Radiomics versus physician assessment for the early prediction of local cancer recurrence after stereotactic radiotherapy for lung cancer

Sarah A. Mattonen, Carol Johnson, David A. Palma, George Rodrigues, Alexander V. Louie, Suresh Senan, Timothy P.C. Yeung, Aaron D. Ward

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Stereotactic ablative radiotherapy (SABR) has recently become a standard treatment option for patients with early-stage lung cancer, which achieves local control rates similar to surgery. Local recurrence following SABR typically presents after one year post-treatment. However, benign radiological changes mimicking local recurrence can appear on CT imaging following SABR, complicating the assessment of response. We hypothesize that subtle changes on early post- SABR CT images are important in predicting the eventual incidence of local recurrence and would be extremely valuable to support timely salvage interventions. The objective of this study was to extract radiomic image features on post-SABR follow-up images for 45 patients (15 with local recurrence and 30 without) to aid in the early prediction of local recurrence. Three blinded thoracic radiation oncologists were also asked to score follow-up images as benign injury or local recurrence. A radiomic signature consisting of five image features demonstrated a classification error of 24%, false positive rate (FPR) of 24%, false negative rate (FNR) of 23%, and area under the receiver operating characteristic curve (AUC) of 0.85 at 2-5 months post-SABR. At the same time point, three physicians assessed the majority of images as benign injury for overall errors of 34-37%, FPRs of 0-4%, and FNRs of 100%. These results suggest that radiomics can detect early changes associated with local recurrence which are not typically considered by physicians. We aim to develop a decision support system which could potentially allow for early salvage therapy of patients with local recurrence following SABR.

Original languageEnglish
Title of host publicationMedical Imaging 2016
Subtitle of host publicationComputer-Aided Diagnosis
PublisherSPIE
Volume9785
ISBN (Electronic)9781510600201
DOIs
Publication statusPublished - 1 Jan 2016
EventMedical Imaging 2016: Computer-Aided Diagnosis - San Diego, United States
Duration: 28 Feb 20162 Mar 2016

Conference

ConferenceMedical Imaging 2016: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego
Period28/02/201602/03/2016

Cite this

Mattonen, S. A., Johnson, C., Palma, D. A., Rodrigues, G., Louie, A. V., Senan, S., ... Ward, A. D. (2016). Radiomics versus physician assessment for the early prediction of local cancer recurrence after stereotactic radiotherapy for lung cancer. In Medical Imaging 2016: Computer-Aided Diagnosis (Vol. 9785). [97851F] SPIE. https://doi.org/10.1117/12.2217236
Mattonen, Sarah A. ; Johnson, Carol ; Palma, David A. ; Rodrigues, George ; Louie, Alexander V. ; Senan, Suresh ; Yeung, Timothy P.C. ; Ward, Aaron D. / Radiomics versus physician assessment for the early prediction of local cancer recurrence after stereotactic radiotherapy for lung cancer. Medical Imaging 2016: Computer-Aided Diagnosis. Vol. 9785 SPIE, 2016.
@inproceedings{37bb3fec3dda43319073539f3f7475a1,
title = "Radiomics versus physician assessment for the early prediction of local cancer recurrence after stereotactic radiotherapy for lung cancer",
abstract = "Stereotactic ablative radiotherapy (SABR) has recently become a standard treatment option for patients with early-stage lung cancer, which achieves local control rates similar to surgery. Local recurrence following SABR typically presents after one year post-treatment. However, benign radiological changes mimicking local recurrence can appear on CT imaging following SABR, complicating the assessment of response. We hypothesize that subtle changes on early post- SABR CT images are important in predicting the eventual incidence of local recurrence and would be extremely valuable to support timely salvage interventions. The objective of this study was to extract radiomic image features on post-SABR follow-up images for 45 patients (15 with local recurrence and 30 without) to aid in the early prediction of local recurrence. Three blinded thoracic radiation oncologists were also asked to score follow-up images as benign injury or local recurrence. A radiomic signature consisting of five image features demonstrated a classification error of 24{\%}, false positive rate (FPR) of 24{\%}, false negative rate (FNR) of 23{\%}, and area under the receiver operating characteristic curve (AUC) of 0.85 at 2-5 months post-SABR. At the same time point, three physicians assessed the majority of images as benign injury for overall errors of 34-37{\%}, FPRs of 0-4{\%}, and FNRs of 100{\%}. These results suggest that radiomics can detect early changes associated with local recurrence which are not typically considered by physicians. We aim to develop a decision support system which could potentially allow for early salvage therapy of patients with local recurrence following SABR.",
keywords = "Cancer therapy response assessment, Classification, Lung cancer, Observer studies, Quantitative imaging biomarkers, Radiation-induced lung injury, Radiomics, Stereotactic radiotherapy",
author = "Mattonen, {Sarah A.} and Carol Johnson and Palma, {David A.} and George Rodrigues and Louie, {Alexander V.} and Suresh Senan and Yeung, {Timothy P.C.} and Ward, {Aaron D.}",
year = "2016",
month = "1",
day = "1",
doi = "10.1117/12.2217236",
language = "English",
volume = "9785",
booktitle = "Medical Imaging 2016",
publisher = "SPIE",
address = "United States",

