@ARTICLE{ iet:/content/journals/10.1049/iet-cvi.2018.5243, author = {Antonia Creswell}, author = {Alison Pouplin}, author = {Anil A. Bharath}, keywords = {denoising components;skin lesions;vast amounts;classifying medical images;unlabelled data;deep learning model;unlabelled medical data;model yields superior classification performance;specific case;labelled data;adversarial autoencoder;learned representation;labelled training data;class labels;}, ISSN = {1751-9632}, language = {English}, abstract = {The authors propose a novel deep learning model for classifying medical images in the setting where there is a large amount of unlabelled medical data available, but the amount of labelled data is limited. They consider the specific case of classifying skin lesions as either benign or malignant. In this setting, the authors’ proposed approach – the semi-supervised, denoising adversarial autoencoder – is able to utilise vast amounts of unlabelled data to learn a representation for skin lesions, and small amounts of labelled data to assign class labels based on the learned representation. They perform an ablation study to analyse the contributions of both the adversarial and denoising components and compare their work with state-of-the-art results. They find that their model yields superior classification performance, especially when evaluating their model at high sensitivity values.}, title = {Denoising adversarial autoencoders: classifying skin lesions using limited labelled training data}, journal = {IET Computer Vision}, issue = {8}, volume = {12}, year = {2018}, month = {December}, pages = {1105-1111(6)}, publisher ={Institution of Engineering and Technology}, copyright = {© The Institution of Engineering and Technology}, url = {https://digital-library.theiet.org/;jsessionid=1qm5tnt8q64lc.x-iet-live-01content/journals/10.1049/iet-cvi.2018.5243} }