Variability in the interpretation of ultrasonography in patients with palpable noncalcified breast tumors.

Abstract

Purpose: To analyze interobserver variability of ultrasonography (US) as an adjunct to mammography in patients with palpable noncalcified breast tumors. Material and Methods: Mammographic, US, and combined reading of 200 patients with palpable noncalcified breast masses were performed independently by four experienced radiologists. Nonneoplastic abnormalities and mammographically obvious cancers were excluded. Receiver operating characteristic (ROC) analysis based on 115 tumors was carried out for mammography, US, and both combined for each radiologist. The US diagnoses of the 45 cancers excluded from ROC analysis and the 55 cancers included were compared. Results: One radiologist revealed a significantly higher diagnostic performance with US than with mammography. Combined reading showed the highest performance for all observers, but the improvement as compared with mammography was significant for only two. Higher accuracy on combined reading was mainly caused by correct upgrading of tumors with benign or indeterminate mammographic findings. One radiologist had benefit of US for downgrading of tumors. All four radiologists made a malignant US diagnosis twice as often in mammographically obvious cancers than in mammographically non-conclusive tumors. Conclusion: Radiologists differ substantially in interpretation of breast imaging. Combined reading offers the highest diagnostic accuracy mainly by correct upgrading of tumors on US. The role of US for downgrading tumors is operator-dependent.