Clinical validation of S-Detect TM mode in semi-automated ultrasound classification of thyroid lesions in surgical office

摘要: Background: In recent years well-recognized scientific societies introduced guidelines for ultrasound (US) malignancy risk stratification of thyroid nodules. These categorize the in relation to a combination several US features. Based on these image lexicons an US-based computer-aided diagnosis (CAD) systems were developed. Nevertheless, their clinical utility has not been evaluated any study surgeon-performed office thyroid. Hence, aim this pilot was validate s-Detect TM mode semi-automated classification lesions during US. Methods: This is prospective 50 patients who underwent (basic skills without CAD vs . with expert CAD) out-patient as part preoperative workup. The real-time system software using artificial intelligence (S-Detect Thyroid; Samsung Medison Co.) integrated into RS85 system. Primary outcome added-value evaluation. Secondary outcomes were: diagnostic accuracy system, intra and interobserver variability assessment Surgical pathology report used pre-surgical diagnosis. Results: by surgeon basic equal 6% (overall 82% evaluation 76% system; P Conclusions: sensitivity negative predictive value similar whereas specificity positive significantly inferior but markedly better than judgement alone.