The use of texture-based radiomics CT analysis to predict outcomes in early-stage non-small cell lung cancer treated with stereotactic ablative radiotherapy

Pierre Starkov, Todd Anthony Aguilera, Daniel I. Golden, David B. Shultz, Nicholas Trakul, Peter G. Maxim, Quynh Thu Le, Billy W. Loo, Maximillan Diehn, Adrien Depeursinge, Daniel L. Rubin

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

objective: Stereotactic ablative radiotherapy (SABR) is being increasingly used as a non-invasive treatment for early-stage non-small cell lung cancer (NSCLC). A non-invasive method to estimate treatment outcomes in these patients would be valuable, especially since access to tissue specimens is often difficult in these cases. Methods: We developed a method to predict survival following SABR in NSCLC patients using analysis of quantitative image features on pre-treatment CT images. We developed a Cox Lasso model based on two-dimensional Riesz wavelet quantitative texture features on CT scans with the goal of separating patients based on survival. results: The median log-rank p-value for 1000 cross-validations was 0.030. Our model was able to separate patients based upon predicted survival. When we added tumor size into the model, the p-value lost its significance, demonstrating that tumor size is not a key feature in the model but rather decreases significance likely due to the relatively small number of events in the dataset. Furthermore, running the model using Riesz features extracted either from the solid component of the tumor or from the ground glass opacity (GGO) component of the tumor maintained statistical significance. However, the p-value improved when combining features from the solid and the GGO components, demonstrating that there are important data that can be extracted from the entire tumor. Conclusions: The model predicting patient survival following SABR in NSCLC may be useful in future studies by enabling prediction of survival-based outcomes using radiomics features in CT images. advances in knowledge: Quantitative image features from NSCLC nodules on CT images have been found to significantly separate patient populations based on overall survival (p = 0.04). In the long term, a non-invasive method to estimate treatment outcomes in patients undergoing SABR would be valuable, especially since access to tissue specimens is often difficult in these cases.

Original languageEnglish (US)
Article number20180228
JournalBritish Journal of Radiology
Volume92
Issue number1094
DOIs
StatePublished - Jan 1 2019

Fingerprint

Non-Small Cell Lung Carcinoma
Radiotherapy
Survival
Neoplasms
Glass
Proportional Hazards Models
Therapeutics
Population

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

The use of texture-based radiomics CT analysis to predict outcomes in early-stage non-small cell lung cancer treated with stereotactic ablative radiotherapy. / Starkov, Pierre; Aguilera, Todd Anthony; Golden, Daniel I.; Shultz, David B.; Trakul, Nicholas; Maxim, Peter G.; Le, Quynh Thu; Loo, Billy W.; Diehn, Maximillan; Depeursinge, Adrien; Rubin, Daniel L.

In: British Journal of Radiology, Vol. 92, No. 1094, 20180228, 01.01.2019.

Research output: Contribution to journalArticle

Starkov, Pierre ; Aguilera, Todd Anthony ; Golden, Daniel I. ; Shultz, David B. ; Trakul, Nicholas ; Maxim, Peter G. ; Le, Quynh Thu ; Loo, Billy W. ; Diehn, Maximillan ; Depeursinge, Adrien ; Rubin, Daniel L. / The use of texture-based radiomics CT analysis to predict outcomes in early-stage non-small cell lung cancer treated with stereotactic ablative radiotherapy. In: British Journal of Radiology. 2019 ; Vol. 92, No. 1094.
@article{5541745eb03141d18c1a2a480c9eebe4,
title = "The use of texture-based radiomics CT analysis to predict outcomes in early-stage non-small cell lung cancer treated with stereotactic ablative radiotherapy",
abstract = "objective: Stereotactic ablative radiotherapy (SABR) is being increasingly used as a non-invasive treatment for early-stage non-small cell lung cancer (NSCLC). A non-invasive method to estimate treatment outcomes in these patients would be valuable, especially since access to tissue specimens is often difficult in these cases. Methods: We developed a method to predict survival following SABR in NSCLC patients using analysis of quantitative image features on pre-treatment CT images. We developed a Cox Lasso model based on two-dimensional Riesz wavelet quantitative texture features on CT scans with the goal of separating patients based on survival. results: The median log-rank p-value for 1000 cross-validations was 0.030. Our model was able to separate patients based upon predicted survival. When we added tumor size into the model, the p-value lost its significance, demonstrating that tumor size is not a key feature in the model but rather decreases significance likely due to the relatively small number of events in the dataset. Furthermore, running the model using Riesz features extracted either from the solid component of the tumor or from the ground glass opacity (GGO) component of the tumor maintained statistical significance. However, the p-value improved when combining features from the solid and the GGO components, demonstrating that there are important data that can be extracted from the entire tumor. Conclusions: The model predicting patient survival following SABR in NSCLC may be useful in future studies by enabling prediction of survival-based outcomes using radiomics features in CT images. advances in knowledge: Quantitative image features from NSCLC nodules on CT images have been found to significantly separate patient populations based on overall survival (p = 0.04). In the long term, a non-invasive method to estimate treatment outcomes in patients undergoing SABR would be valuable, especially since access to tissue specimens is often difficult in these cases.",
author = "Pierre Starkov and Aguilera, {Todd Anthony} and Golden, {Daniel I.} and Shultz, {David B.} and Nicholas Trakul and Maxim, {Peter G.} and Le, {Quynh Thu} and Loo, {Billy W.} and Maximillan Diehn and Adrien Depeursinge and Rubin, {Daniel L.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1259/bjr.20180228",
language = "English (US)",
volume = "92",
journal = "British Journal of Radiology",
issn = "0007-1285",
publisher = "British Institute of Radiology",
number = "1094",

