Detecting unforeseen data properties with diffusion autoencoder embeddings using ppine MRI data

Tools

Item Type:	Conference or Workshop Item
Title:	Detecting unforeseen data properties with diffusion autoencoder embeddings using ppine MRI data
Creators Name:	Graf, R., Hunecke, F., Pohl, S., Atad, M., Moeller, H., Starck, S., Kroencke, T., Bette, S., Bamberg, F., Pischon, T., Niendorf, T., Schmidt, C., Paetzold, J.C., Rueckert, D. and Kirschke, J.S.
Abstract:	Deep learning has made significant strides in medical imaging, leveraging the use of large datasets to improve diagnostics and prognostics. However, large datasets often come with inherent errors through subject selection and acquisition. In this paper, we investigate the use of Diffusion Autoencoder (DAE) embeddings for uncovering and understanding data characteristics and biases, including biases for protected variables like sex and data abnormalities indicative of unwanted protocol variations. We use sagittal T2-weighted magnetic resonance (MR) images of the neck, chest, and lumbar region from 11186 German National Cohort (NAKO) participants. We compare DAE embeddings with existing generative models like StyleGAN and Variational Autoencoder. Evaluations on a large-scale dataset consisting of sagittal T2-weighted MR images of three spine regions show that DAE embeddings effectively separate protected variables such as sex and age. Furthermore, we used t-SNE visualization to identify unwanted variations in imaging protocols, revealing differences in head positioning. Our embedding can identify samples where a sex predictor will have issues learning the correct sex. Our findings highlight the potential of using advanced embedding techniques like DAEs to detect data quality issues and biases in medical imaging datasets. Identifying such hidden relations can enhance the reliability and fairness of deep learning models in healthcare applications, ultimately improving patient care and outcomes.
Keywords:	Bias Detection, Data Quality, Embeddings, Large Cohorts
Source:	Lecture Notes in Computer Science
Series Name:	Lecture Notes in Computer Science
Title of Book:	Medical Image Computing and Computer Assisted Intervention - MICCAI 2024 Workshops
ISSN:	0302-9743
ISBN:	978-3-031-77609-0
Publisher:	Springer
Volume:	2024
Number:	15274
Page Range:	79-88
Number of Pages:	10
Date:	17 January 2025
Official Publication:	https://doi.org/10.1007/978-3-031-77610-6_8

Repository Staff Only: item control page