Document Type


Publication Date



Shuo Wang, Sihua Niu, Enze Qu, Flemming Forsberg, Annina Wilkes, Alexander Sevrukov, Kibo Nam, Robert F. Mattrey, Haydee Ojeda-Fournier, and John R. Eisenbrey "Characterization of indeterminate breast lesions on B-mode ultrasound using automated machine learning models," Journal of Medical Imaging 7(5), 057002 (23 October 2020).

Copyright 2020 Society of Photo‑Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited.


Purpose: While mammography has excellent sensitivity for the detection of breast lesions, its specificity is limited. Adjunct screening with ultrasound may partially alleviate this issue, but also increases false positives, resulting in unnecessary biopsies. This study investigated the use of Google AutoML Vision (Mountain View, CA), a commercially available machine learning service, to both identify and characterize indeterminate breast lesions on ultrasound.

Methods: B-mode images from 253 independent cases of indeterminate breast lesions scheduled for core biopsy were used for model creation and validation. The performances of two sub-models from AutoML Vision, the image classification model and object detection model were evaluated, while also investigating training strategies to enhance model performances. Pathology from the patient’s biopsy were used as a reference standard.

Results: The image classification models trained under different conditions demonstrated areas under the precision recall curve (AUC) ranging from 0.85 to 0.96 during internal validation. Once deployed, the model with highest internal performance demonstrated a sensitivity of 100% (95% confidence interval (CI) of 73.5-100%), specificity of 83.3% (CI=51.6-97.9%), positive predictive value (PPV) of 85.7% (CI=62.9-95.5%), and negative predictive value (NPV) of 100% (CI non-evaluable) in an independent dataset. The object detection model demonstrated lower performance internally during development (AUC=0.67) and during prediction in the independent dataset (sensitivity=75.0% (CI=42.8-94.5), specificity=80.0% (CI=51.9-95.7), PPV=75.0% (CI=50.8-90.0), NPV=80.0% (CI=59.3-91.7%)), but was able to demonstrate the location of the lesion within the image.

Conclusions: Two models appear to be useful tools for identifying and classifying suspicious areas on B-mode images of indeterminate breast lesions.



Included in

Radiology Commons