English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Computer assisted diagnosis in digital pathology is becoming ubiquitous as itcan provide more efficient and objective healthcare diagnostics. Recentadvances have shown that the convolutional Neural Network (CNN) architectures,a well-established deep learning paradigm, can be used to design a ComputerAided Diagnostic (CAD) System for breast cancer detection. However, thechallenges due to stain variability and the effect of stain normalization withsuch deep learning frameworks are yet to be well explored. Moreover,performance analysis with arguably more efficient network models, which may beimportant for high throughput screening, is also not well explored.To addressthis challenge, we consider some contemporary CNN models for binaryclassification of breast histopathology images that involves (1) the datapreprocessing with stain normalized images using an adaptive colourdeconvolution (ACD) based color normalization algorithm to handle the stainvariabilities; and (2) applying transfer learning based training of somearguably more efficient CNN models, namely Visual Geometry Group Network(VGG16), MobileNet and EfficientNet. We have validated the trained CNN networkson a publicly available BreaKHis dataset, for 200x and 400x magnifiedhistopathology images. The experimental analysis shows that pretrained networksin most cases yield better quality results on data augmented breasthistopathology images with stain normalization, than the case without stainnormalization. Further, we evaluated the performance and efficiency of popularlightweight networks using stain normalized images and found that EfficientNetoutperforms VGG16 and MobileNet in terms of test accuracy and F1 Score. Weobserved that efficiency in terms of test time is better in EfficientNet thanother networks; VGG Net, MobileNet, without much drop in the classificationaccuracy.

Stain Normalized Breast Histopathology Image Recognition using Convolutional Neural Networks for Cancer Detection