Medical Professional Enhancement Using Explainable Artificial Intelligence in Fetal Cardiac Ultrasound Screening.

ABSTRACT: Diagnostic support tools based on artificial intelligence (AI) have exhibited high performance in various medical fields. However, their clinical application remains challenging because of the lack of explanatory power in AI decisions (black box problem), making it difficult to build trust with medical professionals. Nevertheless, visualizing the internal representation of deep neural networks will increase explanatory power and improve the confidence of medical professionals in AI decisions. We propose a novel deep learning-based explainable representation "graph chart diagram" to support fetal cardiac ultrasound screening, which has low detection rates of congenital heart diseases due to the difficulty in mastering the technique. Screening performance improves using this representation f

SUBMITTER: Sakai A 

PROVIDER: S-EPMC8945208 | biostudies-literature | 2022 Feb

REPOSITORIES: biostudies-literature