Radiomics predicts clinical outcome in primary gastroesophageal junction adenocarcinoma treated by chemo/radiotherapy and surgery

Qifeng Wang, Shouhao Zhou, Laurence E. Court, Vivek Verma, Eugene J. Koay, Lifei Zhang, Wencheng Zhang, Chad Tang, Steven Lin, James D. Welsh, Mariela Blum, Sonia Betancourt, Dipen Maru, Wayne L. Hofstetter, Joe Y. Chang

Research output: Contribution to journalArticle

Abstract

Purpose: Radiomics has shown great promise to use quantifiable imaging characteristics to predict the behavior and prognosis of neoplasms. This is the first study to evaluate whether radiomic texture analysis can predict outcomes in gastroesophageal junction adenocarcinoma (GEJAC) treated with neoadjuvant chemoradiotherapy (CRT). Materials and Methods: Pretreatment contrast-enhanced CT images of 146 patients with stage II-III GEJAC were reviewed (2009-2011), and randomly split into training and validation groups at a 1:1 ratio stratified with baseline clinical characteristics. Whole-tumor texture was assessed using quantitative image features based on intensity, shape, and gray-level co-occurrence matrix. The relevant pretreatment texture features, in addition to the significant baseline clinical features to predict survival, were identified using multivariate Cox proportional hazard regression model with stepwise variable selection in the training sample and verified in the validation sample, to facilitate the proposal of a multi-point index for standard patient pre-treatment risk classification. Results: Of the factors identified in the training cohort independently associated with OS, only shape compactness (p = 0.04) and pathologic grade differentiation (PDG) (p = 0.02) were confirmed in the validation sample. Using both parameters, we created a 3-point risk classification index: low-risk (wellmoderate PDG and high compactness), medium-risk (poor PDG or low compactness), and high-risk (poor PDG and low compactness). The risk index showed a strong negative association with postoperative pathologic complete response (pCR) (p = 0.04). Median OS for the high-, medium-, and low-risk groups were 23, 51, and ≥ 72 months, respectively (p < 0.01). Similar results were seen with progression-free survival (respective 5-year rates of 15%, 30%, and 63%). Conclusion: Radiomic texture analysis can be used to stratify patients with GEJAC receiving trimodality therapy based on prognosis. The risk scoring system based on shape compactness and PDG shows a great potential for pre-treatment risk classification to guide surgical resection in locally advanced disease. Though in need of greater validation, these hypothesis-generating data could provide a unique platform of personalized oncologic care.

Original languageEnglish (US)
Pages (from-to)37-42
Number of pages6
JournalPhysics and Imaging in Radiation Oncology
Volume3
DOIs
StatePublished - Jul 1 2017

Fingerprint

Esophagogastric Junction
surgery
radiation therapy
Adenocarcinoma
Radiotherapy
void ratio
pretreatment
textures
education
prognosis
neoplasms
scoring
Chemoradiotherapy
Proportional Hazards Models
progressions
hazards
Disease-Free Survival
proposals
regression analysis
grade

