Focal breast lesion characterization according to the BI-RADS US lexicon: role of a computer-aided decision-making support

Choi

et al. 2021

Sci Rep

A major limitation of screening breast ultrasound (US) is a substantial number of false-positive biopsy. This study aimed to develop a deep learning-based computer-aided diagnosis (DL-CAD)-based diagnostic model to improve the differential diagnosis of screening US-detected breast masses and reduce false-positive diagnoses. In this multicenter retrospective study, a diagnostic model was developed based on US images combined with information obtained from the DL-CAD software for patients with breast masses detected using screening US; the data were obtained from two hospitals (development set: 299 imaging studies in 2015). Quantitative morphologic features were obtained from the DL-CAD software, and the clinical findings were collected. Multivariable logistic regression analysis was performed to establish a DL-CAD-based nomogram, and the model was externally validated using data collected from 164 imaging studies conducted between 2018 and 2019 at another hospital. Among the quantitative morphologic features extracted from DL-CAD, a higher irregular shape score (P = .018) and lower parallel orientation score (P = .007) were associated with malignancy. The nomogram incorporating the DL-CAD-based quantitative features, radiologists’ Breast Imaging Reporting and Data Systems (BI-RADS) final assessment (P = .014), and patient age (P < .001) exhibited good discrimination in both the development and validation cohorts (area under the receiver operating characteristic curve, 0.89 and 0.87). Compared with the radiologists’ BI-RADS final assessment, the DL-CAD-based nomogram lowered the false-positive rate (68% vs. 31%, P < .001 in the development cohort; 97% vs. 45% P < .001 in the validation cohort) without affecting the sensitivity (98% vs. 93%, P = .317 in the development cohort; each 100% in the validation cohort). In conclusion, the proposed model showed good performance for differentiating screening US-detected breast masses, thus demonstrating a potential to reduce unnecessary biopsies.

Section: Discussionsupporting

confidence: 92%

mentioning

confidence: 99%

Deep learning-based computer-aided diagnosis in screening breast ultrasound to reduce false-positive diagnoses

Choi

et al. 2021

Sci Rep

“…[1] Previous studies have shown that the use of CAD can lead to a change in the final BI-RADS classification with a significant rate of correct re-classification. [15,16] Bartolotta et al [15] showed a re-classification rate of 21.3% by 2 experienced radiologists after the use of CAD and 81% cases were correctly re-classified. Among the re-classified lesions, there was a correct change in clinical management in 42.2% cases and incorrect change in clinical management in 18.7% cases.…”

Section: Discussionmentioning

confidence: 99%

A computer-aided diagnosis system using artificial intelligence for the diagnosis and characterization of breast masses on ultrasound

et al. 2019

To evaluate the value of the computer-aided diagnosis (CAD) program applied to diagnostic breast ultrasonography (US) based on operator experience.US images of 100 breast masses from 91 women over 2 months (from May to June 2015) were collected and retrospectively analyzed. Three less experienced and 2 experienced breast imaging radiologists analyzed the US features of the breast masses without and with CAD according to the Breast Imaging Reporting and Data System (BI-RADS) lexicon and categories. We then compared the diagnostic performance between the experienced and less experienced radiologists and analyzed the interobserver agreement among the radiologists.Of the 100 breast masses, 41 (41%) were malignant and 59 (59%) were benign. Compared with the experienced radiologists, the less experienced radiologists had significantly improved negative predictive value (86.7%–94.7% vs 53.3%–76.2%, respectively) and area under receiver operating characteristics curve (0.823–0.839 vs 0.623–0.759, respectively) with CAD assistance (all P < .05). In contrast, experienced radiologists had significantly improved specificity (52.5% and 54.2% vs 66.1% and 66.1%) and positive predictive value (55.6% and 58.5% vs 64.9% and 64.9%, respectively) with CAD assistance (all P < .05). Interobserver variability of US features and final assessment by categories were significantly improved and moderate agreement was seen in the final assessment after CAD combination regardless of the radiologist's experience.CAD is a useful additional diagnostic tool for breast US in all radiologists, with benefits differing depending on the radiologist's level of experience. In this study, CAD improved the interobserver agreement and showed acceptable agreement in the characterization of breast masses.

“…Then, the US images were reviewed to see if they were of adequate image quality for CAD analysis and a total of 492 breast lesions (292 benign and 200 malignant masses) in 472 women were nally included for review according to the following indications: 1) masses that were pathologically con rmed with US-guided biopsy or surgery or 2) masses that had been followed for more than 2 years after being detected with benign features on US (Table 1). The proportion of benign and malignant masses used in preceding research to evaluate the performance of AI-CAD was used to select the 492 breast masses in our study [10]. Mean age of the 472 women was 49.4 ± 10.1 years (range, 25-90 years).…”

Section: Data Collectionmentioning

confidence: 99%

Differing Benefits of Artificial Intelligence-based Computer-aided Diagnosis (AI-CAD) for Breast US According to Workflow and Experience Level

Lee¹,

Han²,

Youk³

et al. 2021

Preprint

Background: To evaluate how artificial intelligence-based computer-assisted diagnosis (AI-CAD) for breast ultrasound (US) influences diagnostic performance and agreements between radiologists with varying experience levels in different workflows.Methods: From Apr 2017 to Jun 2018, images of 492 breast lesions (200 malignant and 292 benign masses) in 472 women were included. Six radiologists (3 inexperienced with < 1 year of experience, 3 experienced with 10-15 years of experience) individually reviewed US images with and without the aid of AI-CAD, first in sequential and then in independent reading. Diagnostic performances and interobserver agreements were calculated and compared between radiologists and AI-CAD. Results: After implementing AI-CAD, specificity, PPV and accuracy significantly improved, regardless of experience and workflow (all P<0.001, respectively). Overall area under the receiving operator characteristics curve (AUC) significantly increased in independent reading, but only for inexperienced radiologists. Agreements for BI-RADS descriptors generally increased when AI-CAD was used (κ=0.29-0.63 to 0.35-0.73). Inexperienced radiologists tended to concede to AI-CAD results more easily than experienced radiologists, especially in independent reading (P<0.001). Conversion rates for final assessment changes from BI-RADS 2 or 3 to BI-RADS higher than 4a or vice versa were also significantly higher in independent reading than sequential reading (overall: 15.8% and 6.2%, respectively, P<0.001) for both inexperienced and experienced radiologists. Conclusions: Using AI-CAD to interpret breast US improves the specificity, PPV and accuracy of radiologists regardless of experience level. AI-CAD may work better in independent reading to improve diagnostic performance and agreements between radiologists, especially for inexperienced radiologists.Trial registration: retrospectively registered