Discovery and Validation of a CT-Based Radiomic Signature for Preoperative Prediction of Early Recurrence in Hypopharyngeal Carcinoma

Abstract

Purpose. In the clinical management of hypopharyngeal squamous cell carcinoma (HSCC), preoperative identification of early recurrence (≤2 years) after curative resection is essential. Thus, we aimed to develop a CT-based radiomic signature to predict early recurrence in HSCC patients preoperatively. Methods. In total, 167 HSCC patients who underwent partial surgery were enrolled in this retrospective study and divided into two groups, i.e., the training cohort (n=133) and the validation cohort (n=34). Each individual was followed up for at least for 2 years. Radiomic features were extracted from CT images, and the radiomic signature was built with the least absolute shrinkage and selection operator (LASSO) logistic regression (LR) model. The associations of preoperative clinical factors with early recurrence were evaluated. A radiomic signature-combined model was built, and the area under the curve (AUC) was used to explore their performance in discriminating early recurrence. Results. Among the 1415 features, 335 of them were selected using the variance threshold method. Then, the SelectKBest method was further used for the selection of 31 candidate features. Finally, 11 out of 31 optimal features were identified with the LASSO algorithm. In the LR classifier, the AUCs of the training and validation sets in discriminating early recurrence were 0.83 (95% CI: 0.76-0.90) (sensitivity 0.8 and specificity 0.83) and 0.83 (95% CI: 0.67-0.99) (sensitivity 0.69 and specificity 0.71), respectively. Conclusions. Using the radiomic signature, we developed a radiomic signature to preoperatively predict early recurrence in patients with HSCC, which may serve as a potential noninvasive tool to guide personalized treatment.

A Prospectively Validated Prognostic Model for Patients with Locally Advanced Squamous Cell Carcinoma of the Head and Neck Based on Radiomics of Computed Tomography Images

“…Previous studies have shown that radiomics in computed tomography (CT) imaging can improve the prediction of prognosis of HNSCC . Radiomics on CT HNSCC imaging has been used to predict HPV status [8,9], overall survival [10][11][12][13][14], progression-free survival [10,[12][13][14], local tumour control [8,12,[15][16][17][18][19][20][21], tumour grade [9,22], lymph node response [23,24], tumour invasiveness [9,25], xerostomia [26][27][28], tumour resectability [29], and classifying molecular subtypes [30,31]. While the survival studies show that radiomics on CT data can significantly stratify patients in multiple survival groups, performance expressed through Harrell's C index ranged widely, from 0.58 to 0.9.…”

Radiomics in Hypopharyngeal Cancer Management: A State-of-the-Art Review

“…Twelve studies, all of them retrospective, were subjected to qualitative analysis [ 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 ]. The demographic characteristics of patients from these studies are summarized in Table 1 .…”

MRI Radiomics for Predicting Survival in Patients with Locally Advanced Hypopharyngeal Cancer Treated with Concurrent Chemoradiotherapy

“…Another study reported that wavelet-LHL_firstorder_Maximum and wavelet-LHL-firstorder_Kurtosis—two features extracted from post-contrast CT images—successfully predicted PFS in patients with locally advanced hypopharyngeal cancer who had undergone induction chemotherapy [ 23 ]. Finally, Li et al [ 24 ] developed a CT radiomic signature based on first-order features (i.e., minimum, skewness, and total energy) to be used in the preoperative phase for predicting early recurrences of hypopharyngeal cancer. Second-order radiomic features—also termed texture features—reflect the statistical relationships of gray levels within an image and represent a proxy for intratumor heterogeneity.…”