Abstract
Near infrared fluorescence optical imaging (NIR-FOI) visualises the vascular perfusion of the investigated anatomical structure. Even though there has been a lot of medical research in the field to detect joint inflammation utilising NIR-FOI, an objective machine learning based evaluation method of the image data has not been developed, yet.
The measured NIR-FOI data consists of two spatial dimensions (image pixel) and one temporal dimension. To assess the distribution process an understanding of the hands’ locations is essential. However, random motion changes the positioning, which requires re-segmentation. The goal of this work is to identify the time points (frames) and severity of motion in the previously measured image stack. Due to properties of the NIR-FOI, each data set is split into two phases: Before and after full illumination of the hands. For each phase, an independent model is trained to evaluate the severity and time point of possible motion.
The model for the first phase achieves a precision of 20.78 % and a recall of 69.57 %, while the model for the second phase reaches a precision of 67.71 % and a recall of 98.49 % to detect non-negligible motion. Despite low precision, both models can be considered a success, contemplating the high heterogeneity, self-illumination and real-life consequences of a low precision value, which only affects computation time.
Our general goal is to achieve a robust and early detection of psoriatic arthritis, to increase quality of life while decreasing treatment costs. The presented work plays a key role in this research, especially increasing robustness of the final evaluation pipeline.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The term self-illumination refers to the ICG emitted light being the only measured light source. Visibility, brightness etc. depend on the investigated hands’ conditions.
References
Beauchemin, S.S., Barron, J.L.: The computation of optical flow. ACM Comput. Surv. 27(3), 433–466 (1995). https://doi.org/10.1145/212094.212141
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995). https://doi.org/10.1007/bf00994018
Dziekan, T., et al.: Detection of rheumatoid arthritis by evaluation of normalized variances of fluorescence time correlation functions. J. Biomed. Opt. 16(7), 076015 (2011). https://doi.org/10.1117/1.3599958
Finckh, A., Liang, M.H., van Herckenrode, C.M., de Pablo, P.: Long-term impact of early treatment on radiographic progression in rheumatoid arthritis: a meta-analysis. Arthritis Care Res. 55(6), 864–872 (2006). https://doi.org/10.1002/art.22353
Friedrich, S., et al.: Disturbed microcirculation in the hands of patients with systemic sclerosis detected by fluorescence optical imaging: a pilot study. Arthritis Res. Ther. 19(1), 1–13 (2017). https://doi.org/10.1186/s13075-017-1300-6
Glimm, A.M., Werner, S.G., Burmester, G.R., Backhaus, M., Ohrndorf, S.: Analysis of distribution and severity of inflammation in patients with osteoarthitis compared to rheumatoid arthritis by ICG-enhanced fluorescence optical imaging and musculoskeletal ultrasound: a pilot study. Ann. Rheum. Dis. 75(3), 566–570 (2015). https://doi.org/10.1136/annrheumdis-2015-207345
Haroon, M., Gallagher, P., FitzGerald, O.: Diagnostic delay of more than 6 months contributes to poor radiographic and functional outcome in psoriatic arthritis. Ann. Rheum. Dis. 74(6), 1045–1050 (2014). https://doi.org/10.1136/annrheumdis-2013-204858
Hirano, F.: Comparison of fluorescence optical imaging, ultrasonography and clinical examination with magnetic resonance imaging as a reference in active rheumatoid arthritis patients. Immunol. Med. 41(2), 75–81 (2018). https://doi.org/10.1080/13497413.2018.1481578
Mohajerani, P., Meier, R., Noël, P.B., Rummeny, E.J., Ntziachristos, V.: Spatiotemporal analysis for indocyanine green-aided imaging of rheumatoid arthritis in hand joints. J. Biomed. Optics 18(9), 097004 (2013). https://doi.org/10.1117/1.jbo.18.9.097004
Pfeil, A., et al.: The application of fluorescence optical imaging in systemic sclerosis. Biomed. Res. Int. 2015, 1–6 (2015). https://doi.org/10.1155/2015/658710
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2019). https://doi.org/10.1109/cvpr.2019.00075
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation (2015). https://doi.org/10.48550/ARXIV.1505.04597
Werner, S.G., et al.: Indocyanine green-enhanced fluorescence optical imaging in patients with early and very early arthritis: a comparative study with magnetic resonance imaging. Arthritis Rheum. 65(12), 3036–3044 (2013). https://doi.org/10.1002/art.38175
Acknowledgements
We thank Ulf Henkemeier and team for the data acquisition. Additionally, we thank Andreas Wirtz, Raaghav Radhakrishnan and Phuong-Ha Nguyen for valuable discussions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zerweck, L., Wesarg, S., Kohlhammer, J., Köhm, M. (2023). Machine Learning Based Approach for Motion Detection and Estimation in Routinely Acquired Low Resolution Near Infrared Fluorescence Optical Imaging. In: Chen, Y., et al. Clinical Image-Based Procedures. CLIP 2022. Lecture Notes in Computer Science, vol 13746. Springer, Cham. https://doi.org/10.1007/978-3-031-23179-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-23179-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23178-0
Online ISBN: 978-3-031-23179-7
eBook Packages: Computer ScienceComputer Science (R0)