Definition and validation of a radiomics signature for loco-regional tumour control in patients with locally advanced head and neck squamous cell carcinoma

被引：12

作者：

Meneghetti, Asier Rabasco ^{[1
,2
,3
]}

Zwanenburg, Alex ^{[2
,3
,4
,5
,6
,7
,8
,9
]}

Leger, Stefan ^{[2
,3
,4
,5
,6
,7
,8
,9
]}

Leger, Karoline ^{[2
,3
,4
,5
,6
,7
,8
,9
,10
]}

Troost, Esther G. C. ^{[2
,3
,4
,5
,6
,7
,8
,9
,10
]}

Linge, Annett ^{[2
,3
,4
,5
,6
,7
,8
,9
,10
]}

Lohaus, Fabian ^{[2
,3
,4
,5
,6
,7
,8
,9
,10
]}

Schreiber, Andreas ^{[11
]}

Kalinauskaite, Goda ^{[5
,12
,13
]}

Tinhofer, Inge ^{[5
,12
,13
]}

Guberina, Nika ^{[5
,14
,15
]}

Guberina, Maja ^{[5
,14
,15
]}

Balermpas, Panagiotis ^{[5
,16
,17
]}

von der Gruen, Jens ^{[5
,16
,17
]}

Ganswindt, Ute ^{[5
,18
,19
,20
,21
]}

Belka, Claus ^{[5
,18
,19
,20
]}

Peeken, Jan C. ^{[5
,18
,22
,23
]}

Combs, Stephanie E. ^{[5
,18
,22
,23
]}

Boeke, Simon ^{[24
,25
,26
]}

Zips, Daniel ^{[5
]}

Krause, Mechthild ^{[1
,2
,3
,5
,6
,7
,8
,9
,10
]}

Baumann, Michael ^{[1
,2
,3
,4
,5
,6
,7
,8
,9
,10
]}

Loeck, Steffen ^{[2
,3
,4
,5
,8
,10
]}

机构：

[1] Helmholtz Zentrum Dresden Rossendorf, Inst Radiooncol OncoRay, Dresden, Germany

[2] Tech Univ Dresden, Helmholtz Zentrum Dresden Rossendorf, Fac Med, OncoRay Natl Ctr Radiat Res Oncol, Dresden, Germany

[3] Tech Univ Dresden, Helmholtz Zentrum Dresden Rossendorf, Univ Hosp Carl Gustav Carus, Dresden, Germany

[4] German Canc Consortium DKTK, Partner Site, Dresden, Germany

[5] German Canc Res Ctr, Heidelberg, Germany

[6] Natl Ctr Tumor Dis NCT, Partner Site Dresden, Dresden, Germany

[7] Tech Univ Dresden, Fac Med, Dresden, Germany

[8] Tech Univ Dresden, Univ Hosp Carl Gustav Carus, Fetscherstr 74, D-01307 Dresden, Germany

[9] Helmholtz Zentrum Dresden Rossendorf HZDR, Helmholtz Assoc, Dresden, Germany

[10] Tech Univ Dresden, Fac Med, Dept Radiotherapy & Radiat Oncol, Dresden, Germany

[11] Hosp Dresden Friedrichstadt, Dept Radiotherapy, Dresden, Germany

[12] German Canc Consortium DKTK, Partner Site Berlin, Berlin, Germany

[13] Charite Univ Med Berlin, Dept Radiooncol & Radiotherapy, Berlin, Germany

[14] German Canc Consortium DKTK, Partner Site Essen, Essen, Germany

[15] Univ Duisburg Essen, Med Fac, Univ Hosp Essen, Dept Radiotherapy, Essen, Germany

[16] German Canc Consortium DKTK, DKTK Partner Site Frankfurt, Frankfurt, Germany

[17] Goethe Univ Frankfurt, Dept Radiotherapy & Oncol, Frankfurt, Germany

[18] German Canc Consortium DKTK, Partner Site Munich, Munich, Germany

[19] Ludwig Maximilians Univ Munchen, Dept Radiat Oncol, Munich, Germany

[20] Helmholtz Zentrum, Personalized Radiotherapy Head & Neck Canc, Clin Cooperat Grp, Munich, Germany

[21] Med Univ Innsbruck, Dept Radiat Oncol, Anichstr 35, A-6020 Innsbruck, Austria

[22] Tech Univ Munich, Dept Radiat Oncol, Munich, Germany

[23] Helmholtz Zentrum Munchen, Inst Radiat Med IRM, Neuherberg, Germany

[24] Germany German Canc Res Ctr DKFZ, German Canc Consortium DKTK, Partner Site Tubingen, Heidelberg, Germany

[25] Eberhard Karls Univ Tubingen, Fac Med, Dept Radiat Oncol, Tubingen, Germany

[26] Eberhard Karls Univ Tubingen, Univ Hosp Tubingen, Tubingen, Germany

来源：

CLINICAL AND TRANSLATIONAL RADIATION ONCOLOGY | 2021年 / 26卷

关键词：

HNSCC; Radiomics; Validation; Biomarker; Machine learning; Loco-regional control; PROGNOSTIC VALUE; HPV STATUS; PRIMARY RADIOCHEMOTHERAPY; HUMAN-PAPILLOMAVIRUS; PROSPECTIVE TRIAL; CANCER-PATIENTS; FDG-PET; HYPOXIA; VOLUME; EXPRESSION;

D O I：

10.1016/j.ctro.2020.11.011

中图分类号：

R73 [肿瘤学];

学科分类号：

100214 ;

摘要：

Purpose: To develop and validate a CT-based radiomics signature for the prognosis of loco-regional tumour control (LRC) in patients with locally advanced head and neck squamous cell carcinoma (HNSCC) treated by primary radiochemotherapy (RCTx) based on retrospective data from 6 partner sites of the German Cancer Consortium - Radiation Oncology Group (DKTK-ROG). Material and methods: Pre-treatment CT images of 318 patients with locally advanced HNSCC were collected. Four-hundred forty-six features were extracted from each primary tumour volume and then filtered through stability analysis and clustering. First, a baseline signature was developed from demographic and tumour-associated clinical parameters. This signature was then supplemented by CT imaging features. A final signature was derived using repeated 3-fold cross-validation on the discovery cohort. Performance in external validation was assessed by the concordance index (C-Index). Furthermore, calibration and patient stratification in groups with low and high risk for loco-regional recurrence were analysed. Results: For the clinical baseline signature, only the primary tumour volume was selected. The final signature combined the tumour volume with two independent radiomics features. It achieved moderately good discriminatory performance (C-Index [95% confidence interval]: 0.66 [0.55-0.75]) on the validation cohort along with significant patient stratification (p = 0.005) and good calibration. Conclusion: We identified and validated a clinical-radiomics signature for LRC of locally advanced HNSCC using a multi-centric retrospective dataset. Prospective validation will be performed on the primary cohort of the HNpradBio trial of the DKTK-ROG once follow-up is completed. (C) 2020 The Author(s). Published by Elsevier B.V. on behalf of European Society for Radiotherapy and Oncology.

引用

页码：62 / 70

页数：9

共 54 条

[1] Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [J].