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

Artificial Intelligence has emerged as a useful aid in numerous clinicalapplications for diagnosis and treatment decisions. Deep neural networks haveshown same or better performance than clinicians in many tasks owing to therapid increase in the available data and computational power. In order toconform to the principles of trustworthy AI, it is essential that the AI systembe transparent, robust, fair and ensure accountability. Current deep neuralsolutions are referred to as black-boxes due to a lack of understanding of thespecifics concerning the decision making process. Therefore, there is a need toensure interpretability of deep neural networks before they can be incorporatedin the routine clinical workflow. In this narrative review, we utilizedsystematic keyword searches and domain expertise to identify nine differenttypes of interpretability methods that have been used for understanding deeplearning models for medical image analysis applications based on the type ofgenerated explanations and technical similarities. Furthermore, we report theprogress made towards evaluating the explanations produced by variousinterpretability methods. Finally we discuss limitations, provide guidelinesfor using interpretability methods and future directions concerning theinterpretability of deep neural networks for medical imaging analysis.

Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods