Comprehensive Analysis of Tumour Sub-Volumes for Radiomic Risk Modelling in Locally Advanced HNSCC
Imaging features for radiomic analyses are commonly calculated from the entire gross tumour volume (GTV <sub>entire</sub><inline-formula>)</inline-formula>. However, tumours are biologically complex and the consideration of different tumour regions in radiomic models may lead...
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/12/10/3047 |
id |
doaj-04ceb70c3f4c40f3b3e0bcf9c2cf0b4e |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Stefan Leger Alex Zwanenburg Karoline Leger Fabian Lohaus Annett Linge Andreas Schreiber Goda Kalinauskaite Inge Tinhofer Nika Guberina Maja Guberina Panagiotis Balermpas Jens von der Grün Ute Ganswindt Claus Belka Jan C. Peeken Stephanie E. Combs Simon Boeke Daniel Zips Christian Richter Mechthild Krause Michael Baumann Esther G.C. Troost Steffen Löck |
spellingShingle |
Stefan Leger Alex Zwanenburg Karoline Leger Fabian Lohaus Annett Linge Andreas Schreiber Goda Kalinauskaite Inge Tinhofer Nika Guberina Maja Guberina Panagiotis Balermpas Jens von der Grün Ute Ganswindt Claus Belka Jan C. Peeken Stephanie E. Combs Simon Boeke Daniel Zips Christian Richter Mechthild Krause Michael Baumann Esther G.C. Troost Steffen Löck Comprehensive Analysis of Tumour Sub-Volumes for Radiomic Risk Modelling in Locally Advanced HNSCC Cancers radiomic image-based risk modelling machine learning personalised therapy radiation oncology |
author_facet |
Stefan Leger Alex Zwanenburg Karoline Leger Fabian Lohaus Annett Linge Andreas Schreiber Goda Kalinauskaite Inge Tinhofer Nika Guberina Maja Guberina Panagiotis Balermpas Jens von der Grün Ute Ganswindt Claus Belka Jan C. Peeken Stephanie E. Combs Simon Boeke Daniel Zips Christian Richter Mechthild Krause Michael Baumann Esther G.C. Troost Steffen Löck |
author_sort |
Stefan Leger |
title |
Comprehensive Analysis of Tumour Sub-Volumes for Radiomic Risk Modelling in Locally Advanced HNSCC |
title_short |
Comprehensive Analysis of Tumour Sub-Volumes for Radiomic Risk Modelling in Locally Advanced HNSCC |
title_full |
Comprehensive Analysis of Tumour Sub-Volumes for Radiomic Risk Modelling in Locally Advanced HNSCC |
title_fullStr |
Comprehensive Analysis of Tumour Sub-Volumes for Radiomic Risk Modelling in Locally Advanced HNSCC |
title_full_unstemmed |
Comprehensive Analysis of Tumour Sub-Volumes for Radiomic Risk Modelling in Locally Advanced HNSCC |
title_sort |
comprehensive analysis of tumour sub-volumes for radiomic risk modelling in locally advanced hnscc |
publisher |
MDPI AG |
series |
Cancers |
issn |
2072-6694 |
publishDate |
2020-10-01 |
description |
Imaging features for radiomic analyses are commonly calculated from the entire gross tumour volume (GTV <sub>entire</sub><inline-formula>)</inline-formula>. However, tumours are biologically complex and the consideration of different tumour regions in radiomic models may lead to an improved outcome prediction. Therefore, we investigated the prognostic value of radiomic analyses based on different tumour sub-volumes using computed tomography imaging of patients with locally advanced head and neck squamous cell carcinoma. The GTV <sub>entire</sub> was cropped by different margins to define the rim and the corresponding core sub-volumes of the tumour. Subsequently, the best performing tumour rim sub-volume was extended into surrounding tissue with different margins. Radiomic risk models were developed and validated using a retrospective cohort consisting of 291 patients in one of the six Partner Sites of the German Cancer Consortium Radiation Oncology Group treated between 2005 and 2013. The validation concordance index (C-index) averaged over all applied learning algorithms and feature selection methods using the GTV<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mo form="prefix">entire</mo></msub></semantics></math></inline-formula> achieved a moderate prognostic performance for loco-regional tumour control (C-index: 0.61 ± 0.04 (mean ± std)). The models based on the 5 mm tumour rim and on the 3 mm extended rim sub-volume showed higher median performances (C-index: 0.65 ± 0.02 and 0.64 ± 0.05, respectively), while models based on the corresponding tumour core volumes performed less (C-index: 0.59 ± 0.01). The difference in C-index between the 5 mm tumour rim and the corresponding core volume showed a statistical trend (<i>p</i> = 0.10). After additional prospective validation, the consideration of tumour sub-volumes may be a promising way to improve prognostic radiomic risk models. |
topic |
radiomic image-based risk modelling machine learning personalised therapy radiation oncology |
url |
https://www.mdpi.com/2072-6694/12/10/3047 |
work_keys_str_mv |
