Contactless Respiratory Waveform Estimation Using a Depth Camera and AI-Based Body Detection
Sensors · 01.06.2026 · 26 (11) · 3476
DOI: 10.3390/s26113476 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 01.06.2026. Verfasst von Yuto Kojima und 5 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Advanced Science and Engineering, Hiroshima University, 1-4-1 Kagamiyama, Higashi-Hiroshima City 739-8527, Japan. Hauptthemen laut MEDLINE: Respiration, Artificial Intelligence. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: AMED, Japan Agency for Medical Research and Development (AMED).
Abstract (Originalsprache)
Computed tomography (CT) examinations pose challenges for continuous patient observation, particularly when adverse events such as severe reactions to contrast media occur. To improve patient monitoring in such situations, this preliminary study proposes a contactless method for respiratory waveform estimation using a depth camera and AI-based body detection. The method identifies anatomically relevant respiratory regions and extracts depth-based motion signals while subjects are seated facing the camera, which is positioned approximately 2 m away. Performance was evaluated experimentally using a wearable force-sensor respiration belt as the reference. Quantitative assessment was conducted using waveform error metrics, Pearson correlation coefficients, respiratory-rate agreement, and Bland–Altman analysis, while qualitative analysis was used to examine the influence of clothing conditions on measurement performance. The results show that the proposed method can provide stable respiratory waveform estimation, with the chest region yielding the lowest waveform error and the highest correlation among the evaluated ROIs. Bland–Altman analysis further indicated small systematic errors in respiratory-rate estimation, although variability-related indices were affected by ROI selection and clothing conditions. These findings support the feasibility of the proposed approach for contactless respiratory monitoring during CT examinations and indicate that the main contribution of this study is to clarify the importance of anatomical ROI selection for robust waveform extraction under CT-oriented monitoring conditions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of Advanced Science and Engineering, Hiroshima University, 1-4-1 Kagamiyama, Higashi-Hiroshima City 739-8527, Japan.
- Department of Electrical Engineering and Information Science, National Institute of Technology (KOSEN), Kure College, 2-2-11 Agaminami, Kure City 737-8506, Japan.
- Department of Diagnostic Radiology, Kasumi Campus, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima City 734-8551, Japan.
ORCID-Profile: Yuto Kojima, Toru Higaki, Hirotaka Inoue, Bisser Raytchev, Yuko Nakamura
Förderung
- AMED
- Japan Agency for Medical Research and Development (AMED)
Zitieren
APA
Kojima, Y., Higaki, T., Inoue, H., Raytchev, B., Gu, Y., & Nakamura, Y. (2026). Contactless Respiratory Waveform Estimation Using a Depth Camera and AI-Based Body Detection. Sensors, 26(11), 3476. https://doi.org/10.3390/s26113476
Vancouver
Kojima Y, Higaki T, Inoue H, Raytchev B, Gu Y, Nakamura Y. Contactless Respiratory Waveform Estimation Using a Depth Camera and AI-Based Body Detection. Sensors. 2026;26(11):3476. doi:10.3390/s26113476
BibTeX
@article{Kojima2026,
author = {Kojima, Yuto and Higaki, Toru and Inoue, Hirotaka and Raytchev, Bisser and Gu, Yanlei and Nakamura, Yuko},
title = {Contactless Respiratory Waveform Estimation Using a Depth Camera and AI-Based Body Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {11},
pages = {3476},
doi = {10.3390/s26113476}
}
EUVIMED