Deep Learning Model of Primary Tumor and Metastatic Cervical Lymph Nodes From CT for Outcome Predictions in Oropharyngeal Cancer

Abstract

Importance: Primary tumor (PT) and metastatic cervical lymph node (LN) characteristics are highly associated with oropharyngeal squamous cell carcinoma (OPSCC) prognosis. Currently, there is a lack of studies to combine imaging characteristics of both regions for predictions of p16+ OPSCC outcomes.

Objectives: To develop and validate a computed tomography (CT)-based deep learning classifier that integrates PT and LN features to predict outcomes in p16+ OPSCC and to identify patients with stage I disease who may derive added benefit associated with chemotherapy.

Design, setting, and participants: In this retrospective prognostic study, radiographic CT scans were analyzed of 811 patients with p16+ OPSCC treated with definitive radiotherapy or chemoradiotherapy from 3 independent cohorts. One cohort from the Cancer Imaging Archive (1998-2013) was used for model development and validation and the 2 remaining cohorts (2002-2015) were used to externally test the model performance. The Swin Transformer architecture was applied to fuse the features from both PT and LN into a multiregion imaging risk score (SwinScore) to predict survival outcomes across and within subpopulations at various stages. Data analysis was performed between February and July 2024.

Exposures: Definitive radiotherapy or chemoradiotherapy treatment for patients with p16+ OPSCC.

Main outcomes and measures: Hazard ratios (HRs), log-rank tests, concordance index (C index), and net benefit were used to evaluate the associations between multiregion imaging risk score and disease-free survival (DFS), overall survival (OS), and locoregional failure (LRF). Interaction tests were conducted to assess whether the association of chemotherapy with outcome significantly differs across dichotomized multiregion imaging risk score subgroups.

Results: The total patient cohort comprised 811 patients with p16+ OPSCC (median age, 59.0 years [IQR, 47.4-70.6 years]; 683 men [84.2%]). In the external test set, the multiregion imaging risk score was found to be prognostic of DFS (HR, 3.76 [95% CI, 1.99-7.10]; P < .001), OS (HR, 4.80 [95% CI, 2.22-10.40]; P < .001), and LRF (HR, 4.47 [95% CI, 1.43-14.00]; P = .01) among all patients with p16+ OPSCC. The multiregion imaging risk score, integrating both PT and LN information, demonstrated a higher C index (0.63) compared with models focusing solely on PT (0.61) or LN (0.58). Chemotherapy was associated with improved DFS only among patients with high scores (HR, 0.09 [95% CI, 0.02-0.47]; P = .004) but not those with low scores (HR, 0.83 [95% CI, 0.32-2.10]; P = .69).

Conclusions and relevance: This prognostic study of p16+ OPSCC describes the development of a CT-based imaging risk score integrating PT and metastatic cervical LN features to predict recurrence risk and identify suitable candidates for treatment tailoring. This tool could optimize treatment modulations of p16+ OPSCC at a highly granular level.

Figure 1.. Prognostic Value of the Multiregion Imaging Risk Score

A, Kaplan-Meier survival analysis of the score on the external test set using disease-free survival as the end point. B, Kaplan-Meier survival analysis of the score on the external test set using overall survival as the end point. C, Kaplan-Meier survival analysis of the score on the external test set using locoregional failure as the end point. D, Beeswarm plot of Shapley Additive exPlanations (SHAP) variable importance in multivariate Cox proportional hazards regression analysis of disease-free survival. C index indicates concordance index; HR, hazard ratio; and PY, pack-years.

Figure 2.. Model Interpretability

Four representative examples of original computed tomographic (CT) scans, cropped CT images, and the corresponding integrated gradient attention maps. The integrated gradient results show that the deep learning model focused on regions within the primary tumor and lymph nodes in the images.

Figure 3.. Multiregion Imaging Risk Score as a Predictive Biomarker of Added Benefit Associated With Chemotherapy

A, Kaplan-Meier survival analysis of disease-free survival (DFS) between treatment arms on the training set for patients with high scores. B, Kaplan-Meier survival analysis of DFS between treatment arms on the training set for patients with low scores. C, Kaplan-Meier survival analysis of DFS between treatment arms on the internal validation set and the external test set for patients with high scores. D, Kaplan-Meier survival analysis of DFS between treatment arms on the internal validation set and the external test set for patients with low scores. Patients with high scores who received chemotherapy after radiotherapy experienced a significant DFS benefit compared with patients receiving radiotherapy alone, while patients with low scores did not (P = .03 for interaction for the training set; P = .008 for interaction for the internal validation set and the external test set). HR indicates hazard ratio.