Video object detection for privacy-preserving patient monitoring in intensive care

Emberger, Raphael; Boss, Jens Michael; Baumann, Daniel; Seric, Marko; Huo, Shufan; Tuggener, Lukas; Keller, Emanuela; Stadelmann, Thilo

doi:10.1109/SDS57534.2023.00019

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-27810

Publication type:	Conference paper
Type of review:	Peer review (publication)
Title:	Video object detection for privacy-preserving patient monitoring in intensive care
Authors:	Emberger, Raphael Boss, Jens Michael Baumann, Daniel Seric, Marko Huo, Shufan Tuggener, Lukas Keller, Emanuela Stadelmann, Thilo
et. al:	No
DOI:	10.1109/SDS57534.2023.00019 10.21256/zhaw-27810
Proceedings:	2023 10th IEEE Swiss Conference on Data Science (SDS)
Page(s):	85
Pages to:	88
Conference details:	10th IEEE Swiss Conference on Data Science (SDS), Zurich, Switzerland, 22-23 June 2023
Issue Date:	Jun-2023
Publisher / Ed. Institution:	IEEE
ISBN:	979-8-3503-3875-1
Language:	English
Subjects:	Object recognition; Medical informatics; Data-centric AI; DCAI
Subject (DDC):	006: Special computer methods
Abstract:	Patient monitoring in intensive care units, although assisted by biosensors, needs continuous supervision of staff. To reduce the burden on staff members, IT infrastructures are built to record monitoring data and develop clinical decision support systems. These systems, however, are vulnerable to artifacts (e.g. muscle movement due to ongoing treatment), which are often indistinguishable from real and potentially dangerous signals. Video recordings could facilitate the reliable classification of biosignals using object detection (OD) methods to find sources of unwanted artifacts. Due to privacy restrictions, only blurred videos can be stored, which severely impairs the possibility to detect clinically relevant events such as interventions or changes in patient status with standard OD methods. Hence, new kinds of approaches are necessary that exploit every kind of available information due to the reduced information content of blurred footage and that are at the same time easily implementable within the IT infrastructure of a normal hospital. In this paper, we propose a new method for exploiting information in the temporal succession of video frames. To be efficiently implementable using off-the-shelf object detectors that comply with given hardware constraints, we repurpose the image color channels to account for temporal consistency, leading to an improved detection rate of the object classes. Our method outperforms a standard YOLOv5 baseline model by +1.7% mAP@.5 while also training over ten times faster on our proprietary dataset. We conclude that this approach has shown effectiveness in the preliminary experiments and holds potential for more general video OD in the future.
URI:	https://digitalcollection.zhaw.ch/handle/11475/27810
Fulltext version:	Accepted version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Centre for Artificial Intelligence (CAI)
Published as part of the ZHAW project:	AUTODIDACT – Automated Video Data Annotation to Empower the ICU Cockpit Platform for Clinical Decision Support
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2023_Emberger-etal_Video-OD-for-privacy-preserving-patient-monitoring_SDS.pdf	Accepted Version	2.89 MB	Adobe PDF	View/Open

Show full item record

Emberger, R., Boss, J. M., Baumann, D., Seric, M., Huo, S., Tuggener, L., Keller, E., & Stadelmann, T. (2023). Video object detection for privacy-preserving patient monitoring in intensive care [Conference paper]. 2023 10th IEEE Swiss Conference on Data Science (SDS), 85–88. https://doi.org/10.1109/SDS57534.2023.00019

Emberger, R. et al. (2023) ‘Video object detection for privacy-preserving patient monitoring in intensive care’, in 2023 10th IEEE Swiss Conference on Data Science (SDS). IEEE, pp. 85–88. Available at: https://doi.org/10.1109/SDS57534.2023.00019.

R. Emberger et al., “Video object detection for privacy-preserving patient monitoring in intensive care,” in 2023 10th IEEE Swiss Conference on Data Science (SDS), Jun. 2023, pp. 85–88. doi: 10.1109/SDS57534.2023.00019.

EMBERGER, Raphael, Jens Michael BOSS, Daniel BAUMANN, Marko SERIC, Shufan HUO, Lukas TUGGENER, Emanuela KELLER und Thilo STADELMANN, 2023. Video object detection for privacy-preserving patient monitoring in intensive care. In: 2023 10th IEEE Swiss Conference on Data Science (SDS). Conference paper. IEEE. Juni 2023. S. 85–88. ISBN 979-8-3503-3875-1

Emberger, Raphael, Jens Michael Boss, Daniel Baumann, Marko Seric, Shufan Huo, Lukas Tuggener, Emanuela Keller, and Thilo Stadelmann. 2023. “Video Object Detection for Privacy-Preserving Patient Monitoring in Intensive Care.” Conference paper. In 2023 10th IEEE Swiss Conference on Data Science (SDS), 85–88. IEEE. https://doi.org/10.1109/SDS57534.2023.00019.

Emberger, Raphael, et al. “Video Object Detection for Privacy-Preserving Patient Monitoring in Intensive Care.” 2023 10th IEEE Swiss Conference on Data Science (SDS), IEEE, 2023, pp. 85–88, https://doi.org/10.1109/SDS57534.2023.00019.