RESUMEN
Purpose To develop a prediction model combining both clinical and CT texture analysis radiomics features for predicting pneumothorax complications in patients undergoing CT-guided core needle biopsy. Materials and Methods A total of 424 patients (mean age, 65.6 years ± 12.7 [SD]; 232 male, 192 female) who underwent CT-guided core needle biopsy between January 2021 and October 2022 were retrospectively included as the training data set. Clinical and procedure-related characteristics were documented. Texture analysis radiomics features were extracted from the subpleural lung parenchyma traversed by needle. Moderate pneumothorax was defined as a postprocedure air rim of 2 cm or greater. The prediction model was developed using logistic regression with backward elimination, presented by linear fusion of the selected features weighted by their coefficients. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). Validation was conducted in an external cohort (n = 45; mean age, 58.2 years ± 12.7; 19 male, 26 female) from a different hospital. Results Moderate pneumothorax occurred in 12.0% (51 of 424) of the training cohort and 8.9% (four of 45) of the external test cohort. Patients with emphysema (P < .001) or a longer needle path length (P = .01) exhibited a higher incidence of moderate pneumothorax in the training cohort. Texture analysis features, including gray-level co-occurrence matrix cluster shade (P < .001), gray-level run-length matrix low gray-level run emphasis (P = .049), gray-level run-length matrix run entropy (P = .003), gray-level size-zone matrix gray-level variance (P < .001), and neighboring gray-tone difference matrix complexity (P < .001), showed higher values in patients with moderate pneumothorax. The combined clinical-radiomics model demonstrated satisfactory performance in both the training (AUC 0.78, accuracy = 71.9%) and external test cohorts (AUC 0.86, accuracy 73.3%). Conclusion The model integrating both clinical and radiomics features offered practical diagnostic performance and accuracy for predicting moderate pneumothorax in patients undergoing CT-guided core needle biopsy. Keywords: Biopsy/Needle Aspiration, Thorax, CT, Pneumothorax, Core Needle Biopsy, Texture Analysis, Radiomics, CT Supplemental material is available for this article. © RSNA, 2024.
Asunto(s)
Biopsia Guiada por Imagen , Neumotórax , Tomografía Computarizada por Rayos X , Humanos , Neumotórax/etiología , Neumotórax/epidemiología , Neumotórax/diagnóstico por imagen , Masculino , Femenino , Anciano , Biopsia Guiada por Imagen/métodos , Biopsia Guiada por Imagen/efectos adversos , Estudios Retrospectivos , Tomografía Computarizada por Rayos X/métodos , Biopsia con Aguja Gruesa/métodos , Biopsia con Aguja Gruesa/efectos adversos , Persona de Mediana Edad , Radiografía Intervencional/métodos , Pulmón/patología , Pulmón/diagnóstico por imagen , Valor Predictivo de las Pruebas , RadiómicaRESUMEN
BACKGROUND/PURPOSE: We evaluated the utility of combining quantitative pulmonary vasculature measures with clinical factors for predicting pulmonary hemorrhage after computed tomography (CT)-guided lung biopsy. METHODS: Patients who underwent CT-guided lung biopsy were retrospectively included in this study. Clinical and radiographic vasculature variables were evaluated as predictors of pulmonary hemorrhage. The radiographic pulmonary vascular analysis included vessel count, density, diameter, and area, and also blood volume in small vessels with a cross-sectional area ≤5 mm2 (BV5) and total blood vessel volume (TBV) in the lungs. Univariate and multivariate logistic regressions were used to identify the independent risk factors of higher-grade pulmonary hemorrhage and establish the prediction model presented as a nomogram. RESULTS: The study included 126 patients; discovery cohort n = 103, and validation cohort n = 23. All pulmonary hemorrhage, higher-grade (grade ≥2) pulmonary hemorrhage, and hemoptysis occurred in 42.9%, 15.9%, and 3.2% of patients who underwent CT-guided lung biopsies. In the discovery cohort, patients with larger lesion depth (p = 0.013), higher vessel density (p = 0.033), and higher BV5 (p = 0.039) were more likely to experience higher-grade hemorrhage. The nomogram prediction model for higher-grade hemorrhage built by the discovery cohort showed similar performance in the validation cohort. CONCLUSIONS: Higher-grade pulmonary hemorrhage may occur after CT-guided lung biopsy. Lesion depth, vessel density, and BV5 are independent risk factors for higher-grade pulmonary hemorrhage. Nomograms integrating clinical parameters and radiographic pulmonary vasculature measures offer enhanced capability for assessing hemorrhage risk following CT-guided lung biopsy, thereby facilitating improved patient clinical care.