AUTHOR=To Tyrell , Lu Tongtong , Jorns Julie M. , Patton Mollie , Schmidt Taly Gilat , Yen Tina , Yu Bing , Ye Dong Hye 

TITLE=Deep learning classification of deep ultraviolet fluorescence images toward intra-operative margin assessment in breast cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1179025

DOI=10.3389/fonc.2023.1179025

ISSN=2234-943X

ABSTRACT=Breast-conserving surgery is aimed at removing all cancerous cells while minimizing the loss of healthy tissue. To ensure a balance between the complete resection of cancer and the preservation of healthy tissue, it is necessary to assess the margins of the removed specimen during the operation. Deep ultraviolet (DUV) fluorescence scanning microscopy provides rapid whole-surface imaging (WSI) of resected tissues with significant contrast between malignant and normal tissue. Intraoperative margin assessment with DUV images would benefit from an automated breast cancer classification method. Deep learning has shown promising results in breast cancer classification, but the limited DUV image dataset presents the challenge of overfitting to training a robust network. To address this challenge, we split the DUV-WSI images into small patches and use them to train a convolutional neural network for patch-level classification. We then use an ensemble learning approach that merges patch-level classification results and regional importance to determine the margin status. Our proposed method outperforms the standard deep-learning classification methods on 60 DUV breast surgical samples. The results suggest that it can be used to improve classification performance and identify cancerous regions more effectively.