Automated assessment of breast cancer margin in optical coherence tomography images via pretrained convolutional neural network

Among women, breast cancer is the second leading cause of cancer in the developing countries. The gold standard method for the evaluation of breast cancer detection involves microscopic testing of a hematoxylin and eosin (H&E) ‐stained tissue biopsy. In our study, we propose a pretrained Inception‐v3 convolutional neural network (CNN) with reverse active learning for the classification of healthy and malignancy breast tissue using optical coherence tomography (OCT) images. The present method will be helpful for real‐ time, rapid, in‐vivo, intra‐operative margin assessment over large surface areas while preserving tissue structure. The benchmark method for the evaluation of breast cancers involves microscopic testing of a hematoxylin and eosin (H&E) ‐stained tissue biopsy. Resurgery is required in 20% to 30% of cases because of incomplete excision of malignant tissues. Therefore, a more accurate method is required to detect the cancer margin to avoid the risk of recurrence. In the recent years, convolutional neural networks (CNNs) has achieve d excellent performance in the field of medical images diagnosis. It automatically extracts the features from the images and classifies them. In the proposed study, we apply a pretrained Inception‐v3 CNN with reverse active learning for the classification of healthy and malignancy breast tissue us ing optical coherence tomography (OCT) images. This proposed method attained the sensitivity, specificity and accuracy is 90.2%, ...
Source: Journal of Biophotonics - Category: Physics Authors: Tags: FULL ARTICLE Source Type: research