Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancer
<p><strong>Objectives</strong> This retrospective cohort study developed a prognostic model incorporating PET texture analysis in patients with oesophageal cancer (OC). Internal validation of the model was performed.</p> <p><strong>Methods</strong> Consecuti...
Main Authors: | , , , , , , , , |
---|---|
Format: | Journal article |
Language: | English |
Published: |
Springer Verlag
2017
|
_version_ | 1797070740494745600 |
---|---|
author | Foley, KG Hills, RK Berthon, B Marshall, C Parkinson, C Lewis, WG Crosby, TDL Spezi, E Roberts, SA |
author_facet | Foley, KG Hills, RK Berthon, B Marshall, C Parkinson, C Lewis, WG Crosby, TDL Spezi, E Roberts, SA |
author_sort | Foley, KG |
collection | OXFORD |
description | <p><strong>Objectives</strong> This retrospective cohort study developed a prognostic model incorporating PET texture analysis in patients with oesophageal cancer (OC). Internal validation of the model was performed.</p> <p><strong>Methods</strong> Consecutive OC patients (n = 403) were chronologically separated into development (n = 302, September 2010-September 2014, median age = 67.0, males = 227, adenocarcinomas = 237) and validation cohorts (n = 101, September 2014-July 2015, median age = 69.0, males = 78, adenocarcinomas = 79). Texture metrics were obtained using a machine-learning algorithm for automatic PET segmentation. A Cox regression model including age, radiological stage, treatment and 16 texture metrics was developed. Patients were stratified into quartiles according to a prognostic score derived from the model. A p-value < 0.05 was considered statistically significant. Primary outcome was overall survival (OS).</p> <p><strong>Results</strong> Six variables were significantly and independently associated with OS: age [HR =1.02 (95% CI 1.01-1.04), p < 0.001], radiological stage [1.49 (1.20-1.84), p < 0.001], treatment [0.34 (0.24–0.47), p < 0.001], log(TLG) [5.74 (1.44–22.83), p = 0.013], log(Histogram Energy) [0.27 (0.10–0.74), p = 0.011] and Histogram Kurtosis [1.22 (1.04–1.44), p = 0.017]. The prognostic score demonstrated significant differences in OS between quartiles in both the development (X2 143.14, df 3, p < 0.001) and validation cohorts (X2 20.621, df 3, p < 0.001).</p> <p><strong>Conclusions</strong> This prognostic model can risk stratify patients and demonstrates the additional benefit of PET texture analysis in OC staging.</p> |
first_indexed | 2024-03-06T22:43:15Z |
format | Journal article |
id | oxford-uuid:5c4e3f59-613a-4121-b699-f688c3c16442 |
institution | University of Oxford |
language | English |
last_indexed | 2024-03-06T22:43:15Z |
publishDate | 2017 |
publisher | Springer Verlag |
record_format | dspace |
spelling | oxford-uuid:5c4e3f59-613a-4121-b699-f688c3c164422022-03-26T17:27:25ZDevelopment and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancerJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:5c4e3f59-613a-4121-b699-f688c3c16442EnglishSymplectic Elements at OxfordSpringer Verlag2017Foley, KGHills, RKBerthon, BMarshall, CParkinson, CLewis, WGCrosby, TDLSpezi, ERoberts, SA<p><strong>Objectives</strong> This retrospective cohort study developed a prognostic model incorporating PET texture analysis in patients with oesophageal cancer (OC). Internal validation of the model was performed.</p> <p><strong>Methods</strong> Consecutive OC patients (n = 403) were chronologically separated into development (n = 302, September 2010-September 2014, median age = 67.0, males = 227, adenocarcinomas = 237) and validation cohorts (n = 101, September 2014-July 2015, median age = 69.0, males = 78, adenocarcinomas = 79). Texture metrics were obtained using a machine-learning algorithm for automatic PET segmentation. A Cox regression model including age, radiological stage, treatment and 16 texture metrics was developed. Patients were stratified into quartiles according to a prognostic score derived from the model. A p-value < 0.05 was considered statistically significant. Primary outcome was overall survival (OS).</p> <p><strong>Results</strong> Six variables were significantly and independently associated with OS: age [HR =1.02 (95% CI 1.01-1.04), p < 0.001], radiological stage [1.49 (1.20-1.84), p < 0.001], treatment [0.34 (0.24–0.47), p < 0.001], log(TLG) [5.74 (1.44–22.83), p = 0.013], log(Histogram Energy) [0.27 (0.10–0.74), p = 0.011] and Histogram Kurtosis [1.22 (1.04–1.44), p = 0.017]. The prognostic score demonstrated significant differences in OS between quartiles in both the development (X2 143.14, df 3, p < 0.001) and validation cohorts (X2 20.621, df 3, p < 0.001).</p> <p><strong>Conclusions</strong> This prognostic model can risk stratify patients and demonstrates the additional benefit of PET texture analysis in OC staging.</p> |
spellingShingle | Foley, KG Hills, RK Berthon, B Marshall, C Parkinson, C Lewis, WG Crosby, TDL Spezi, E Roberts, SA Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancer |
title | Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancer |
title_full | Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancer |
title_fullStr | Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancer |
title_full_unstemmed | Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancer |
title_short | Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancer |
title_sort | development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of pet in patients with oesophageal cancer |
work_keys_str_mv | AT foleykg developmentandvalidationofaprognosticmodelincorporatingtextureanalysisderivedfromstandardisedsegmentationofpetinpatientswithoesophagealcancer AT hillsrk developmentandvalidationofaprognosticmodelincorporatingtextureanalysisderivedfromstandardisedsegmentationofpetinpatientswithoesophagealcancer AT berthonb developmentandvalidationofaprognosticmodelincorporatingtextureanalysisderivedfromstandardisedsegmentationofpetinpatientswithoesophagealcancer AT marshallc developmentandvalidationofaprognosticmodelincorporatingtextureanalysisderivedfromstandardisedsegmentationofpetinpatientswithoesophagealcancer AT parkinsonc developmentandvalidationofaprognosticmodelincorporatingtextureanalysisderivedfromstandardisedsegmentationofpetinpatientswithoesophagealcancer AT lewiswg developmentandvalidationofaprognosticmodelincorporatingtextureanalysisderivedfromstandardisedsegmentationofpetinpatientswithoesophagealcancer AT crosbytdl developmentandvalidationofaprognosticmodelincorporatingtextureanalysisderivedfromstandardisedsegmentationofpetinpatientswithoesophagealcancer AT spezie developmentandvalidationofaprognosticmodelincorporatingtextureanalysisderivedfromstandardisedsegmentationofpetinpatientswithoesophagealcancer AT robertssa developmentandvalidationofaprognosticmodelincorporatingtextureanalysisderivedfromstandardisedsegmentationofpetinpatientswithoesophagealcancer |