All Science Journal Classification (ASJC) codes

  • Radiation
  • Radiology Nuclear Medicine and imaging

Cite this

Wang, Qifeng ; Zhou, Shouhao ; Court, Laurence E. ; Verma, Vivek ; Koay, Eugene J. ; Zhang, Lifei ; Zhang, Wencheng ; Tang, Chad ; Lin, Steven ; Welsh, James D. ; Blum, Mariela ; Betancourt, Sonia ; Maru, Dipen ; Hofstetter, Wayne L. ; Chang, Joe Y. / Radiomics predicts clinical outcome in primary gastroesophageal junction adenocarcinoma treated by chemo/radiotherapy and surgery. In: Physics and Imaging in Radiation Oncology. 2017 ; Vol. 3. pp. 37-42.
@article{f87a50d9917e46c19104151050e92af4,
title = "Radiomics predicts clinical outcome in primary gastroesophageal junction adenocarcinoma treated by chemo/radiotherapy and surgery",
abstract = "Purpose: Radiomics has shown great promise to use quantifiable imaging characteristics to predict the behavior and prognosis of neoplasms. This is the first study to evaluate whether radiomic texture analysis can predict outcomes in gastroesophageal junction adenocarcinoma (GEJAC) treated with neoadjuvant chemoradiotherapy (CRT). Materials and Methods: Pretreatment contrast-enhanced CT images of 146 patients with stage II-III GEJAC were reviewed (2009-2011), and randomly split into training and validation groups at a 1:1 ratio stratified with baseline clinical characteristics. Whole-tumor texture was assessed using quantitative image features based on intensity, shape, and gray-level co-occurrence matrix. The relevant pretreatment texture features, in addition to the significant baseline clinical features to predict survival, were identified using multivariate Cox proportional hazard regression model with stepwise variable selection in the training sample and verified in the validation sample, to facilitate the proposal of a multi-point index for standard patient pre-treatment risk classification. Results: Of the factors identified in the training cohort independently associated with OS, only shape compactness (p = 0.04) and pathologic grade differentiation (PDG) (p = 0.02) were confirmed in the validation sample. Using both parameters, we created a 3-point risk classification index: low-risk (wellmoderate PDG and high compactness), medium-risk (poor PDG or low compactness), and high-risk (poor PDG and low compactness). The risk index showed a strong negative association with postoperative pathologic complete response (pCR) (p = 0.04). Median OS for the high-, medium-, and low-risk groups were 23, 51, and ≥ 72 months, respectively (p < 0.01). Similar results were seen with progression-free survival (respective 5-year rates of 15{\%}, 30{\%}, and 63{\%}). Conclusion: Radiomic texture analysis can be used to stratify patients with GEJAC receiving trimodality therapy based on prognosis. The risk scoring system based on shape compactness and PDG shows a great potential for pre-treatment risk classification to guide surgical resection in locally advanced disease. Though in need of greater validation, these hypothesis-generating data could provide a unique platform of personalized oncologic care.",
author = "Qifeng Wang and Shouhao Zhou and Court, {Laurence E.} and Vivek Verma and Koay, {Eugene J.} and Lifei Zhang and Wencheng Zhang and Chad Tang and Steven Lin and Welsh, {James D.} and Mariela Blum and Sonia Betancourt and Dipen Maru and Hofstetter, {Wayne L.} and Chang, {Joe Y.}",
year = "2017",
month = "7",
day = "1",
doi = "10.1016/j.phro.2017.07.006",
language = "English (US)",
volume = "3",
pages = "37--42",
journal = "Physics and Imaging in Radiation Oncology",
issn = "2405-6316",
publisher = "Elsevier Ireland Ltd",

}

Wang, Q, Zhou, S, Court, LE, Verma, V, Koay, EJ, Zhang, L, Zhang, W, Tang, C, Lin, S, Welsh, JD, Blum, M, Betancourt, S, Maru, D, Hofstetter, WL & Chang, JY 2017, 'Radiomics predicts clinical outcome in primary gastroesophageal junction adenocarcinoma treated by chemo/radiotherapy and surgery', Physics and Imaging in Radiation Oncology, vol. 3, pp. 37-42. https://doi.org/10.1016/j.phro.2017.07.006

Radiomics predicts clinical outcome in primary gastroesophageal junction adenocarcinoma treated by chemo/radiotherapy and surgery. / Wang, Qifeng; Zhou, Shouhao; Court, Laurence E.; Verma, Vivek; Koay, Eugene J.; Zhang, Lifei; Zhang, Wencheng; Tang, Chad; Lin, Steven; Welsh, James D.; Blum, Mariela; Betancourt, Sonia; Maru, Dipen; Hofstetter, Wayne L.; Chang, Joe Y.

In: Physics and Imaging in Radiation Oncology, Vol. 3, 01.07.2017, p. 37-42.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Radiomics predicts clinical outcome in primary gastroesophageal junction adenocarcinoma treated by chemo/radiotherapy and surgery

AU - Wang, Qifeng

AU - Zhou, Shouhao

AU - Court, Laurence E.

AU - Verma, Vivek

AU - Koay, Eugene J.

AU - Zhang, Lifei

AU - Zhang, Wencheng

AU - Tang, Chad

AU - Lin, Steven

AU - Welsh, James D.

AU - Blum, Mariela

AU - Betancourt, Sonia

AU - Maru, Dipen

AU - Hofstetter, Wayne L.

AU - Chang, Joe Y.

