Karsten Seidl
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Karsten Seidl has a total of 118 co-authors. Here are the top co-authors by number of shared publications:
- Christian Wiede
Fraunhofer Institute for Microelectronic Circuits and Systems, Duisburg, Germany
5 shared publications - Andreas Erbslöh
University of Duisburg-Essen, Duisburg, Germany
4 shared publications - Alexander Utz
Faculty of Information, Media and Electrical Engineering, Institute of Applied Optics and Electronics, Kln, Germany
3 shared publications - Belmin Alić
University of Duisburg-Essen
3 shared publications Eline Reger
Fraunhofer Institute for Microelectronic Circuits and Systems Finkenstrasse 61 47057 Duisburg Germany
3 shared publications- Ingo Hoyer
Fraunhofer Institute for Microelectronic Circuits and Systems (IMS), Duisburg, Germany
3 shared publications
Latest Publications
- 18 August 2026
- Published by IOP Publishing in Physiological Measurement
- Vol. 47 (8) , 085020
Analysis of the frequency-dependent sensitivity distribution for lower forearm impedance plethysmography
Objective . The assessment of hemodynamic parameters plays an important role for the diagnosis and detection of cardiovascular diseases. One of the promising techniques for the non-invasive and continuous monitoring of arterial hemodynamics is the impedance plethysmography (IPG), which aims to measure the pulsatile volume change of superficial arteries. Crucial for the success of an IPG measurement is the selection of a setup that effectively targets the artery. Approach . This work analyzes the influence of the injection frequency alteration on the sensitivity distribution of an IPG measurement and the sensitivity towards the radial artery. The analysis is performed both in simulation and using study data obtained from 41 participants. The simulation consists of a finite element model representing the lower forearm and a fixed IPG setup, in which the sensitivity distribution is analyzed for different excitation frequencies between 3 kHz and 100 kHz. To allow for comparison, the IPG study utilizes the same five excitation frequencies between 3 kHz and 100 kHz. Main results . The results of the finite element simulation show that increasing excitation frequency shifts the region of large sensitivity away from the artery and especially towards deeper muscle tissue layers. The analysis of the study data supports this hypothesis by demonstrating that lower-frequency excitation yields larger relative pulsatile changes than larger excitation frequencies, thus indicating a larger sensitivity towards the pulsatile artery. Significance . The results of this paper show, that injection frequency directly affects the sensitivity regions. Analysis of the finite element method and study results indicate that the largest sensitivity towards the radial artery occurs at the smallest injection frequency. Thus, comparison of IPG measurements performed at different excitation frequencies should be interpreted carefully, comparability between individual measurements may be limited.
- 18 August 2026
- Published by IOP Publishing in Physiological Measurement
- Vol. 47 (8) , 085020
Analysis of the frequency-dependent sensitivity distribution for lower forearm impedance plethysmography
Objective . The assessment of hemodynamic parameters plays an important role for the diagnosis and detection of cardiovascular diseases. One of the promising techniques for the non-invasive and continuous monitoring of arterial hemodynamics is the impedance plethysmography (IPG), which aims to measure the pulsatile volume change of superficial arteries. Crucial for the success of an IPG measurement is the selection of a setup that effectively targets the artery. Approach . This work analyzes the influence of the injection frequency alteration on the sensitivity distribution of an IPG measurement and the sensitivity towards the radial artery. The analysis is performed both in simulation and using study data obtained from 41 participants. The simulation consists of a finite element model representing the lower forearm and a fixed IPG setup, in which the sensitivity distribution is analyzed for different excitation frequencies between 3 kHz and 100 kHz. To allow for comparison, the IPG study utilizes the same five excitation frequencies between 3 kHz and 100 kHz. Main results . The results of the finite element simulation show that increasing excitation frequency shifts the region of large sensitivity away from the artery and especially towards deeper muscle tissue layers. The analysis of the study data supports this hypothesis by demonstrating that lower-frequency excitation yields larger relative pulsatile changes than larger excitation frequencies, thus indicating a larger sensitivity towards the pulsatile artery. Significance . The results of this paper show, that injection frequency directly affects the sensitivity regions. Analysis of the finite element method and study results indicate that the largest sensitivity towards the radial artery occurs at the smallest injection frequency. Thus, comparison of IPG measurements performed at different excitation frequencies should be interpreted carefully, comparability between individual measurements may be limited.
