Authors: Wei-Chung Shia, Yu-Len Huang, Yi-Chun Chen, Hwa-Koon Wu, Dar-Ren Chen

Published on: April 16, 2024

Impact Score: 7.2

Arxiv code: Arxiv:2404.10600

Summary

• What is new: The study introduces a new intra-operative tumour margin evaluation using specimen mammography combined with deep learning.
• Why this is important: Reducing the occurrence of positive margins in breast-conserving surgery to lower the risk of local recurrences.
• What the research proposes: An image thresholding and deep learning model (SegNet) based method for real-time, intra-operative evaluation of tumour margins.
• Results: The method showed a promising average difference (6.53 mm +- 5.84) when comparing the evaluated margins with manual sketches by physicians, indicating potential for accurate intra-operative margin detection.

Technical Details

Technological frameworks used: SegNet

Models used: Deep Learning for Image Segmentation

Data used: Specimen mammography images from 30 cases

Potential Impact

Healthcare and surgical equipment companies, especially those specializing in cancer surgery technologies, could benefit from integrating or adopting this imaging and analysis technology.

Want to implement this idea in a business?

We have generated a startup concept here: MarginScan.