A Deep Learning Framework for Breast Tumor Detection and Localization from Microwave Imaging Data

Breast Microwave Imaging (BMI) has emerged as a viable alternative to conventional breast cancer screening techniques due to its favorable features and a higher rate of detection. This paper presents a deep learning framework consisting of deep neural networks with convolutional layers to facilitate the process of tumor detection, localization, and characterization from scattering parameter measurements and metadata features. The developed deep learning framework outperforms other techniques in the literature in terms of detection accuracy, tumor localization, and characterization. The promising results of this paper demonstrate the potential and benefits of performing BMI via deep neural networks trained on practical scattering parameter measurements.

Published in: 2021 28th IEEE International Conference on Electronics, Circuits, and Systems (ICECS)

Link on IEEE

Link on ResearchGate

Download the paper.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

Create a website or blog at WordPress.com

Up ↑

%d bloggers like this: