DermX: An end-to-end framework for explainable automated dermatological diagnosis
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Dokumenter
- Fulltext
Forlagets udgivne version, 3,16 MB, PDF-dokument
Dermatological diagnosis automation is essential in addressing the high prevalence of skin diseases and critical shortage of dermatologists. Despite approaching expert-level diagnosis performance, convolutional neural network (ConvNet) adoption in clinical practice is impeded by their limited explainability, and by subjective, expensive explainability validations. We introduce DermX, an end-to-end framework for explainable automated dermatological diagnosis. DermX is a clinically-inspired explainable dermatological diagnosis ConvNet, trained using DermXDB, a 554 image dataset annotated by eight dermatologists with diagnoses, supporting explanations, and explanation attention maps. DermX+ extends DermX with guided attention training for explanation attention maps. Both methods achieve near-expert diagnosis performance, with DermX, DermX+, and dermatologist F1 scores of 0.79, 0.79, and 0.87, respectively. We assess the explanation performance in terms of identification and localization by comparing model-selected with dermatologist-selected explanations, and gradient-weighted class-activation maps with dermatologist explanation maps, respectively. DermX obtained an identification F1 score of 0.77, while DermX+ obtained 0.79. The localization F1 score is 0.39 for DermX and 0.35 for DermX+. These results show that explainability does not necessarily come at the expense of predictive power, as our high-performance models provide expert-inspired explanations for their diagnoses without lowering their diagnosis performance.
Originalsprog | Engelsk |
---|---|
Artikelnummer | 102647 |
Tidsskrift | Medical Image Analysis |
Vol/bind | 83 |
Antal sider | 12 |
ISSN | 1361-8415 |
DOI | |
Status | Udgivet - 2023 |
Bibliografisk note
Funding Information:
Raluca Jalaboi’s work was supported in part by the Danish Innovation Fund, Denmark under Grant 0153-00154 A . Ole Winther’s work was funded in part by the Novo Nordisk Foundation, Denmark through the Center for Basic Machine Learning Research in Life Science ( NNF20OC0062606 ). Ole Winther acknowledges supporting the Pioneer Centre for AI, DNRF, Denmark grant number P1 .
Publisher Copyright:
© 2022 The Author(s)
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
ID: 327786747