Authors: MingXuan Xiao, Yufeng Li, Xu Yan, Min Gao, Weimin Wang

Published on: April 12, 2024

Impact Score: 7.8

Arxiv code: Arxiv:2404.08279

Summary

• What is new: An approach utilizing convolutional neural networks (CNNs) with the Inceptionv3 architecture for rapid and automatic classification of breast pathological images
• Why this is important: The dependence on pathologists’ expertise and the time-consuming process of accurately classifying breast pathological images
• What the research proposes: Employing a CNN model leveraging Inceptionv3 architecture and transfer learning to quickly categorize pathological images into benign and malignant
• Results: Achieved classification accuracy rates surpassing 0.92 across all magnification levels on the BreaKHis dataset

Technical Details

Technological frameworks used: Convolutional Neural Networks (CNNs), Inceptionv3, Transfer Learning

Models used: Inceptionv3

Data used: BreaKHis public dataset

Potential Impact

Healthcare diagnostics, companies developing diagnostic tools, and digital pathology platforms

Want to implement this idea in a business?

We have generated a startup concept here: PathoPrecision.