Premium
Bayesian Probability of Malignancy With BI‐RADS Sonographic Features
Author(s) -
Bouzghar Ghizlane,
Levenback Benjamin J.,
Sultan Laith R.,
Venkatesh Santosh S.,
Cwanger Alyssa,
Conant Emily F.,
Sehgal Chandra M.
Publication year - 2014
Publication title -
journal of ultrasound in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.574
H-Index - 91
eISSN - 1550-9613
pISSN - 0278-4297
DOI - 10.7863/ultra.33.4.641
Subject(s) - medicine , bi rads , malignancy , radiology , breast imaging , ultrasound , bayes' theorem , mammography , receiver operating characteristic , diagnostic accuracy , bayesian probability , breast cancer , pathology , artificial intelligence , cancer , computer science
Objectives The purpose of this study was to develop a quantitative approach for combining individual American College of Radiology Breast Imaging Reporting and Data System (BI‐RADS) sonographic features of breast masses for assessing the overall probability of malignancy. Methods Sonograms of solid breast masses were analyzed by 2 observers blinded to patient age, mammographic features, and lesion pathologic findings. BI‐RADS sonographic features were determined by using American College of Radiology criteria. A naïve Bayes model was used to determine the probability of malignancy of all the sonographic features together and with age and BI‐RADS mammographic features. The diagnostic performance for various combinations was evaluated by using the area under the receiver operating curve (A z ). Results Sonographic features had high positive and negative predictive values. The A z values for BI‐RADS sonographic features for the 2 observers ranged from 0.772 to 0.884, which increased to 0.866 to 0.924 when used with patient age and BI‐RADS mammographic features. The benefit of adding age and mammographic information was more marked for the observer with lower initial diagnostic performance. Age‐specific analysis showed that diagnostic performance varied with age, with higher performance for patients aged 45 years and younger and patients older than 60 years compared to those aged 46 to 60 years. In 85% of cases, the diagnosis of the observers matched. When the consensus between the observers was used for diagnostic decisions, a high level of diagnostic performance (A z , 0.954) was achieved. Conclusions A naïve Bayes model provides a systematic approach for combining sonographic features and other patient characteristics for assessing the probability of malignancy to differentiate malignant and benign breast masses.