Intratumoral and peritumoral radiomics of MRIs predicts pathologic complete response to neoadjuvant chemoimmunotherapy in patients with head and neck squamous cell carcinoma

Abstract

Background: For patients with locally advanced head and neck squamous cell carcinoma (HNSCC), combined programmed death receptor-1 inhibitor and chemotherapy improved response rate to neoadjuvant therapy. However, treatment response varies among patients. There is no tool to predict pathologic complete response (pCR) with high accuracy for now. To develop a tool based on radiomics features of MRI to predict pCR to neoadjuvant chemoimmunotherapy (NACI) may provide valuable assistance in treatment regimen determination for HNSCC.

Methods: From January 2021 to April 2024, a total of 172 patients with HNSCC from three medical center, who received NACI followed by surgery, were included and allocated into a training set (n=84), an internal validation set (n=37) and an external validation set (n=51). Radiomics features were extracted from intratumoral and different peritumoral areas, and radiomics signature (Rad-score) for each area was constructed. A radiomics-clinical nomogram was developed based on Rad-scores and clinicopathological characteristics, tested in the validation sets, and compared with clinical nomogram and combined positive score (CPS) in predicting pCR.

Results: The radiomics-clinical nomogram, incorporating peritumoral Rad-score, intratumoral Rad-score and CPS, achieved the highest accuracy with areas under the receiver operating characteristic curve of 0.904 (95% CI, 0.835 to 0.972) in the training cohort, 0.860 (95% CI, 0.722 to 0.998) in the internal validation cohort, and 0.849 (95% CI, 0.739 to 0.959) in the external validation cohort, respectively, which outperformed the clinical nomogram and CPS in predict pCR to NACI for HNSCC.

Conclusion: A nomogram developed based on intratumoral and peritumoral MRI radiomics features outperformed CPS, a widely employed biomarker, in predict pCR to NACI for HNSCC, which would provide incremental value in treatment regimen determination.

Keywords: Head and Neck Cancer; Immunotherapy; Neoadjuvant; Pathologic Complete Response - pCR.

Figure 1. The workflow for the development of the radiomics-clinical nomogram to predict pathologic complete response to neoadjuvant chemoimmunotherapy in head and neck squamous cell carcinoma. AUC, area under the receiver operator characteristic curve; CPS, combined positive score; DCA, decision curve analysis; pCR, pathologic complete response; ROC, receiver operator characteristic curve.

Figure 2. Construction and validation of the radiomics-clinical nomogram performance. (A) Radiomics-clinical nomogram for the prediction of pathologic complete response to neoadjuvant chemoimmunotherapy in head and neck squamous cell carcinoma. (B) Receiver operator characteristic curves of the radiomics-clinical nomogram in the training set. (C) Receiver operator characteristic curves of the radiomics-clinical nomogram in the internal validation set. (D) Receiver operator characteristic curves of the radiomics-clinical nomogram in the external validation set. (E) Calibration curves of the radiomics-clinical nomogram in the training set. (F) Calibration curves of the radiomics-clinical nomogram in the internal validation set. (G) Calibration curves of the radiomics-clinical nomogram in the external validation set. Calibration curves depict agreement between the nomogram-predicted probability of pCR (x-axis) and the actual probability of pCR (y-axis). Dashed line=ideal nomogram; dotted line=apparent predicted accuracy; solid line=calibration estimate from the internally validated model. Perfect prediction would correspond to the dashed line. AUC, area under the receiver operator characteristic curve; CPS, combined positive score; pCR, pathologic complete response.

Figure 3. Clinical utility assessment of the radiomics-clinical nomogram. (A) Radiomics-clinical nomogram developed based on intratumoral radiomics features and clinicopathological characteristics. (B) Radiomics-clinical nomogram developed based on clinicopathological characteristics. (C) Receiver operator characteristic curves of the nomograms, CPS, Rad-scores in all 172 patients. Radiomics-clinical nomogram I refers to the radiomics-clinical nomogram based on intratumoral radiomics score and clinicopathological characteristics. Radiomics-clinical nomogram II refers to the radiomics-clinical nomogram based on intratumoral radiomics score, peritumoral radiomics score and clinicopathological characteristics. Intra-Rad-score refers to the radiomics score of intratumoral area. Peri-Rad-score refers to the radiomics score of the peritumoral area with inward 3 mm. (D) DCA for the nomogram. The net benefit was plotted versus the threshold probability, the value of the lowest suspected probability of pCR to advise the patient to receive neoadjuvant chemoimmunotherapy. The red line represents the radiomics-clinical nomogram. The gray and black lines represent the hypothesis that all patients and no patients received neoadjuvant chemoimmunotherapy. AUC, area under the receiver operator characteristic curve; CPS, combined positive score; DCA, decision curve analysis; pCR, pathologic complete response.

Figure 4. Receiver operator characteristic curves of the nomograms, CPS, Rad-scores in oral SCC (A) and oropharyngeal SCC (B). Radiomics-clinical nomogram I refers to the radiomics-clinical nomogram based on intratumoral radiomics score and clinicopathological characteristics. Radiomics-clinical nomogram II refers to the radiomics-clinical nomogram based on intratumoral radiomics score, peritumoral radiomics score and clinicopathological characteristics. Intra-Rad-score refers to the radiomics score of intratumoral area. Peri-Rad-score refers to the radiomics score of the peritumoral area with inward 3 mm. AUC, area under the receiver operator characteristic curve; CPS, combined positive score; SCC, squamous cell carcinoma.