Search

Purpose: To assess the consistency of Ovarian-Adnexal Reporting and Data System (O-RADS) lexicon interpretation between senior and junior sonologists and to investigate its impact on O-RADS classification and diagnostic performance. Methods: We prospectively studied 620 patients with adnexal lesions, all of whom underwent transvaginal or transrectal ultrasound performed by a senior sonologist (R1) who selected the O-RADS lexicon description and O-RADS category for the lesion after the examination. Meanwhile, the junior sonologist (R2) analyzed the images retained by R1 and divided the lesion in the same way. Pathological findings were used as a reference standard. kappa (к) statistics were used to assess the interobserver agreement. Results: Of the 620 adnexal lesions, 532 were benign and 88 were malignant. When using the O-RADS lexicon, R1 and R2 had almost perfect agreement regarding lesion category, external contour of solid lesions, presence of papillary inside cystic lesions, and fluid echogenicity (к: 0.81–1.00). Substantial agreement in solid components, acoustic shadow, vascularity and O-RADS categories (к: 0.61–0.80). Consistency in classifying classic benign lesions in the O-RADS category was only moderate (к = 0.535). No significant difference in diagnostic performance between them using O-RADS (P = 0.1211). Conclusion: There was good agreement between senior and junior sonologists in the interpretation of the O-RADS lexicon and in the classification of O-RADS, except for a moderate agreement in the interpretation and classification of classic benign lesions. Differences in O-RADS category delineation between sonologists had no significant effect on the diagnostic performance of O-RADS. [ABSTRACT FROM AUTHOR]

Objectives: To establish a breast lesion risk stratification system using ultrasound images to predict breast malignancy and assess Breast Imaging Reporting and Data System (BI-RADS) categories simultaneously. Methods: This multicenter study prospectively collected a dataset of ultrasound images for 5012 patients at thirty-two hospitals from December 2018 to December 2020. A deep learning (DL) model was developed to conduct binary categorization (benign and malignant) and BI-RADS categories (2, 3, 4a, 4b, 4c, and 5) simultaneously. The training set of 4212 patients and the internal test set of 416 patients were from thirty hospitals. The remaining two hospitals with 384 patients were used as an external test set. Three experienced radiologists performed a reader study on 324 patients randomly selected from the test sets. We compared the performance of the DL model with that of three radiologists and the consensus of the three radiologists. Results: In the external test set, the DL model achieved areas under the receiver operating characteristic curve (AUCs) of 0.980 and 0.945 for the binary categorization and six-way categorizations, respectively. In the reader study set, the DL BI-RADS categories achieved a similar AUC (0.901 vs. 0.933, p = 0.0632), sensitivity (90.98% vs. 95.90%, p = 0.1094), and accuracy (83.33% vs. 79.01%, p = 0.0541), but higher specificity (78.71% vs. 68.81%, p = 0.0012) than those of the consensus of the three radiologists. Conclusions: The DL model performed well in distinguishing benign from malignant breast lesions and yielded outcomes similar to experienced radiologists. This indicates the potential applicability of the DL model in clinical diagnosis. Key Points: • The DL model can achieve binary categorization for benign and malignant breast lesions and six-way BI-RADS categorizations for categories 2, 3, 4a, 4b, 4c, and 5, simultaneously. • The DL model showed acceptable agreement with radiologists for the classification of breast lesions. • The DL model performed well in distinguishing benign from malignant breast lesions and had promise in helping reduce unnecessary biopsies of BI-RADS 4a lesions. [ABSTRACT FROM AUTHOR]

Background: Studies on deep learning (DL)-based models in breast ultrasound (US) remain at the early stage due to a lack of large datasets for training and independent test sets for verification. We aimed to develop a DL model for differentiating benign from malignant breast lesions on US using a large multicenter dataset and explore the model's ability to assist the radiologists. Methods: A total of 14,043 US images from 5012 women were prospectively collected from 32 hospitals. To develop the DL model, the patients from 30 hospitals were randomly divided into a training cohort (n = 4149) and an internal test cohort (n = 466). The remaining 2 hospitals (n = 397) were used as the external test cohorts (ETC). We compared the model with the prospective Breast Imaging Reporting and Data System assessment and five radiologists. We also explored the model's ability to assist the radiologists using two different methods. Results: The model demonstrated excellent diagnostic performance with the ETC, with a high area under the receiver operating characteristic curve (AUC, 0.913), sensitivity (88.84%), specificity (83.77%), and accuracy (86.40%). In the comparison set, the AUC was similar to that of the expert (p = 0.5629) and one experienced radiologist (p = 0.2112) and significantly higher than that of three inexperienced radiologists (p < 0.01). After model assistance, the accuracies and specificities of the radiologists were substantially improved without loss in sensitivities. Conclusions: The DL model yielded satisfactory predictions in distinguishing benign from malignant breast lesions. The model showed the potential value in improving the diagnosis of breast lesions by radiologists. [ABSTRACT FROM AUTHOR]