Automated Detection and Classification of Pleural Effusion on Computed Tomography Using Deep Learning.
Authors
Affiliations (6)
Affiliations (6)
- Department of Radiology, Inonu Unıversıty, Malatya, Turkey. [email protected].
- Department of Electrical Electronics Engineering, Gaziantep Islam Scıence and Technology Unıversıty, Gaziantep, Turkey.
- Department of Radiology, Inonu Unıversıty, Malatya, Turkey.
- Department of Anatomy, Gaziantep Islam Scıence and Technology Unıversıty, Gaziantep, Turkey.
- Sirnak State Hospital, Sirnak, Turkey.
- Department of Pathology, Inonu University, Malatya, Turkey.
Abstract
The aim of this study is to develop and evaluate the performance of a two-stage deep learning-based artificial intelligence framework for the automatic segmentation and etiological classification of pleural effusion from noncontrast thoracic computed tomography (CT) images. In this retrospective study, patients with pleural effusion detected on noncontrast thorax CT and with available pathogenic and/or cytological examinations after diagnostic thoracentesis were included. In the first stage, pleural effusion regions were automatically segmented using a U-Net-based deep learning model. In the second stage, pleural effusions were classified into three groups-empyema, malignant, and transudative-using quantitative imaging features derived from the segmentation masks, including area-, density-, and texture-based features. Logistic regression, support vector machines, random forest, and gradient boosting algorithms were used for classification. The U-Net-based segmentation model demonstrated high agreement in delineating pleural effusion regions and achieved successful segmentation performance on the validation dataset. In the etiological classification performed using quantitative features extracted after segmentation, the highest performance was obtained with tree-based models. The gradient boosting and random forest algorithms achieved 96% accuracy and a macro F1-score of 0.95 in three-class etiological discrimination. Feature importance analysis showed that pleural effusion area, the standard deviation of intensity within the mask, and GLCM-based parameters reflecting texture heterogeneity were the most discriminative features for classification. The two-stage artificial intelligence approach developed in this study achieved high accuracy in the automatic segmentation and etiological classification of pleural effusion on noncontrast thorax CT images. The proposed system has the potential to serve as a strong decision support tool in clinical practice by enabling rapid, objective, and reproducible evaluation of pleural effusions.