Intelligent multi-modal shear wave elastography to reduce unnecessary biopsies in breast cancer diagnosis (INSPiRED 002): a retrospective, international, multicentre analysis. (December 2022)

• Record Type: Journal Article
• Authors: Pfob, André; Sidey-Gibbons, Chris; Barr, Richard G.; Duda, Volker; Alwafai, Zaher; Balleyguier, Corinne; Clevert, Dirk-André; Fastner, Sarah; Gomez, Christina; Goncalo, Manuela; Gruber, Ines; Hahn, Markus; Hennigs, André; Kapetas, Panagiotis; Lu, Sheng-Chieh; Nees, Juliane; Ohlinger, Ralf; Riedel, Fabian; Rutten, Matthieu; Schaefgen, Benedikt; Stieber, Anne; Togawa, Riku; Tozaki, Mitsuhiro; Wojcinski, Sebastian; Xu, Cai; Rauch, Geraldine; Heil, Joerg; Golatta, Michael
• Is Part Of: European journal of cancer. Volume 177(2022)
• Page Start: 1
• Page End: 14
• Publication Date: 2022-12
• Subjects: Breast cancer -- Breast imaging -- Machine learning -- Artificial intelligence -- Elastography; ACR American College of Radiology -- BI-RADS Breast Imaging Reporting and Data System -- CI confidence interval -- AUC area under the curve -- ROC receiver-operating characteristic -- ML machine learning -- LR logistic regression; Cancer -- Periodicals; Neoplasms -- Periodicals; Cancer -- Périodiques; Cancer; Tumors; Electronic journals; Periodicals; Electronic journals; 616.994
• DOI: 10.1016/j.ejca.2022.09.018
• Languages: English
• ISSNs: 0959-8049

Abstract

Abstract: Background: Breast ultrasound identifies additional carcinomas not detected in mammography but has a higher rate of false-positive findings. We evaluated whether use of intelligent multi-modal shear wave elastography (SWE) can reduce the number of unnecessary biopsies without impairing the breast cancer detection rate. Methods: We trained, tested, and validated machine learning algorithms using SWE, clinical, and patient information to classify breast masses. We used data from 857 women who underwent B-mode breast ultrasound, SWE, and subsequent histopathologic evaluation at 12 study sites in seven countries from 2016 to 2019. Algorithms were trained and tested on data from 11 of the 12 sites and externally validated using the additional site's data. We compared findings to the histopathologic evaluation and compared the diagnostic performance between B-mode breast ultrasound, traditional SWE, and intelligent multi-modal SWE. Results: In the external validation set (n = 285), intelligent multi-modal SWE showed a sensitivity of 100% (95% CI, 97.1–100%, 126 of 126), a specificity of 50.3% (95% CI, 42.3–58.3%, 80 of 159), and an area under the curve of 0.93 (95% CI, 0.90–0.96). Diagnostic performance was significantly higher compared to traditional SWE and B-mode breast ultrasound ( P < 0.001). Unlike traditional SWE, positive-predictive values of intelligent multi-modal SWE were significantly higher compared to B-mode breast ultrasound. Unnecessary biopsies were reduced by 50.3% (79 versus 159, P < 0.001) without missing cancer compared to B-mode ultrasound. Conclusion: The majority of unnecessary breast biopsies might be safely avoided by using intelligent multi-modal SWE. These results may be helpful to reduce diagnostic burden for patients, providers, and healthcare systems. Highlights: Breast ultrasound results in false-positive findings causing unnecessary biopsies. We developed and tested an intelligent multi-modal shear wave elastography algorithm. Performance was higher compared to breast ultrasound and traditional elastography. Unnecessary biopsies were significantly reduced by 50.3% with 0% undetected malignancies. Prospective validation of the algorithm in a diverse setting seems warranted.