Convolutional Neural Networks Promising in Lung Cancer T-Parameter Assessment on Baseline FDG-PET/CT

Margarita Kirienko, Martina Sollini, Giorgia Silvestri, Serena Mognetti, Emanuele Voulaz, Lidija Antunovic, Alexia Rossi, Luca Antiga, Arturo Chiti

Research output: Contribution to journalArticle

Abstract

Aim: To develop an algorithm, based on convolutional neural network (CNN), for the classification of lung cancer lesions as T1-T2 or T3-T4 on staging fluorodeoxyglucose positron emission tomography (FDG-PET)/CT images.

Methods: We retrospectively selected a cohort of 472 patients (divided in the training, validation, and test sets) submitted to staging FDG-PET/CT within 60 days before biopsy or surgery. TNM system seventh edition was used as reference. Postprocessing was performed to generate an adequate dataset. The input of CNNs was a bounding box on both PET and CT images, cropped around the lesion centre. The results were classified as Correct (concordance between reference and prediction) and Incorrect (discordance between reference and prediction). Accuracy (Correct/[Correct + Incorrect]), recall (Correctly predicted T3-T4/[all T3-T4]), and specificity (Correctly predicted T1-T2/[all T1-T2]), as commonly defined in deep learning models, were used to evaluate CNN performance. The area under the curve (AUC) was calculated for the final model.

Results: The algorithm, composed of two networks (a "feature extractor" and a "classifier"), developed and tested achieved an accuracy, recall, specificity, and AUC of 87%, 69%, 69%, and 0.83; 86%, 77%, 70%, and 0.73; and 90%, 47%, 67%, and 0.68 in the training, validation, and test sets, respectively.

Conclusion: We obtained proof of concept that CNNs can be used as a tool to assist in the staging of patients affected by lung cancer.

Original languageEnglish
Pages (from-to)1382309
JournalContrast Media and Molecular Imaging
Volume2018
DOIs
Publication statusPublished - 2018

Fingerprint

Positron-Emission Tomography
Area Under Curve
Lung Neoplasms
Learning
Biopsy
Datasets

Cite this

Convolutional Neural Networks Promising in Lung Cancer T-Parameter Assessment on Baseline FDG-PET/CT. / Kirienko, Margarita; Sollini, Martina; Silvestri, Giorgia; Mognetti, Serena; Voulaz, Emanuele; Antunovic, Lidija; Rossi, Alexia; Antiga, Luca; Chiti, Arturo.

In: Contrast Media and Molecular Imaging, Vol. 2018, 2018, p. 1382309.

Research output: Contribution to journalArticle

@article{7c53bed39af3489ab0d3a2a6ba0a76b6,
title = "Convolutional Neural Networks Promising in Lung Cancer T-Parameter Assessment on Baseline FDG-PET/CT",
abstract = "Aim: To develop an algorithm, based on convolutional neural network (CNN), for the classification of lung cancer lesions as T1-T2 or T3-T4 on staging fluorodeoxyglucose positron emission tomography (FDG-PET)/CT images.Methods: We retrospectively selected a cohort of 472 patients (divided in the training, validation, and test sets) submitted to staging FDG-PET/CT within 60 days before biopsy or surgery. TNM system seventh edition was used as reference. Postprocessing was performed to generate an adequate dataset. The input of CNNs was a bounding box on both PET and CT images, cropped around the lesion centre. The results were classified as Correct (concordance between reference and prediction) and Incorrect (discordance between reference and prediction). Accuracy (Correct/[Correct + Incorrect]), recall (Correctly predicted T3-T4/[all T3-T4]), and specificity (Correctly predicted T1-T2/[all T1-T2]), as commonly defined in deep learning models, were used to evaluate CNN performance. The area under the curve (AUC) was calculated for the final model.Results: The algorithm, composed of two networks (a {"}feature extractor{"} and a {"}classifier{"}), developed and tested achieved an accuracy, recall, specificity, and AUC of 87{\%}, 69{\%}, 69{\%}, and 0.83; 86{\%}, 77{\%}, 70{\%}, and 0.73; and 90{\%}, 47{\%}, 67{\%}, and 0.68 in the training, validation, and test sets, respectively.Conclusion: We obtained proof of concept that CNNs can be used as a tool to assist in the staging of patients affected by lung cancer.",
author = "Margarita Kirienko and Martina Sollini and Giorgia Silvestri and Serena Mognetti and Emanuele Voulaz and Lidija Antunovic and Alexia Rossi and Luca Antiga and Arturo Chiti",
year = "2018",
doi = "10.1155/2018/1382309",
language = "English",
volume = "2018",
pages = "1382309",
journal = "Contrast Media and Molecular Imaging",
issn = "1555-4309",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Convolutional Neural Networks Promising in Lung Cancer T-Parameter Assessment on Baseline FDG-PET/CT

