Exploratory ensemble interpretable model for predicting local failure in head and neck cancer: the additive benefit of CT and intra-treatment cone-beam computed tomography features

Abstract

Background: Local failure (LF) following chemoradiation (CRT) for head and neck cancer is associated with poor overall survival. If machine learning techniques could stratify patients at risk of treatment failure based on baseline and intra-treatment imaging, such a model could facilitate response-adapted approaches to escalate, de-escalate, or switch therapy.Methods: A 1:2 retrospective case control cohort of patients treated at a single institution with definitive radiotherapy for head and neck cancer who failed locally, in-field at a primary or nodal structure were included. Radiomic features were extracted from baseline CT and CBCT scans at fractions 1 and 21 (delta) of radiotherapy with PyRadiomics and were selected for by: reproducibility (intra-class correlation coefficients ≥0.95), redundancy [maximum relevance and minimum redundancy (mRMR)], and informativeness [recursive feature elimination (RFE)]. Separate models predicting LF of primaries or nodes were created using the explainable boosting machine (EBM) classifier with 5-fold cross-validation for (I) clinical only, (II) radiomic only (CT1 and delta features), and (III) fused models (clinical + radiomic). Twenty-five iterations were performed, and predicted scores were averaged with a parallel ensemble design. Receiver operating characteristic curves were compared between models with paired-samples t-tests. Results:The fused ensemble model for primaries (using clinical, CT1, and delta features) achieved an AUC of 0.871 with a sensitivity of 78.3% and specificity of 90.9% at the maximum Youden J statistic.The fused ensemble model trended towards improvement when compared to the clinical only ensemble model (AUC =0.788, P=0.134) but reached significance when compared to the radiomic ensemble model (AUC =0.770, P=0.017). The fused ensemble model for nodes achieved an AUC of 0.910 with a sensitivity of 100.0% and specificity of 68.0%, which also trended towards improvement when compared to the clinical model (AUC =0.865, P=0.080). Conclusions:The fused ensemble EBM model achieved high discriminatory ability at predicting LF for head and neck cancer in independent primary and nodal structures. Although an additive benefit of delta radiomics over clinical factors could not be proven, the results trended towards improvement with the fused ensemble model, which are promising and worthy of prospective investigation in a larger cohort.

Applying multisequence MRI radiomics of the primary tumor and lymph node to predict HPV-related p16 status in patients with oropharyngeal squamous cell carcinoma

“…However, in traditional imaging analysis, the characteristics of whole-tumor imaging findings are based on a radiologist's diagnostic experience, and intratumor heterogeneity has not been analyzed using quantitative imaging methods. Radiomics, which provides highthroughput mining of large amounts of quantitative features derived from medical imaging, is a promising tool in the decision support systems of precision medicine (8)(9)(10)(11). Evidence from previous studies shows that radiomics features could be helpful for personalized risk stratification (12) and individual treatment decisions (13) and may also serve as prognostic indicators (14) of OPSCC.…”

Towards reliable head and neck cancers locoregional recurrence prediction using delta‐radiomics and learning with rejection option

“…Radiomics features extracted from radiological images collected at separate times with the same imaging protocol for the same patient can measure the therapy‐induced changes in the tumor area. The changes in radiomics features, termed delta‐radiomics features, have been associated with treatment response or outcome for serval types of cancers 14–19 . Lin et al.…”

“…They used them together with baseline CT radiomics features for primary tumor local failure prediction. 16 In their results, they showed that adding the delta-radiomics features to the baseline CT-radiomics features improved the AUC value from 0.69 to 0.77. For local advanced rectal cancer (LARC), Jeon et al developed and evaluated the predictive ability of 2D and 3D delta-radiomicsbased signatures for predicting treatment outcome of patients received preoperative chemoradiotherapy and surgery, the constructed delta-radiomics-based signatures were independent prognostic factors and successfully predicted the outcomes.…”

Predicting local persistence/recurrence after radiation therapy for head and neck cancer from PET/CT using a multi-objective, multi-classifier radiomics model

“…The goal of this study was to develop and validate a multi-objective, multi-classifier radiomics model that can predict post-treatment local P/R in patients with HNSCC. As many clinical parameters such as patient age, tumor stage, primary site and HPV status have shown strong correlation to treatment outcome in different studies, we added several of these parameters as features for model training ( 19 , 24 , 25 ). In the multi-objective model, to select the most predictive feature set and to balance the model performance on prediction sensitivity and specificity, we optimized the sparsity of the selected radiomic feature set, the prediction sensitivity, and prediction specificity simultaneously through an immune algorithm.…”