ABSTRACT
To discriminate between malignant and benign liver lesions, we evaluated the ultrasound features of the target lesions in 266 patients and established a prediction model using a logistic regression algorithm. The prediction model based on independent factors was expressed as predictive scoreâ¯=â¯1.129â¯×â¯interaction of irregular shape and unclear boundaryâ¯+â¯1.398â¯×â¯occupying effectâ¯+â¯2.363â¯×â¯hypo-echoic haloâ¯+â¯1.987â¯×â¯marginal vascular signâ¯+â¯3.627â¯×â¯cirrhosis backgroundâ¯+â¯2.976â¯×â¯nodule in nodule signâ¯+â¯3.690â¯×â¯metastasis sign. Receiver operating characteristic curve analysis revealed that the optimal cutoff predictive score was 2.8 (area under the curveâ¯=â¯0.942). The specificity of the prediction model was not significantly different from that of computed tomography/magnetic resonance imaging (91.7% vs. 98.8%, pâ¯=â¯0.077), whereas the prediction model had a lower sensitivity (90.1% vs. 97.8%, p < 0.001) and accuracy (90.6% vs. 98.1%, p < 0.001) than computed tomography/magnetic resonance imaging. We conclude that the ultrasound prediction model exhibited good diagnostic performance in discriminating malignant from benign liver lesions.