Automated Lymph Node and Extranodal Extension Assessment Improves Risk Stratification in Oropharyngeal Carcinoma.
Authors
Affiliations (11)
Affiliations (11)
- Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA.
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women's Hospital, Harvard Medical School, Boston, MA.
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA.
- Department of Medical Oncology, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
- Department of Surgery/Otolaryngology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA.
- Department of Medical Biophysics, University Health Network, Toronto, ON, Canada.
- Division of Radiation Oncology, Department of Radiation Oncology, MD Anderson Cancer Center, Houston, TX.
- Department of Medicine and Yale Cancer Center, Yale University School of Medicine and Yale Cancer Center, New Haven, CT.
- Department of Radiology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
- Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, the Netherlands.
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Reproduction, Maastricht University Medical Center, Maastricht, the Netherlands.
Abstract
Extranodal extension (ENE) is a biomarker in oropharyngeal carcinoma (OPC) but can only be diagnosed via surgical pathology. We applied an automated artificial intelligence (AI) imaging platform integrating lymph node autosegmentation with ENE prediction to determine the prognostic value of the number of predicted ENE nodes. We conducted a multisite, retrospective study of 1,733 OPC patients with pretreatment computed tomography who underwent definitive radiation therapy across three institutions. Malignant lymph nodes were segmented using a validated deep learning auto-segmentation model, and segmented lymph nodes were sequentially processed with a validated ENE prediction model to calculate number of nodes with AI-predicted ENE (AI-ENE) per patient. We evaluated associations of AI-ENE with disease outcomes using site-stratified, multivariable Cox regression, adjusting for human papillomavirus (HPV) status, smoking pack-years, tumor and nodal stage, age, and sex. We evaluated risk-stratification improvement when incorporating AI-ENE into the Radiation Therapy Oncology Group (RTOG)-0129 risk groupings and derived American Joint Committee on Cancer (AJCC) 8th edition staging with Uno C-indices and decision curve analyses. Overall, median AI-ENE node number was 1 (range, 0-6). AI-ENE node number was independently associated with poorer distant control (DC; hazard ratio [HR], 1.44 [95% CI, 1.23 to 1.69]; <i>P</i> < .001) and overall survival (OS; HR, 1.30 [95% CI, 1.16 to 1.46]; <i>P</i> < .001). Increasing AI-ENE node number was incrementally associated with worse outcome, particularly DC (<i>P</i> < .001). C-indices improved in the external data set when incorporating AI-ENE into RTOG-0129 groupings (OS: 0.70 <i>v</i> 0.65; DC: 0.65 <i>v</i> 0.57) and AJCC-8 stage (OS: 0.75 <i>v</i> 0.70; DC: 0.72 <i>v</i> 0.67; <i>P</i> < .001 for each). The largest improvements were observed among HPV-negative patients (C-index: +15% for OS, +14% for DC). Automated, AI-ENE node number is a novel risk factor for OPC that may better inform pretreatment risk stratification and decision-making.