}

Mattonen, SA, Johnson, C, Palma, DA, Rodrigues, G, Louie, AV, Senan, S, Yeung, TPC & Ward, AD 2016, Radiomics versus physician assessment for the early prediction of local cancer recurrence after stereotactic radiotherapy for lung cancer. in Medical Imaging 2016: Computer-Aided Diagnosis. vol. 9785, 97851F, SPIE, Medical Imaging 2016: Computer-Aided Diagnosis, San Diego, United States, 28/02/2016. https://doi.org/10.1117/12.2217236

Radiomics versus physician assessment for the early prediction of local cancer recurrence after stereotactic radiotherapy for lung cancer. / Mattonen, Sarah A.; Johnson, Carol; Palma, David A.; Rodrigues, George; Louie, Alexander V.; Senan, Suresh; Yeung, Timothy P.C.; Ward, Aaron D.

Medical Imaging 2016: Computer-Aided Diagnosis. Vol. 9785 SPIE, 2016. 97851F.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Radiomics versus physician assessment for the early prediction of local cancer recurrence after stereotactic radiotherapy for lung cancer

AU - Mattonen, Sarah A.

AU - Johnson, Carol

AU - Palma, David A.

AU - Rodrigues, George

AU - Louie, Alexander V.

AU - Senan, Suresh

AU - Yeung, Timothy P.C.

AU - Ward, Aaron D.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Stereotactic ablative radiotherapy (SABR) has recently become a standard treatment option for patients with early-stage lung cancer, which achieves local control rates similar to surgery. Local recurrence following SABR typically presents after one year post-treatment. However, benign radiological changes mimicking local recurrence can appear on CT imaging following SABR, complicating the assessment of response. We hypothesize that subtle changes on early post- SABR CT images are important in predicting the eventual incidence of local recurrence and would be extremely valuable to support timely salvage interventions. The objective of this study was to extract radiomic image features on post-SABR follow-up images for 45 patients (15 with local recurrence and 30 without) to aid in the early prediction of local recurrence. Three blinded thoracic radiation oncologists were also asked to score follow-up images as benign injury or local recurrence. A radiomic signature consisting of five image features demonstrated a classification error of 24%, false positive rate (FPR) of 24%, false negative rate (FNR) of 23%, and area under the receiver operating characteristic curve (AUC) of 0.85 at 2-5 months post-SABR. At the same time point, three physicians assessed the majority of images as benign injury for overall errors of 34-37%, FPRs of 0-4%, and FNRs of 100%. These results suggest that radiomics can detect early changes associated with local recurrence which are not typically considered by physicians. We aim to develop a decision support system which could potentially allow for early salvage therapy of patients with local recurrence following SABR.

AB - Stereotactic ablative radiotherapy (SABR) has recently become a standard treatment option for patients with early-stage lung cancer, which achieves local control rates similar to surgery. Local recurrence following SABR typically presents after one year post-treatment. However, benign radiological changes mimicking local recurrence can appear on CT imaging following SABR, complicating the assessment of response. We hypothesize that subtle changes on early post- SABR CT images are important in predicting the eventual incidence of local recurrence and would be extremely valuable to support timely salvage interventions. The objective of this study was to extract radiomic image features on post-SABR follow-up images for 45 patients (15 with local recurrence and 30 without) to aid in the early prediction of local recurrence. Three blinded thoracic radiation oncologists were also asked to score follow-up images as benign injury or local recurrence. A radiomic signature consisting of five image features demonstrated a classification error of 24%, false positive rate (FPR) of 24%, false negative rate (FNR) of 23%, and area under the receiver operating characteristic curve (AUC) of 0.85 at 2-5 months post-SABR. At the same time point, three physicians assessed the majority of images as benign injury for overall errors of 34-37%, FPRs of 0-4%, and FNRs of 100%. These results suggest that radiomics can detect early changes associated with local recurrence which are not typically considered by physicians. We aim to develop a decision support system which could potentially allow for early salvage therapy of patients with local recurrence following SABR.

KW - Cancer therapy response assessment

KW - Classification

KW - Lung cancer

KW - Observer studies

KW - Quantitative imaging biomarkers

KW - Radiation-induced lung injury

KW - Radiomics

KW - Stereotactic radiotherapy

UR - http://www.scopus.com/inward/record.url?scp=84988864920&partnerID=8YFLogxK

U2 - 10.1117/12.2217236

DO - 10.1117/12.2217236

M3 - Conference contribution

VL - 9785

BT - Medical Imaging 2016

PB - SPIE

ER -

Mattonen SA, Johnson C, Palma DA, Rodrigues G, Louie AV, Senan S et al. Radiomics versus physician assessment for the early prediction of local cancer recurrence after stereotactic radiotherapy for lung cancer. In Medical Imaging 2016: Computer-Aided Diagnosis. Vol. 9785. SPIE. 2016. 97851F https://doi.org/10.1117/12.2217236