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

Reliable classification of benign and malignant lesions in breast ultrasoundimages can provide an effective and relatively low cost method for earlydiagnosis of breast cancer. The accuracy of the diagnosis is however highlydependent on the quality of the ultrasound systems and the experience of theusers (radiologists). The leverage in deep convolutional neural networkapproaches provided solutions in efficient analysis of breast ultrasoundimages. In this study, we proposed a new framework for classification of breastcancer lesions by use of an attention module in modified VGG16 architecture. Wealso proposed new ensembled loss function which is the combination of binarycross-entropy and logarithm of the hyperbolic cosine loss to improve the modeldiscrepancy between classified lesions and its labels. Networks trained frompretrained ImageNet weights, and subsequently fine-tuned with ultrasounddatasets. The proposed model in this study outperformed other modified VGG16architectures with the accuracy of 93% and also the results are competitivewith other state of the art frameworks for classification of breast cancerlesions. In this study, we employed transfer learning approaches with thepre-trained VGG16 architecture. Different CNN models for classification taskwere trained to predict benign or malignant lesions in breast ultrasoundimages. Our Experimental results show that the choice of loss function ishighly important in classification task and by adding an attention block wecould empower the performance our model.

Classification of Breast Cancer Lesions in Ultrasound Images by using Attention Layer and loss Ensembles in Deep Convolutional Neural Networks