Deep learning enhanced MRI radiomics in predicting pathologic response of head and neck squamous carcinoma to neoadjuvant chemoimmunotherapy: a retrospective analysis.
Authors
Affiliations (7)
Affiliations (7)
- Department of Oral and Maxillofacial Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, Guangdong, China.
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Medical Research Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China.
- School of Biomedical Engineering, Southern Medical University, Guangzhou, Guangdong, China.
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Guangzhou, Guangdong, China.
- Department of Stomatology, The First People's Hospital of Foshan, Foshan, Guangdong, China.
- Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, Guangdong, China.
- School of Mathematics and Big Data, Foshan University, Foshan, Guangdong, China.
Abstract
Neoadjuvant chemoimmunotherapy (NACI) has become one of the most widely adopted therapies for head and neck squamous cell carcinoma (HNSCC) before surgery. However, the accurate prediction of patients responding to this therapy has been challenging owing to the lack of predictive biomarkers. In the present study, histologically confirmed HNSCC patients with complete clinicopathological data, who received chemotherapy plus programmed cell death protein 1 inhibitor as the NACI regimen for 2-3 cycles before radical surgery between 2021 and 2023, were screened, and both clinicopathological and magnetic resonance imaging (MRI) image data were collected and divided into training, testing, and external validation cohorts. Both traditional radiomics and deep learning techniques were employed to extract features from MRI images, followed by feature selection using both Spearman correlation and least absolute shrinkage and selection operator analysis. The selected features were incorporated into predictive models using a logistic regression classifier for pathologic complete response. The results demonstrated that three out of seven features extracted from MRI images were deep-learning features. Notably, the integration of deep learning features with clinicopathological and radiomics features increased the area under the curve (AUCs) in the training, testing, and external validation cohorts to 0.781, 0.759, and 0.740, respectively. Moreover, multimodal prediction for patient stratification can significantly improve the prognosis of HNSCC patients undergoing NACI. In conclusion, deep learning features from MRI images can augment traditional imaging analysis to uncover hidden predictive patterns reflecting responsiveness to NACI in HNSCC patients, and integration of different data types provides a more robust prediction strategy.