Statistical harmonization can improve the development of a multicenter CT‐based radiomic model predictive of nonresponse to induction chemotherapy in laryngeal cancers

Abstract

To develop a radiomic model predicting nonresponse to induction chemotherapy in laryngeal cancers, from multicenter pretherapeutic contrast-enhanced computed tomography (CE-CT) and evaluate the benefit of feature harmonization in such a context. Methods: Patients (n = 104) eligible for laryngeal preservation chemotherapy were included in five centers. Primary tumor was manually delineated on the CE-CT images. The following radiomic features were extracted with an in-house software (MIRAS v1.1, LaTIM UMR 1101): intensity, shape, and textural features derived from Gray-Level Co-occurrence Matrix (GLCM), Neighborhood Gray Tone Difference Matrix (NGTDM), Gray-Level Run Length Matrix (GLRLM), and Gray-Level Size Zone Matrix (GLSZM). Harmonization was performed using ComBat after unsupervised hierarchical clustering, used to determine labels automatically, given the high heterogeneity of imaging characteristics across and within centers. Patients with similar feature distributions were grouped with unsupervised clustering into an optimal number of clusters (2) determined with "silhouette scoring." Statistical harmonization was then carried out with ComBat on these 2 identified clusters. The cohort was split into training/validation (n = 66) and testing (n = 32) sets. Area under the receiver operating characteristics curves (AUC) were used to evaluate the ability of radiomic features (before and after harmonization) to predict nonresponse to chemotherapy, and specificity (Sp) and sensitivity (Se) were used to quantify their performance in the testing set. Results: Without harmonization, none of the features identified as predictive in the training set remained significant in the testing set. After ComBat, one textural feature identified in the training set keeps a predictive trend in the testing set-Zone Percentage, derived from the GLSZM, was predictive of nonresponse in the training set (AUC = 0.62, Se = 70%, Sp = 64%, P = 0.04) and obtained a satisfactory performance in the testing set (Se = 80%, Sp = 67%, P = 0.03), although significance was limited by the size of the testing set. These results are consistent with previously published findings in head and neck cancers.

Pretreatment radiomics power in evaluating neoadjuvant chemotherapy response and outcome for patients with head and neck squamous cell carcinoma: a systematic review and meta-analysis

“…Included studies and quality assessment A total of 375 articles were retrieved, 325 articles were excluded at the initial assessment screening the topics and abstracts, and 50 full text articles were further screened. Finally, 16 identi ed relevant records [9,[22][23][24][25][26][27][28][29][30][31][32][33][34][35][36], 8238 patients were included in this meta-analysis published from January 2019 to June 2022. Among them, one article [27] was included twice, because it made predictive analysis on different chemotherapy schemes.…”

“…Since the data used in external validation are obtained from a separate database, the external validation model is more reliable and accurate than that of the internal validation model. Eleven [23,25,27,[29][30][31][32][33][34][35][36] articles included in the meta-analysis used internal validation, and four [9,22,24,26] articles used external validation. External validation is necessary in validating the model's generality and ensuring the randomness of patient selection and the homogeneity of the clinical characteristics [44].…”

Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning

“… 63 Common methods for the image domain include standardization of image acquisition, 64 , 65 post-processing of raw sensor-level image data, 66 data augmentation using generative adversarial networks, 67 and style transfer. 68 For the feature domain, identification of reproducible features (e.g., annotation or segmentation reproducibility and computational reproducibility), 55 , 56 , 69 normalization techniques, 70 intensity harmonization, 71 ComBat along with its derivatives, 72 and normalization using deep learning 73 are common methods.…”

Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods

“…Related studies [163][164][165] have used histogram matching to normalize MRI intensity scales. A few studies [166,167] have also applied histogram equalization (enhancing the contrast by flattening the histogram) on images to normalize intensity scales to pre-process images before applying a ComBat harmonization method on top of it. Refer to Table 7 for summary.…”