Assisted deep learning framework for multi-class skin lesion classification considering a binary classification support. (September 2020)

• Record Type: Journal Article
• Authors: Harangi, Balazs; Baran, Agnes; Hajdu, Andras
• Is Part Of: Biomedical signal processing and control. Volume 62(2020)
• Publication Date: 2020-09
• Subjects: Assisted learning -- Deep learning -- Ensemble learning -- Skin lesion; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2020.102041
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Highlights: We propose a CNN framework to classify dermoscopy images into seven classes. We take the advantage that these classes can be merged into two ones. We used the confidences of the binary classification to tune the multi-classes. We define a fusion layer which merges the involved neural networks. Our ensemble outperforms the accuracy of the individual CNNs. Abstract: In this paper, we propose a deep convolutional neural network framework to classify dermoscopy images into seven classes. With taking the advantage that these classes can be merged into two (healthy/diseased) ones we can train a part of the network regarding this binary task only. Then, the confidences regarding the binary classification are used to tune the multi-class confidence values provided by the other part of the network, since the binary task can be solved more accurately. For both the classification tasks we used GoogLeNet Inception-v3, however, any CNN architectures could be applied for these purposes. The whole network is trained in the usual way, and as our experimental results on the skin lesion image classification show, the accuracy of the multi-class problem has been remarkably raised (by 7% considering the balanced multi-class accuracy) via embedding the more reliable binary classification outcomes.