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Purpose: Radiomics has shown great promise to use quantifiable imaging characteristics to predict the behavior and prognosis of neoplasms. This is the first study to evaluate whether radiomic texture analysis can predict outcomes in gastroesophageal junction adenocarcinoma (GEJAC) treated with neoadjuvant chemoradiotherapy (CRT). Materials and Methods: Pretreatment contrast-enhanced CT images of 146 patients with stage II-III GEJAC were reviewed (2009-2011), and randomly split into training and validation groups at a 1:1 ratio stratified with baseline clinical characteristics. Whole-tumor texture was assessed using quantitative image features based on intensity, shape, and gray-level co-occurrence matrix. The relevant pretreatment texture features, in addition to the significant baseline clinical features to predict survival, were identified using multivariate Cox proportional hazard regression model with stepwise variable selection in the training sample and verified in the validation sample, to facilitate the proposal of a multi-point index for standard patient pre-treatment risk classification. Results: Of the factors identified in the training cohort independently associated with OS, only shape compactness (p = 0.04) and pathologic grade differentiation (PDG) (p = 0.02) were confirmed in the validation sample. Using both parameters, we created a 3-point risk classification index: low-risk (wellmoderate PDG and high compactness), medium-risk (poor PDG or low compactness), and high-risk (poor PDG and low compactness). The risk index showed a strong negative association with postoperative pathologic complete response (pCR) (p = 0.04). Median OS for the high-, medium-, and low-risk groups were 23, 51, and ≥ 72 months, respectively (p < 0.01). Similar results were seen with progression-free survival (respective 5-year rates of 15%, 30%, and 63%). Conclusion: Radiomic texture analysis can be used to stratify patients with GEJAC receiving trimodality therapy based on prognosis. The risk scoring system based on shape compactness and PDG shows a great potential for pre-treatment risk classification to guide surgical resection in locally advanced disease. Though in need of greater validation, these hypothesis-generating data could provide a unique platform of personalized oncologic care.

AB - Purpose: Radiomics has shown great promise to use quantifiable imaging characteristics to predict the behavior and prognosis of neoplasms. This is the first study to evaluate whether radiomic texture analysis can predict outcomes in gastroesophageal junction adenocarcinoma (GEJAC) treated with neoadjuvant chemoradiotherapy (CRT). Materials and Methods: Pretreatment contrast-enhanced CT images of 146 patients with stage II-III GEJAC were reviewed (2009-2011), and randomly split into training and validation groups at a 1:1 ratio stratified with baseline clinical characteristics. Whole-tumor texture was assessed using quantitative image features based on intensity, shape, and gray-level co-occurrence matrix. The relevant pretreatment texture features, in addition to the significant baseline clinical features to predict survival, were identified using multivariate Cox proportional hazard regression model with stepwise variable selection in the training sample and verified in the validation sample, to facilitate the proposal of a multi-point index for standard patient pre-treatment risk classification. Results: Of the factors identified in the training cohort independently associated with OS, only shape compactness (p = 0.04) and pathologic grade differentiation (PDG) (p = 0.02) were confirmed in the validation sample. Using both parameters, we created a 3-point risk classification index: low-risk (wellmoderate PDG and high compactness), medium-risk (poor PDG or low compactness), and high-risk (poor PDG and low compactness). The risk index showed a strong negative association with postoperative pathologic complete response (pCR) (p = 0.04). Median OS for the high-, medium-, and low-risk groups were 23, 51, and ≥ 72 months, respectively (p < 0.01). Similar results were seen with progression-free survival (respective 5-year rates of 15%, 30%, and 63%). Conclusion: Radiomic texture analysis can be used to stratify patients with GEJAC receiving trimodality therapy based on prognosis. The risk scoring system based on shape compactness and PDG shows a great potential for pre-treatment risk classification to guide surgical resection in locally advanced disease. Though in need of greater validation, these hypothesis-generating data could provide a unique platform of personalized oncologic care.

UR - http://www.scopus.com/inward/record.url?scp=85070485076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070485076&partnerID=8YFLogxK

U2 - 10.1016/j.phro.2017.07.006

DO - 10.1016/j.phro.2017.07.006

M3 - Article

VL - 3

SP - 37

EP - 42

JO - Physics and Imaging in Radiation Oncology

JF - Physics and Imaging in Radiation Oncology

SN - 2405-6316

ER -