Pilot Study for the Assessment of the Best Radiomic Features for Bosniak Cyst Classification Using Phantom and Radiologist Inter-Observer Selection

Since the Bosniak cysts classification is highly reader-dependent, automated tools based on radiomics could help in the diagnosis of the lesion. This study is an initial step in the search for radiomic features that may be good classifiers of benign-malignant Bosniak cysts in machine learning models. A CCR phantom was used through five CT scanners. Registration was performed with ARIA software, while Quibim Precision was used for feature extraction. R software was used for the statistical analysis. Robust radiomic features based on repeatability and reproducibility criteria were chosen. Excellent correlation criteria between different radiologists during lesion segmentation were imposed. With the selected features, their classification ability in benignity-malignity terms was assessed. From the phantom study, 25.3% of the features were robust. For the study of inter-observer correlation (ICC) in the segmentation of cystic masses, 82 subjects were prospectively selected, finding 48.4% of the features as excellent regarding concordance. Comparing both datasets, 12 features were established as repeatable, reproducible, and useful for the classification of Bosniak cysts and could serve as initial candidates for the elaboration of a classification model. With those features, the Linear Discriminant Analysis model classified the Bosniak cysts in terms of benignity or malignancy with 88.2% accuracy.

Automated summary

As the classification of Bosniak cysts heavily relies on the radiologists, automated tools based on radiomics can assist in diagnosing the lesions. This study aims to find radiomic features that can effectively classify benign-malignant Bosniak cysts in machine learning models. A CCR phantom was used with five CT scanners, and ARIA software was used for registration, Quibim Precision was used for feature extraction, and R software was used for statistical analysis. Robust radiomic features based on repeatability and reproducibility were selected, and excellent correlation criteria were imposed among different radiologists during lesion segmentation. The selected features were assessed for their classification ability in terms of benignity-malignity. In the phantom study, 25.3% of the features were found to be robust. In the inter-observer correlation (ICC) study on the segmentation of cystic masses, 82 subjects were selected, and 48.4% of the features showed excellent concordance. By comparing both datasets, 12 features were identified as repeatable, reproducible, and useful in classifying Bosniak cysts, laying the foundation for the development of a classification model. Using these features, the Linear Discriminant Analysis model achieved an 88.2% accuracy in classifying Bosniak cysts in terms of benignity or malignancy.