Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 16, 2026

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

Photoacoustic device fingerprints induce bias in deep learning models.

Christoph J Bender^1,2, Marcel Knopp^3,4, Niklas Holzwarth^3,4

¹Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany. christophjulien.bender@dkfz-heidelberg.de.

Scientific Reports

|June 13, 2026

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

What is at stake in genetic newborn screening for rare diseases? - An exploratory qualitative study of parents' and expectant parents' concerns in the Screen4Care project.

Public health genomics·2026

Same author

Bedside trans-burrhole dynamic contrast-enhanced ultrasound (DCE-US) and Ultrasound Localization Microscopy (ULM) in relapsed Glioblastoma - a retrospective comparative case series.

Ultraschall in der Medizin (Stuttgart, Germany : 1980)·2026

Same author

PhotIQA: A photoacoustic image data set with image quality ratings.

Scientific data·2026

Same author

Author Correction: Large-scale self-supervised video foundation model for intelligent surgery.

NPJ digital medicine·2026

Same author

Impact of higher versus lower PEEP on mortality in mechanically ventilated patients with Sepsis - A multicenter, multi-cohort observational analysis.

Journal of critical care·2026

Same author

Longitudinal Assessment of Muscle Involvement in Late-Onset Pompe Disease Using Quantitative MRI: A Prospective Cohort Study.

Journal of cachexia, sarcopenia and muscle·2026

Summary

Deep learning models in photoacoustic imaging (PAI) can be biased by hardware differences between devices. This study reveals that PAI device fingerprints can lead to inaccurate disease diagnosis, highlighting the need for bias evaluation.

Area of Science:

Medical Imaging
Artificial Intelligence
Biomedical Engineering

Background:

Deep learning (DL) models excel in established medical imaging but struggle with emerging modalities like photoacoustic imaging (PAI) due to data sparsity and bias.
Hardware-induced bias in PAI is an unexplored challenge, risking multicentric deployment failure.

Purpose of the Study:

To conduct the first multicentric analysis of hardware-induced bias in photoacoustic imaging.
To investigate how device-specific characteristics affect DL model performance in PAI.
To evaluate the impact of device-health correlations on diagnostic accuracy.

Main Methods:

Analyzed device-specific characteristics from four PAI device instances across two peripheral artery disease studies.
Trained DL models to classify device origin and diagnose disease under varying device-health correlations.

Keywords:

Bias Deep learning Hardware confounder Photoacoustic Shortcut learning

Related Experiment Videos

Last Updated: Jun 16, 2026

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

Assessed the ability of DL models to detect device-specific fingerprints.

Main Results:

Identified unique 'fingerprints' embedded in PAI images from different device instances.
Achieved high accuracy in DL-based device detection using these fingerprints.
Demonstrated that DL models exploit device signatures as shortcuts when device and health status are correlated, leading to biased predictions.

Conclusions:

Overlooking hardware-induced bias in PAI can lead to overestimated algorithm performance and clinically misleading results.
Emphasizes the critical need for bias evaluation and explainable AI methods in PAI research.
Facilitates the development of robust and reliable DL models for multicentric photoacoustic imaging studies.