Application of Computer‐Aided Diagnosis on Breast Ultrasonography: Evaluation of Diagnostic Performances and Agreement of Radiologists According to Different Levels of Experience

Abstract

S-Detect is a clinically feasible diagnostic tool that can be used to improve the specificity, PPV, and accuracy of breast US, with a moderate degree of agreement in final assessments, regardless of the experience of the radiologist.

Automated classification of focal breast lesions according to S-detect: validation and role as a clinical and teaching tool

“…According to Cho et al [24], when the performance of S-detect was compared to that of 2 radiologists with different levels of experience, the software alone showed lower sensitivity and higher specificity than the more experienced radiologist and the less experienced radiologist-72.2 vs. 94.4% and 94.4% sensitivity and 90.8 vs. 49.2% and 55.4% specificity. However, when the operators' readings and the software assessments were combined, a significant increase in specificity and PPV was noted, with no statistically significant detrimental effect on sensitivity.…”

Breast Ultrasound Computer-Aided Diagnosis: Analysis of Types of Errors

“…US BI-RADS has substantially contributed to improving communication between physicians and radiologists, but observer variability remains a major limitation of US, which is 97.9 C4A = category 4A, low suspicion for malignancy, C4B = category 4B, moderate suspicious for malignancy, CAD = computer-aided diagnosis, NPV = negative predictive value, PPV = positive predictive value (4,6,9,11,13,15,16). In this study, we evaluated the di- (4,9,11,17).…”

“…Many studies have applied CAD systems to breast US to demonstrate the efficiency of CAD systems and to evaluate the usefulness of CAD systems for improving diagnostic accuracy (4)(5)(6)(7)(8)(9)(10)(11). There are two algorithms in breast US-CAD systems for lesion interpretations.…”

Caracterização de lesões em imagens digitais de ultrassonografia e elastografia da mama utilizando técnicas inteligentes

“…Da mesma forma que alguns sistemas comerciais (B-CAD e S-detect) de classificação de lesões da mama em imagens de ultrassom modo-B (CHABI et al, 2012;CHO et al, 2017;KIM et al, 2017), o sistema CADx desenvolvido também permite que o contorno da lesão possa ser determinado de forma manual ou automática. O radiologista é quem escolhe a forma mais precisa de delineamento e, se necessário, pode modificar o contorno.…”

“…Dentre os métodos de aprendizado de máquina abordados (item 4.4), o SVM é um classificador que vem sendo amplamente utilizado na literatura para distinguir lesões benignas de lesões malignas em imagens de ultrassom modo-B (HUANG et al, 2008;SHAN et al, 2016), incluindo sistemas comerciais como, por exemplo, o S-detect (CHO et al, 2017;KIM et al, 2017) e o B-CAD (CHABI et al, 2012). Este estudo apontou resultado superior ao Sdetect -cuja AUC foi de 0,815, enquanto que a do sistema CADx proposto foi de 0,840…”