Abstract
Radiomics reflects the texture and morphological features of tumours by quantitatively analysing the grey values of medical images. We aim to develop a nomogram incorporating radiomics and the Breast Imaging Reporting and Data System (BI-RADS) for predicting breast cancer in BI-RADS ultrasound (US) category 4 or 5 lesions. From January 2017 to August 2018, a total of 315 pathologically proven breast lesions were included. Patients from the study population were divided into a training group (n = 211) and a validation group (n = 104) according to a cut-off date of March 1st, 2018. Each lesion was assigned a category (4A, 4B, 4C or 5) according to the second edition of the American College of Radiology (ACR) BI-RADS US. A radiomics score was generated from the US image. A nomogram was developed based on the results of multivariate regression analysis from the training group. Discrimination, calibration and clinical usefulness of the nomogram for predicting breast cancer were assessed in the validation group. The radiomics score included 9 selected radiomics features. The radiomics score and BI-RADS category were independently associated with breast malignancy. The nomogram incorporating the radiomics score and BI-RADS category showed better discrimination (area under the receiver operating characteristic curve [AUC]: 0.928; 95% confidence interval [CI]: 0.876, 0.980) between malignant and benign lesions than either the radiomics score (P = 0.029) or BI-RADS category (P = 0.011). The nomogram demonstrated good calibration and clinical usefulness. In conclusion, the nomogram combining the radiomics score and BI-RADS category is potentially useful for predicting breast malignancy in BI-RADS US category 4 or 5 lesions.
Highlights
In the second edition of the American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) US atlas, breast lesions are assigned a category after analysing their sonographic features[4]
We focused our study on breast lesions classified as ACR BI-RADS US categories 4 or 5 because these lesions have a wide-ranging likelihood of malignancy (>2%) and were recommended for biopsy
Our results demonstrated that the radiomics score showed similar discrimination performance to BI-RADS classification, and the nomogram showed better performance than the radiomics score or BI-RADS category. These results demonstrated that incorporating radiomics with BI-RADS category could improve the predictive performance for identifying breast malignancy, which can likely be reproduced by other radiologists
Summary
In the second edition of the ACR BI-RADS US atlas, breast lesions are assigned a category after analysing their sonographic features[4]. Category 4 is defined as suspicious lesion with 2% to 95% malignant probability that is recommended for biopsy. Radiomics can extract many quantitative features from medical images through a computer algorithm[9,10,11]. We hypothesized that these potential quantitative features extracted from US images could predict the malignancy of breast lesions. A nomogram incorporating the radiomics score and BI-RADS category was developed to predict the malignancy of breast lesions. We focused our study on breast lesions classified as ACR BI-RADS US categories 4 or 5 because these lesions have a wide-ranging likelihood of malignancy (>2%) and were recommended for biopsy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
