Deep learning for improved breast cancer monitoring using a portable ultrasound scanner
Insight
SEPTEMBER 20, 2019
The model was a modified U-Net and trained on GPU hosted by Amazon Web Services (AWS) EC2 instances. The model is optimized for recall in order to reduce the false negative. In order to reduce cost, combining the device and the mode can reduce the manual process involved. The testing accuracy of the model is 0.79 on test data.
Let's personalize your content