This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of an artificial intelligence (AI) system component for healthcare. The system explains decisions made by deep learning networks analyzing images of skin lesions. The co-design of trustworthy AI developed here used a holistic approach rather than a static ethical checklist and required a multidisciplinary team of experts working with the AI designers and their managers. Ethical, legal, and technical issues potentially arising from the future use of the AI system were investigated. This paper is a first report on co-designing in the early design phase. Our results can also serve as guidance for other early-phase AI-similar tool developments.
Zusammenfassung Hintergrund Seit 2017 berichten Wissenschafts- und Populärmedien immer wieder von bildanalytischen Verfahren der künstlichen Intelligenz, die in der medizinischen Diagnostik zu menschlichen Experten vergleichbar gute Resultate erzielen. Mit der erstmaligen Zulassung eines solchen Systems durch die amerikanische Arzneimittelbehörde 2018 begann ihr Einzug in den klinischen Alltag. Fragestellung Dieser Beitrag gibt einen Überblick der wichtigsten Entwicklungen der künstlichen Intelligenz für bildanalytische Verfahren in klinischen Anwendungen mit Fokus auf die Dermatologie. Material und Methode Am Beispiel der ImageNet Challenge wird gezeigt, dass klassische Ansätze des maschinellen Lernens stark auf menschlicher Expertise beruhten und dass ihre Performance und Skalierbarkeit praktischen Anforderungen nicht genügen konnten. Mittels Deep Learning, einem auf neuronalen Netzen beruhenden Verfahren, konnten diese Limitierungen und insbesondere die Abhängigkeit von menschlicher Expertise überwunden werden. Wir beschreiben wichtige Eigenschaften von Deep Learning, den methodischen Durchbruch von Transfer Learning und berichten über vielversprechende Entwicklungen hin zu generativen Modellen. Ergebnisse Mittels Deep Learning erreichen bildanalytische Verfahren in vielen Fällen die für den industriellen und klinischen Einsatz geforderte Genauigkeit. Zudem gestaltet sich ihre Industrialisierung weitestgehend barrierefrei. Derzeitige Entwicklungen fokussieren sich daher weniger auf die nochmalige Verbesserung der Genauigkeit, sondern nehmen sich den Herausforderungen der Interpretierbarkeit und Anwendbarkeit unter Alltagsbedingungen an. Durch die Weiterentwicklung zu generativen Modellen werden gänzlich neuartige Anwendungen möglich. Schlussfolgerungen Deep Learning hat in vielerlei Hinsicht beeindruckende Erfolge vorzuweisen und gilt heute nicht nur in der Bildanalyse als das Standardverfahren schlechthin. Dieser Durchbruch der künstlichen Intelligenz ermöglicht eine rasch anwachsende Zahl von klinischen Anwendungen und entwickelt sich fortwährend zu einem unverzichtbaren Werkzeug in der modernen Medizin.
Background The exact location of skin lesions is key in clinical dermatology. On one hand, it supports differential diagnosis (DD) since most skin conditions have specific predilection sites. On the other hand, location matters for dermatosurgical interventions. In practice, lesion evaluation is not well standardized and anatomical descriptions vary or lack altogether. Automated determination of anatomical location could benefit both situations.Objective Establish an automated method to determine anatomical regions in clinical patient pictures and evaluate the gain in DD performance of a deep learning model (DLM) when trained with lesion locations and images.Methods Retrospective study based on three datasets: macro-anatomy for the main body regions with 6000 patient pictures partially labelled by a student, micro-anatomy for the ear region with 182 pictures labelled by a student and DD with 3347 pictures of 16 diseases determined by dermatologists in clinical settings. For each dataset, a DLM was trained and evaluated on an independent test set. The primary outcome measures were the precision and sensitivity with 95% CI. For DD, we compared the performance of a DLM trained with lesion pictures only with a DLM trained with both pictures and locations. ResultsThe average precision and sensitivity were 85% (CI 84-86), 84% (CI 83-85) for macro-anatomy, 81% (CI 80-83), 80% (CI 77-83) for micro-anatomy and 82% (CI 78-85), 81% (CI 77-84) for DD. We observed an improvement in DD performance of 6% (McNemar test P-value 0.0009) for both average precision and sensitivity when training with both lesion pictures and locations.Conclusion Including location can be beneficial for DD DLM performance. The proposed method can generate body region maps from patient pictures and even reach surgery relevant anatomical precision, e.g. the ear region. Our method enables automated search of large clinical databases and make targeted anatomical image retrieval possible.
Objectives: Pustular psoriasis (PP) is one of the most severe and chronic skin conditions. Its treatment is difficult, and measurements of its severity are highly dependent on clinicians’ experience. Pustules and brown spots are the main efflorescences of the disease and directly correlate with its activity. We propose an automated deep learning model (DLM) to quantify lesions in terms of count and surface percentage from patient photographs. Methods: In this retrospective study, two dermatologists and a student labeled 151 photographs of PP patients for pustules and brown spots. The DLM was trained and validated with 121 photographs, keeping 30 photographs as a test set to assess the DLM performance on unseen data. We also evaluated our DLM on 213 unstandardized, out-of-distribution photographs of various pustular disorders (referred to as the pustular set), which were ranked from 0 (no disease) to 4 (very severe) by one dermatologist for disease severity. The agreement between the DLM predictions and experts’ labels was evaluated with the intraclass correlation coefficient (ICC) for the test set and Spearman correlation (SC) coefficient for the pustular set. Results: On the test set, the DLM achieved an ICC of 0.97 (95% confidence interval [CI], 0.97–0.98) for count and 0.93 (95% CI, 0.92–0.94) for surface percentage. On the pustular set, the DLM reached a SC coefficient of 0.66 (95% CI, 0.60–0.74) for count and 0.80 (95% CI, 0.75–0.83) for surface percentage. Conclusions: The proposed method quantifies efflorescences from PP photographs reliably and automatically, enabling a precise and objective evaluation of disease activity.
Hand eczema (HE), also called hand dermatitis, is an inflammatory disease, often chronic, causing a wide spectrum of symptoms including redness (erythema), scaling, hyperkeratosis, fissures, vesicles and erosions. 1 All these features are visible on digital pictures. It is one of the most frequent dermatoses with 15% life prevalence and 10% 1-year prevalence in the general population. It has a multifactorial aetiology including both environmental and genetic factors. 2 HE severity range spans from mild to severe cases, the latter causing adverse physical and psychological effects, both in private and professional activities, and significant impairment to patients' quality
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.