Statistical harmonization can improve the development of a multicenter CT based radiomic model predictive of non-response to induction chemotherapy in laryngeal cancers - Centre René Gauducheau Accéder directement au contenu
Article Dans Une Revue Medical Physics Année : 2021

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

Résumé

PURPOSE: To develop a radiomic model predicting non-response to induction chemotherapy in laryngeal cancers, from multicenter pre-therapeutic contrast-enhanced computed tomography (CE-CT) and evaluate the benefit of features harmonization in such a context. METHODS: Patients (n=104) eligible for laryngeal preservation chemotherapy were included in 5 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 Grey Level Co-occurrence Matrix: GLCM; Neighbourhood Grey Tone Difference Matrix: NGTDM; Grey Level Run Length Matrix: GLRLM; Grey 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 features 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 two identified 2 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 non-response 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 non-response 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." CONCLUSIONS: Radiomic features from CE-CT could help in the selection of patients for induction chemotherapy in laryngeal cancers, with relatively good sensitivity and specificity in predicting lack of response. Statistical harmonization with ComBat and unsupervised clustering seems to improve the predictive value of features extracted in such a heterogeneous multicenter setting.
Fichier principal
Vignette du fichier
Masson et al-2021-Statistical harmonization can improve the development of a multicenter CT based.pdf (1.63 Mo) Télécharger le fichier
Masson1_mp14948-sup-0001-supinfo.docx (83.63 Ko) Télécharger le fichier
Masson1_mp14948-sup-0001-supinfo.pdf (276.11 Ko) Télécharger le fichier
Masson2_mp14948-sup-0002-legends.docx (10.21 Ko) Télécharger le fichier
Masson2_mp14948-sup-0002-legends.pdf (165.73 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03246262 , version 1 (15-06-2021)

Identifiants

Citer

Ingrid Masson, Ronrick Da-Ano, François Lucia, Mélanie Doré, Joel Castelli, et al.. Statistical harmonization can improve the development of a multicenter CT based radiomic model predictive of non-response to induction chemotherapy in laryngeal cancers. Medical Physics, 2021, 48 (7), pp.4099-4109. ⟨10.1002/mp.14948⟩. ⟨hal-03246262⟩
146 Consultations
217 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More