Machine Learning Based Non-Enhanced CT Radiomics for the Identification of Orbital Cavernous Venous Malformations: An Innovative Tool

J Craniofac Surg. 2022 May 1;33(3):814-820. doi: 10.1097/SCS.0000000000008446. Epub 2022 Jan 12.

Abstract

Purpose: To evaluate the capability of non-enhanced computed tomography (CT) images for distinguishing between orbital cavernous venous malformations (OCVM) and non-OCVM, and to identify the optimal model from radiomics-based machine learning (ML) algorithms.

Methods: A total of 215 cases of OCVM and 120 cases of non- OCVM were retrospectively analyzed in this study. A stratified random sample of 268 patients (80%) was used as the training set (172 OCVM and 96 non-OCVM); the remaining data were used as the testing set. Six feature selection techniques and thirteen ML models were evaluated to construct an optimal classification model.

Results: There were statistically significant differences between the OCVM and non-OCVM groups in the density and tumor location (P < 0.05), whereas other indicators were comparable (age, gender, sharp, P > 0.05). Linear regression (area under the curve [AUC] = 0.9351; accuracy = 0.8657) and Stochastic Gradient Descent (AUC = 0.9448; accuracy = 0.8806) classifiers, both of which coupled with the f test and L1-based feature selection method, achieved optimal performance. The support vector machine (AUC = 0.9186; accuracy = 0.8806), Random Forest (AUC = 0.9288; accuracy = 0.8507) and eXtreme Gradient Boosting (AUC = 0.9147; accuracy = 0.8507) classifier combined with f test method showed excellent average performance among our study, respectively.

Conclusions: The effect of non-enhanced CT images in OCVM not only can help ophthalmologist to find and locate lesion, but also bring great help for the qualitative diagnosis value using radiomic- based ML algorithms.

MeSH terms

  • Algorithms
  • Humans
  • Linear Models
  • Machine Learning*
  • Retrospective Studies
  • Tomography, X-Ray Computed* / methods