}

TY - JOUR

T1 - The use of texture-based radiomics CT analysis to predict outcomes in early-stage non-small cell lung cancer treated with stereotactic ablative radiotherapy

AU - Starkov, Pierre

AU - Aguilera, Todd Anthony

AU - Golden, Daniel I.

AU - Shultz, David B.

AU - Trakul, Nicholas

AU - Maxim, Peter G.

AU - Le, Quynh Thu

AU - Loo, Billy W.

AU - Diehn, Maximillan

AU - Depeursinge, Adrien

AU - Rubin, Daniel L.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - objective: Stereotactic ablative radiotherapy (SABR) is being increasingly used as a non-invasive treatment for early-stage non-small cell lung cancer (NSCLC). A non-invasive method to estimate treatment outcomes in these patients would be valuable, especially since access to tissue specimens is often difficult in these cases. Methods: We developed a method to predict survival following SABR in NSCLC patients using analysis of quantitative image features on pre-treatment CT images. We developed a Cox Lasso model based on two-dimensional Riesz wavelet quantitative texture features on CT scans with the goal of separating patients based on survival. results: The median log-rank p-value for 1000 cross-validations was 0.030. Our model was able to separate patients based upon predicted survival. When we added tumor size into the model, the p-value lost its significance, demonstrating that tumor size is not a key feature in the model but rather decreases significance likely due to the relatively small number of events in the dataset. Furthermore, running the model using Riesz features extracted either from the solid component of the tumor or from the ground glass opacity (GGO) component of the tumor maintained statistical significance. However, the p-value improved when combining features from the solid and the GGO components, demonstrating that there are important data that can be extracted from the entire tumor. Conclusions: The model predicting patient survival following SABR in NSCLC may be useful in future studies by enabling prediction of survival-based outcomes using radiomics features in CT images. advances in knowledge: Quantitative image features from NSCLC nodules on CT images have been found to significantly separate patient populations based on overall survival (p = 0.04). In the long term, a non-invasive method to estimate treatment outcomes in patients undergoing SABR would be valuable, especially since access to tissue specimens is often difficult in these cases.

AB - objective: Stereotactic ablative radiotherapy (SABR) is being increasingly used as a non-invasive treatment for early-stage non-small cell lung cancer (NSCLC). A non-invasive method to estimate treatment outcomes in these patients would be valuable, especially since access to tissue specimens is often difficult in these cases. Methods: We developed a method to predict survival following SABR in NSCLC patients using analysis of quantitative image features on pre-treatment CT images. We developed a Cox Lasso model based on two-dimensional Riesz wavelet quantitative texture features on CT scans with the goal of separating patients based on survival. results: The median log-rank p-value for 1000 cross-validations was 0.030. Our model was able to separate patients based upon predicted survival. When we added tumor size into the model, the p-value lost its significance, demonstrating that tumor size is not a key feature in the model but rather decreases significance likely due to the relatively small number of events in the dataset. Furthermore, running the model using Riesz features extracted either from the solid component of the tumor or from the ground glass opacity (GGO) component of the tumor maintained statistical significance. However, the p-value improved when combining features from the solid and the GGO components, demonstrating that there are important data that can be extracted from the entire tumor. Conclusions: The model predicting patient survival following SABR in NSCLC may be useful in future studies by enabling prediction of survival-based outcomes using radiomics features in CT images. advances in knowledge: Quantitative image features from NSCLC nodules on CT images have been found to significantly separate patient populations based on overall survival (p = 0.04). In the long term, a non-invasive method to estimate treatment outcomes in patients undergoing SABR would be valuable, especially since access to tissue specimens is often difficult in these cases.

UR - http://www.scopus.com/inward/record.url?scp=85060542219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060542219&partnerID=8YFLogxK

U2 - 10.1259/bjr.20180228

DO - 10.1259/bjr.20180228

M3 - Article

VL - 92

JO - British Journal of Radiology

JF - British Journal of Radiology

SN - 0007-1285

IS - 1094

M1 - 20180228

ER -