Deep Learning Model for Breast Shear Wave Elastography to Improve Breast Cancer Diagnosis (INSPiRED 006): An International, Multicenter Analysis.
Authors
Affiliations (17)
Affiliations (17)
- Department of Obstetrics and Gynecology, Heidelberg University Hospital, Heidelberg, Germany.
- National Center for Tumor Diseases (NCT) and German Cancer Research Center (DKFZ), Heidelberg, Germany.
- Breast Center Heidelberg, Hospital St Elisabeth, Heidelberg, Germany.
- Department of Radiology, Northeast Ohio Medical University, Ravenna, OH.
- Department of Gynecology and Obstetrics, University of Marburg, Marburg, Germany.
- Department of Gynecology and Obstetrics, University of Greifswald, Greifswald, Germany.
- Department of Radiology, Institut Gustave Roussy, Villejuif Cedex, France.
- Department of Radiology, University Hospital Munich-Grosshadern, Munich, Germany.
- Department of Radiology, University of Coimbra, Coimbra, Portugal.
- Department of Gynecology and Obstetrics, University of Tuebingen, Tuebingen, Germany.
- Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria.
- Breast Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer, New York, NY.
- Department of Radiology, Jeroen Bosch Hospital, 's-Hertogenbosch, the Netherlands.
- Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands.
- Health AI Innovation, Oracle Corporation, Austin, TX.
- Department of Radiology, Sagara Hospital, Kagoshima, Japan.
- Department of Gynecology and Obstetrics, Breast Cancer Center, Klinikum Bielefeld, Bielefeld, Germany.
Abstract
Shear wave elastography (SWE) has been investigated as a complement to B-mode ultrasound for breast cancer diagnosis. Although multicenter trials suggest benefits for patients with Breast Imaging Reporting and Data System (BI-RADS) 4(a) breast masses, widespread adoption remains limited because of the absence of validated velocity thresholds. This study aims to develop and validate a deep learning (DL) model using SWE images (artificial intelligence [AI]-SWE) for BI-RADS 3 and 4 breast masses and compare its performance with human experts using B-mode ultrasound. We used data from an international, multicenter trial (ClinicalTrials.gov identifier: NCT02638935) evaluating SWE in women with BI-RADS 3 or 4 breast masses across 12 institutions in seven countries. Images from 11 sites were used to develop an EfficientNetB1-based DL model. An external validation was conducted using data from the 12th site. Another validation was performed using the latest SWE software from a separate institutional cohort. Performance metrics included sensitivity, specificity, false-positive reduction, and area under the receiver operator curve (AUROC). The development set included 924 patients (4,026 images); the external validation sets included 194 patients (562 images) and 176 patients (188 images, latest SWE software). AI-SWE achieved an AUROC of 0.94 (95% CI, 0.91 to 0.96) and 0.93 (95% CI, 0.88 to 0.98) in the two external validation sets. Compared with B-mode ultrasound, AI-SWE significantly reduced false-positive rates by 62.1% (20.4% [30/147] <i>v</i> 53.8% [431/801]; <i>P</i> < .001) and 38.1% (33.3% [14/42] <i>v</i> 53.8% [431/801]; <i>P</i> < .001), with comparable sensitivity (97.9% [46/47] and 97.8% [131/134] <i>v</i> 98.1% [311/317]; <i>P</i> = .912 and <i>P</i> = .810). AI-SWE demonstrated accuracy comparable with human experts in malignancy detection while significantly reducing false-positive imaging findings (ie, unnecessary biopsies). Future studies should explore its integration into multimodal breast cancer diagnostics.