Quantitative computed tomography texture analysis: can it improve diagnostic accuracy to differentiate malignant lymph nodes?

This study evaluated the accuracy of computed tomography texture analysis (CTTA) in differentiating benign and malignant mediastinal lymph nodes (LNs) in non-small-cell lung cancer patients. Using "AVIEW" software by Coreline Soft, CTTA was applied to pathologically confirmed LN samples obtained via endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA), along with chest CT and FDG PET/CT data. The study included 132 LNs from 80 patients, classified into malignant (61) and benign (71) groups. EBUS findings showed that size >1 cm, round shape, heterogeneous echogenicity, and coagulation necrosis were more prevalent in malignant LNs. CTTA features such as compactness and normalized standard deviation (SD) differed between the groups. High standard uptake value (SUV) on FDG PET/CT and normalized SD on CTTA showed similar diagnostic accuracy, though normalized SD had low sensitivity. The study concludes that while CTTA may aid in differentiating LNs, its diagnostic value is limited and should be integrated with other imaging modalities.