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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Being able to explain the prediction to clinical end-users is a necessity toleverage the power of artificial intelligence (AI) models for clinical decisionsupport. For medical images, a feature attribution map, or heatmap, is the mostcommon form of explanation that highlights important features for AI models'prediction. However, it is unknown how well heatmaps perform on explainingdecisions on multi-modal medical images, where each image modality or channelvisualizes distinct clinical information of the same underlying biomedicalphenomenon. Understanding such modality-dependent features is essential forclinical users' interpretation of AI decisions. To tackle this clinicallyimportant but technically ignored problem, we propose the modality-specificfeature importance (MSFI) metric. It encodes clinical image and explanationinterpretation patterns of modality prioritization and modality-specificfeature localization. We conduct a clinical requirement-grounded, systematicevaluation using computational methods and a clinician user study. Results showthat the examined 16 heatmap algorithms failed to fulfill clinical requirementsto correctly indicate AI model decision process or decision quality. Theevaluation and MSFI metric can guide the design and selection of XAI algorithmsto meet clinical requirements on multi-modal explanation.

Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?