Antonella

AU - Chiti, Arturo

AU - Sollini, Martina

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Purpose: To evaluate the ability of CT and PET radiomics features to classify lung lesions as primary or metastatic, and secondly to differentiate histological subtypes of primary lung cancers. Methods: A cohort of 534 patients with lung lesions were retrospectively studied. Radiomics texture features were extracted using the LIFEx package from semiautomatically segmented PET and CT images. Histology data were recorded in all patients. The patient cohort was divided into a training and a validation group and linear discriminant analysis (LDA) was performed to classify the lesions using both direct and backward stepwise methods. The robustness of the procedure was tested by repeating the entire process 100 times with different assignments to the training and validation groups. Scoring metrics included analysis of the receiver operating characteristic curves in terms of area under the curve (AUC), sensitivity, specificity and accuracy. Results: Radiomics features extracted from CT and PET datasets were able to differentiate primary tumours from metastases in both the training and the validation group (AUCs 0.79 ± 0.03 and 0.70 ± 0.04, respectively, from the CT dataset; AUCs 0.92 ± 0.01 and 0.91 ± 0.03, respectively, from the PET dataset). The AUC cut-off thresholds identified by LDA using direct and backward elimination strategies were −0.79 ± 0.06 and −0.81 ± 0.08, respectively (CT dataset) and −0.69 ± 0.05 and −0.68 ± 0.04, respectively (PET dataset). For differentiation between primary subgroups based on CT features, the AUCs in the training and validation groups were 0.81 ± 0.02 and 0.69 ± 0.04 for adenocarcinoma (Adc) vs. squamous cell carcinoma (Sqc) or “Other”, 0.85 ± 0.02 and 0.70 ± 0.05 for Sqc vs. Adc or Other, and 0.77 ± 0.03 and 0.57 ± 0.05 for Other vs. Adc or Sqc. The same analyses for the PET data revealed AUCs of 0.90 ± 0.10 and 0.80 ± 0.04, 0.80 ± 0.02 and 0.61 ± 0.06, and 0.97 ± 0.01 and 0.88 ± 0.04, respectively. Conclusion: PET radiomics features were able to differentiate between primary and metastatic lung lesions and showed the potential to identify primary lung cancer subtypes.

AB - Purpose: To evaluate the ability of CT and PET radiomics features to classify lung lesions as primary or metastatic, and secondly to differentiate histological subtypes of primary lung cancers. Methods: A cohort of 534 patients with lung lesions were retrospectively studied. Radiomics texture features were extracted using the LIFEx package from semiautomatically segmented PET and CT images. Histology data were recorded in all patients. The patient cohort was divided into a training and a validation group and linear discriminant analysis (LDA) was performed to classify the lesions using both direct and backward stepwise methods. The robustness of the procedure was tested by repeating the entire process 100 times with different assignments to the training and validation groups. Scoring metrics included analysis of the receiver operating characteristic curves in terms of area under the curve (AUC), sensitivity, specificity and accuracy. Results: Radiomics features extracted from CT and PET datasets were able to differentiate primary tumours from metastases in both the training and the validation group (AUCs 0.79 ± 0.03 and 0.70 ± 0.04, respectively, from the CT dataset; AUCs 0.92 ± 0.01 and 0.91 ± 0.03, respectively, from the PET dataset). The AUC cut-off thresholds identified by LDA using direct and backward elimination strategies were −0.79 ± 0.06 and −0.81 ± 0.08, respectively (CT dataset) and −0.69 ± 0.05 and −0.68 ± 0.04, respectively (PET dataset). For differentiation between primary subgroups based on CT features, the AUCs in the training and validation groups were 0.81 ± 0.02 and 0.69 ± 0.04 for adenocarcinoma (Adc) vs. squamous cell carcinoma (Sqc) or “Other”, 0.85 ± 0.02 and 0.70 ± 0.05 for Sqc vs. Adc or Other, and 0.77 ± 0.03 and 0.57 ± 0.05 for Other vs. Adc or Sqc. The same analyses for the PET data revealed AUCs of 0.90 ± 0.10 and 0.80 ± 0.04, 0.80 ± 0.02 and 0.61 ± 0.06, and 0.97 ± 0.01 and 0.88 ± 0.04, respectively. Conclusion: PET radiomics features were able to differentiate between primary and metastatic lung lesions and showed the potential to identify primary lung cancer subtypes.

KW - CT

KW - Lung adenocarcinoma, squamous cell carcinoma

KW - Lung metastases

KW - PET/CT

KW - Radiomics

KW - Solitary lung nodule

KW - Texture analysis, lung cancer

UR - http://www.scopus.com/inward/record.url?scp=85045065074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045065074&partnerID=8YFLogxK

U2 - 10.1007/s00259-018-3987-2

DO - 10.1007/s00259-018-3987-2

M3 - Article

C2 - 29623375

AN - SCOPUS:85045065074

VL - 45

SP - 1649

EP - 1660

JO - European Journal of Pediatrics

JF - European Journal of Pediatrics

SN - 0340-6199

IS - 10

ER -