AT stefanleger comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT alexzwanenburg comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT karolineleger comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT fabianlohaus comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT annettlinge comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT andreasschreiber comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT godakalinauskaite comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT ingetinhofer comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT nikaguberina comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT majaguberina comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT panagiotisbalermpas comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT jensvondergrun comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT uteganswindt comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT clausbelka comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT jancpeeken comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT stephanieecombs comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT simonboeke comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT danielzips comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT christianrichter comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT mechthildkrause comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT michaelbaumann comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT esthergctroost comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc AT steffenlock comprehensiveanalysisoftumoursubvolumesforradiomicriskmodellinginlocallyadvancedhnscc |
_version_ |
1724517885732192256 |
spelling |
doaj-04ceb70c3f4c40f3b3e0bcf9c2cf0b4e2020-11-25T03:43:51ZengMDPI AGCancers2072-66942020-10-01123047304710.3390/cancers12103047Comprehensive Analysis of Tumour Sub-Volumes for Radiomic Risk Modelling in Locally Advanced HNSCCStefan Leger0Alex Zwanenburg1Karoline Leger2Fabian Lohaus3Annett Linge4Andreas Schreiber5Goda Kalinauskaite6Inge Tinhofer7Nika Guberina8Maja Guberina9Panagiotis Balermpas10Jens von der Grün11Ute Ganswindt12Claus Belka13Jan C. Peeken14Stephanie E. Combs15Simon Boeke16Daniel Zips17Christian Richter18Mechthild Krause19Michael Baumann20Esther G.C. Troost21Steffen Löck22OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyOncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyOncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyOncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyOncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyDepartment of Radiotherapy, Hospital Dresden-Friedrichstadt, 01067 Dresden, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 10117 Berlin, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 10117 Berlin, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 45147 Essen, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 45147 Essen, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 60596 Frankfurt, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 60596 Frankfurt, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 81377 Munich, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 81377 Munich, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 81377 Munich, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 81377 Munich, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 72076 Tübingen, GermanyGerman Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site, 72076 Tübingen, GermanyOncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyOncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyOncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyOncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyOncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden—Rossendorf, 01307 Dresden, GermanyImaging features for radiomic analyses are commonly calculated from the entire gross tumour volume (GTV <sub>entire</sub><inline-formula>)</inline-formula>. However, tumours are biologically complex and the consideration of different tumour regions in radiomic models may lead to an improved outcome prediction. Therefore, we investigated the prognostic value of radiomic analyses based on different tumour sub-volumes using computed tomography imaging of patients with locally advanced head and neck squamous cell carcinoma. The GTV <sub>entire</sub> was cropped by different margins to define the rim and the corresponding core sub-volumes of the tumour. Subsequently, the best performing tumour rim sub-volume was extended into surrounding tissue with different margins. Radiomic risk models were developed and validated using a retrospective cohort consisting of 291 patients in one of the six Partner Sites of the German Cancer Consortium Radiation Oncology Group treated between 2005 and 2013. The validation concordance index (C-index) averaged over all applied learning algorithms and feature selection methods using the GTV<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mo form="prefix">entire</mo></msub></semantics></math></inline-formula> achieved a moderate prognostic performance for loco-regional tumour control (C-index: 0.61 ± 0.04 (mean ± std)). The models based on the 5 mm tumour rim and on the 3 mm extended rim sub-volume showed higher median performances (C-index: 0.65 ± 0.02 and 0.64 ± 0.05, respectively), while models based on the corresponding tumour core volumes performed less (C-index: 0.59 ± 0.01). The difference in C-index between the 5 mm tumour rim and the corresponding core volume showed a statistical trend (<i>p</i> = 0.10). After additional prospective validation, the consideration of tumour sub-volumes may be a promising way to improve prognostic radiomic risk models.https://www.mdpi.com/2072-6694/12/10/3047radiomicimage-based risk modellingmachine learningpersonalised therapyradiation oncology |