Prediction of Non-Response to Neoadjuvant Chemoradiotherapy in Esophageal Cancer Patients with <sup>18</sup>F-FDG PET Radiomics Based Machine Learning Classification
Roelof J. Beukinga,
Floris B. Poelmann,
Gursah Kats-Ugurlu,
Alain R. Viddeleer,
Ronald Boellaard,
Robbert J. De Haas,
John Th. M. Plukker,
Jan Binne Hulshoff
Affiliations
Roelof J. Beukinga
Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9700 RB Groningen, The Netherlands
Floris B. Poelmann
Department of Surgical Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9700 RB Groningen, The Netherlands
Gursah Kats-Ugurlu
Department of Pathology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9700 RB Groningen, The Netherlands
Alain R. Viddeleer
Department of Radiology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9700 RB Groningen, The Netherlands
Ronald Boellaard
Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9700 RB Groningen, The Netherlands
Robbert J. De Haas
Department of Radiology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9700 RB Groningen, The Netherlands
John Th. M. Plukker
Department of Surgical Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9700 RB Groningen, The Netherlands
Jan Binne Hulshoff
Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9700 RB Groningen, The Netherlands
Background: Approximately 26% of esophageal cancer (EC) patients do not respond to neoadjuvant chemoradiotherapy (nCRT), emphasizing the need for pre-treatment selection. The aim of this study was to predict non-response using a radiomic model on baseline 18F-FDG PET. Methods: Retrospectively, 143 18F-FDG PET radiomic features were extracted from 199 EC patients (T1N1-3M0/T2–4aN0-3M0) treated between 2009 and 2019. Non-response (n = 57; 29%) was defined as Mandard Tumor Regression Grade 4–5 (n = 44; 22%) or interval progression (n = 13; 7%). Randomly, 139 patients (70%) were allocated to explore all combinations of 24 feature selection strategies and 6 classification methods towards the cross-validated average precision (AP). The predictive value of the best-performing model, i.e AP and area under the ROC curve analysis (AUC), was evaluated on an independent test subset of 60 patients (30%). Results: The best performing model had an AP (mean ± SD) of 0.47 ± 0.06 on the training subset, achieved by a support vector machine classifier trained on five principal components of relevant clinical and radiomic features. The model was externally validated with an AP of 0.66 and an AUC of 0.67. Conclusion: In the present study, the best-performing model on pre-treatment 18F-FDG PET radiomics and clinical features had a small clinical benefit to identify non-responders to nCRT in EC.
