Buchumschlag

Reconstruction of patient-specific confounders in AI-based radiologic image interpretation using generative pretraining

Reliably detecting potentially misleading patterns in automated diagnostic assistance systems, such as those powered by artificial intelligence (AI), is crucial for instilling user trust and ensuring reliability. Current techniques fall short in visualizing such confounding factors. We propose DiffC...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Han, Tianyu (VerfasserIn) , Žigutytė, Laura (VerfasserIn) , Huck, Luisa (VerfasserIn) , Huppertz, Marc Sebastian (VerfasserIn) , Siepmann, Robert (VerfasserIn) , Gandelsman, Yossi (VerfasserIn) , Blüthgen, Christian (VerfasserIn) , Khader, Firas (VerfasserIn) , Kuhl, Christiane (VerfasserIn) , Nebelung, Sven (VerfasserIn) , Kather, Jakob Nikolas (VerfasserIn) , Truhn, Daniel (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 17 September 2024
In: Cell reports. Medicine
Year: 2024, Jahrgang: 5, Heft: 9, Pages: 1-11
ISSN:2666-3791
DOI:10.1016/j.xcrm.2024.101713
Online-Zugang:Verlag, kostenfrei, Volltext: https://doi.org/10.1016/j.xcrm.2024.101713
Verlag, kostenfrei, Volltext: https://www.sciencedirect.com/science/article/pii/S2666379124004348
Volltext
Verfasserangaben:Tianyu Han, Laura Žigutytė, Luisa Huck, Marc Sebastian Huppertz, Robert Siepmann, Yossi Gandelsman, Christian Blüthgen, Firas Khader, Christiane Kuhl, Sven Nebelung, Jakob Nikolas Kather, Daniel Truhn
Beschreibung
Zusammenfassung:Reliably detecting potentially misleading patterns in automated diagnostic assistance systems, such as those powered by artificial intelligence (AI), is crucial for instilling user trust and ensuring reliability. Current techniques fall short in visualizing such confounding factors. We propose DiffChest, a self-conditioned diffusion model trained on 515,704 chest radiographs from 194,956 patients across the US and Europe. DiffChest provides patient-specific explanations and visualizes confounding factors that might mislead the model. The high inter-reader agreement, with Fleiss’ kappa values of 0.8 or higher, validates its capability to identify treatment-related confounders. Confounders are accurately detected with 10%-100% prevalence rates. The pretraining process optimizes the model for relevant imaging information, resulting in excellent diagnostic accuracy for 11 chest conditions, including pleural effusion and heart insufficiency. Our findings highlight the potential of diffusion models in medical image classification, providing insights into confounding factors and enhancing model robustness and reliability.
Beschreibung:Gesehen am 16.04.2025
Beschreibung:Online Resource
ISSN:2666-3791
DOI:10.1016/j.xcrm.2024.101713

Ähnliche Einträge