AU - Kirienko, Margarita

AU - Sollini, Martina

AU - Silvestri, Giorgia

AU - Mognetti, Serena

AU - Voulaz, Emanuele

AU - Antunovic, Lidija

AU - Rossi, Alexia

AU - Antiga, Luca

AU - Chiti, Arturo

PY - 2018

Y1 - 2018

N2 - Aim: To develop an algorithm, based on convolutional neural network (CNN), for the classification of lung cancer lesions as T1-T2 or T3-T4 on staging fluorodeoxyglucose positron emission tomography (FDG-PET)/CT images.Methods: We retrospectively selected a cohort of 472 patients (divided in the training, validation, and test sets) submitted to staging FDG-PET/CT within 60 days before biopsy or surgery. TNM system seventh edition was used as reference. Postprocessing was performed to generate an adequate dataset. The input of CNNs was a bounding box on both PET and CT images, cropped around the lesion centre. The results were classified as Correct (concordance between reference and prediction) and Incorrect (discordance between reference and prediction). Accuracy (Correct/[Correct + Incorrect]), recall (Correctly predicted T3-T4/[all T3-T4]), and specificity (Correctly predicted T1-T2/[all T1-T2]), as commonly defined in deep learning models, were used to evaluate CNN performance. The area under the curve (AUC) was calculated for the final model.Results: The algorithm, composed of two networks (a "feature extractor" and a "classifier"), developed and tested achieved an accuracy, recall, specificity, and AUC of 87%, 69%, 69%, and 0.83; 86%, 77%, 70%, and 0.73; and 90%, 47%, 67%, and 0.68 in the training, validation, and test sets, respectively.Conclusion: We obtained proof of concept that CNNs can be used as a tool to assist in the staging of patients affected by lung cancer.

AB - Aim: To develop an algorithm, based on convolutional neural network (CNN), for the classification of lung cancer lesions as T1-T2 or T3-T4 on staging fluorodeoxyglucose positron emission tomography (FDG-PET)/CT images.Methods: We retrospectively selected a cohort of 472 patients (divided in the training, validation, and test sets) submitted to staging FDG-PET/CT within 60 days before biopsy or surgery. TNM system seventh edition was used as reference. Postprocessing was performed to generate an adequate dataset. The input of CNNs was a bounding box on both PET and CT images, cropped around the lesion centre. The results were classified as Correct (concordance between reference and prediction) and Incorrect (discordance between reference and prediction). Accuracy (Correct/[Correct + Incorrect]), recall (Correctly predicted T3-T4/[all T3-T4]), and specificity (Correctly predicted T1-T2/[all T1-T2]), as commonly defined in deep learning models, were used to evaluate CNN performance. The area under the curve (AUC) was calculated for the final model.Results: The algorithm, composed of two networks (a "feature extractor" and a "classifier"), developed and tested achieved an accuracy, recall, specificity, and AUC of 87%, 69%, 69%, and 0.83; 86%, 77%, 70%, and 0.73; and 90%, 47%, 67%, and 0.68 in the training, validation, and test sets, respectively.Conclusion: We obtained proof of concept that CNNs can be used as a tool to assist in the staging of patients affected by lung cancer.

U2 - 10.1155/2018/1382309

DO - 10.1155/2018/1382309

M3 - Article

C2 - 30510492

VL - 2018

SP - 1382309

JO - Contrast Media and Molecular Imaging

JF - Contrast Media and Molecular Imaging

SN - 1555-4309

ER -