MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1038/s41598-026-53468-6

Медицинская библиотека · Scientific reports · 2026

Photoacoustic device fingerprints induce bias in deep learning models.

Bender Christoph J, Knopp Marcel, Holzwarth Niklas, Rix Tom, Nölke Jan-Hinrich, Dreher Kris K, Li Yi, Kempf Julius, Caranovic Milenko, Schneider Fabian, Schellenberg Melanie, Boland Leonie, Haney Briain, Knieling Ferdinand, Rother Ulrich, Seitel Alexander, Maier-Hein Lena

СтатьяПеревод в очереди

Аннотация

Deep learning (DL) models developed for established medical imaging modalities have shown increasing performance and reliability as a result of scaling efforts. In contrast, model development for emerging modalities such as photoacoustic imaging (PAI) remains challenged by data sparsity, which limits model generalizability and raises the susceptibility to bias. While recent studies in PAI have started to investigate subject-related confounders, the impact of hardware-related confounders remains unexplored, posing a critical risk for failure in multicentric deployment scenarios. We are the first to provide a multicentric analysis of hardware-induced bias in PAI. We analyzed device-specific characteristics in images from four device instances and two peripheral artery disease studies, and trained DL models to classify device origin and disease under varying levels of device-health correlations in the data. We showed that 1) multiple instances of the same PAI device type embed identifiable fingerprints in the images, 2) that DL models can leverage these fingerprints to reach [Formula: see text] accuracy in device detection and critically, 3) when a correlation between device instance and health status is present, models trained for disease diagnosis exploit these device-specific signatures as shortcuts, thereby producing biased and clinically misleading predictions. This research highlights the risk of overestimating algorithm performance when such confounding is overlooked, emphasizing the importance of bias evaluation and explainable artificial intelligence methods to identify potential shortcuts, finally enabling multicentric PAI studies.

Для цитирования: Bender Christoph J, Knopp Marcel, Holzwarth Niklas, Rix Tom, Nölke Jan-Hinrich, Dreher Kris K, Li Yi, Kempf Julius, Caranovic Milenko, Schneider Fabian, Schellenberg Melanie, Boland Leonie, Haney Briain, Knieling Ferdinand, Rother Ulrich, Seitel Alexander, Maier-Hein Lena. Photoacoustic device fingerprints induce bias in deep learning models.. Scientific reports. 2026. DOI: 10.1038/s41598-026-53468-6.

Предметные рубрики MeSH

Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.