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

Interpretability is a key factor in the design of automatic classifiers formedical diagnosis. Deep learning models have been proven to be a very effectiveclassification algorithm when trained in a supervised way with enough data. Themain concern is the difficulty of inferring rationale interpretations fromthem. Different attempts have been done in last years in order to convert deeplearning classifiers from high confidence statistical black box machines intoself-explanatory models. In this paper we go forward into the generation ofexplanations by identifying the independent causes that use a deep learningmodel for classifying an image into a certain class. We use a combination ofIndependent Component Analysis with a Score Visualization technique. In thispaper we study the medical problem of classifying an eye fundus image into 5levels of Diabetic Retinopathy. We conclude that only 3 independent componentsare enough for the differentiation and correct classification between the 5disease standard classes. We propose a method for visualizing them anddetecting lesions from the generated visual maps.

Identification and Visualization of the Underlying Independent Causes of the Diagnostic of Diabetic Retinopathy made by a Deep Learning Classifier