Hardware-related biases in machine learning algorithms for photoacoustic image analysis

Christoph J. Bender; Kris K. Dreher; Niklas Holzwarth; Marcel Knopp; Jan-Hinrich Nölke; Tom Rix; Melanie Schellenberg; Julius Kempf; Werner Lang M.D.; Alexander Seitel; Ulrich Rother; Lena Maier-Hein

doi:10.1117/12.3000348

13 March 2024 Hardware-related biases in machine learning algorithms for photoacoustic image analysis

Christoph J. Bender, Kris K. Dreher, Niklas Holzwarth, Marcel Knopp, Jan-Hinrich Nölke, Tom Rix, Melanie Schellenberg, Julius Kempf, Werner Lang M.D., Alexander Seitel, Ulrich Rother, Lena Maier-Hein

Author Affiliations +

Proceedings Volume PC12842, Photons Plus Ultrasound: Imaging and Sensing 2024; PC128422T (2024) https://doi.org/10.1117/12.3000348
Event: SPIE BiOS, 2024, San Francisco, California, United States

Conference Poster

Abstract

This study delves into the largely uncharted domain of biases in photoacoustic imaging, spotlighting potential shortcut learning as a key issue in reliable machine learning. Our focus is on hardware variation biases. We identify device-specific traits that create detectable fingerprints in photoacoustic images, demonstrate machine learning's capability to use these discrepancies to determine the device that acquired the image, and highlight their potential impact on machine learning model predictions in downstream tasks, such as disease classification.

Citation Download Citation

Christoph J. Bender, Kris K. Dreher, Niklas Holzwarth, Marcel Knopp, Jan-Hinrich Nölke, Tom Rix, Melanie Schellenberg, Julius Kempf, Werner Lang M.D., Alexander Seitel, Ulrich Rother, and Lena Maier-Hein "Hardware-related biases in machine learning algorithms for photoacoustic image analysis", Proc. SPIE PC12842, Photons Plus Ultrasound: Imaging and Sensing 2024, PC128422T (13 March 2024); https://doi.org/10.1117/12.3000348

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available