- Open Access
- 2 February 2026
- Published by Springer Nature in Pflügers Archiv - European Journal of Physiology
- Vol. 478 (2) , 21
Just a little prick: careful cell contacts enabled by ceramic nanostraws
Nanostraw arrays represent a novel and promising approach for the controlled delivery of substances into cells characterized by very little cellular activation or damage. Herein, we describe a sensitive strategy to establish intracellular contact with human macrophage-like differentiated THP-1 cells. Macrophages must function under stressful in-vivo conditions in oxygen-deprived tissues with inflammation. THP-1 cells stayed healthy and did not show signs of activation when cultured on nanostraw arrays. Importantly, we found convincing evidence for the successful delivery of gold nanoparticles and fluorescence-labeled antibodies into THP-1 cells. Future applications of nanostraw arrays are the functionalization with silane coating to immobilize proteins and/or the analysis of membrane located ion channels in THP-1 cells by electrophysiology. Our findings demonstrate that nanostraw arrays can enable intracellular contact for substance delivery and they might also allow measurements of the cellular membrane potential under stressful culture conditions like hypoxia in the future, in particular for immune cells. Graphical Abstract
- 2 February 2026
- Published by Springer Nature in Pflügers Archiv - European Journal of Physiology
- Vol. 478 (2) , 21
Open AccessJust a little prick: careful cell contacts enabled by ceramic nanostraws
Nanostraw arrays represent a novel and promising approach for the controlled delivery of substances into cells characterized by very little cellular activation or damage. Herein, we describe a sensitive strategy to establish intracellular contact with human macrophage-like differentiated THP-1 cells. Macrophages must function under stressful in-vivo conditions in oxygen-deprived tissues with inflammation. THP-1 cells stayed healthy and did not show signs of activation when cultured on nanostraw arrays. Importantly, we found convincing evidence for the successful delivery of gold nanoparticles and fluorescence-labeled antibodies into THP-1 cells. Future applications of nanostraw arrays are the functionalization with silane coating to immobilize proteins and/or the analysis of membrane located ion channels in THP-1 cells by electrophysiology. Our findings demonstrate that nanostraw arrays can enable intracellular contact for substance delivery and they might also allow measurements of the cellular membrane potential under stressful culture conditions like hypoxia in the future, in particular for immune cells. Graphical Abstract
- Open Access
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Areas in Sensors
- Vol. 3, 69-77
Field Programmable Neural Array for Biomedical Signal Processing
Processing biomedical signals using artificial intelligence (AI) algorithms, particularly convolutional neural networks (CNNs), presents challenges for resource-limited systems, such as smart patches. For instance, screening electrocardiogram (ECG) signals for heart arrhythmias, including atrial fibrillation (AF), is crucial for enhancing early diagnosis, as this condition is closely linked to an increased risk of stroke and overall mortality. Common approaches for System-on-Chip (SoC) implementation typically involve either a software-based solution utilizing a standard microcontroller or a dedicated hardware accelerator designed to execute the full CNN. This study investigates an approach utilizing reconfigurable fabric, including a theoretical model for efficiency estimation, similar to field programmable gate arrays (FPGAs). These specialized field programmable neural arrays (FPNAs) incorporate specialized tiles designed for AI inference. For instance, in the case of a single convolution, the FPNA occupies only half the silicon area while maintaining equivalent timing performance and achieving a 52.9 % reduction in energy consumption per inference. Further results are presented for a test CNN and a CNN for ECG processing. Although the FPNA may require more area and, at times, more energy per inference than a direct hardware implementation, this trade-off is deemed acceptable due to the advantages of reconfigurability.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Areas in Sensors
- Vol. 3, 69-77
Open AccessField Programmable Neural Array for Biomedical Signal Processing
Processing biomedical signals using artificial intelligence (AI) algorithms, particularly convolutional neural networks (CNNs), presents challenges for resource-limited systems, such as smart patches. For instance, screening electrocardiogram (ECG) signals for heart arrhythmias, including atrial fibrillation (AF), is crucial for enhancing early diagnosis, as this condition is closely linked to an increased risk of stroke and overall mortality. Common approaches for System-on-Chip (SoC) implementation typically involve either a software-based solution utilizing a standard microcontroller or a dedicated hardware accelerator designed to execute the full CNN. This study investigates an approach utilizing reconfigurable fabric, including a theoretical model for efficiency estimation, similar to field programmable gate arrays (FPGAs). These specialized field programmable neural arrays (FPNAs) incorporate specialized tiles designed for AI inference. For instance, in the case of a single convolution, the FPNA occupies only half the silicon area while maintaining equivalent timing performance and achieving a 52.9 % reduction in energy consumption per inference. Further results are presented for a test CNN and a CNN for ECG processing. Although the FPNA may require more area and, at times, more energy per inference than a direct hardware implementation, this trade-off is deemed acceptable due to the advantages of reconfigurability.
- Open Access
- 1 September 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 30 (09) , 095001-17
Phasor and neural network approaches for rapid fluorophore fraction analysis in temporal–spectral multiplexed data
In fluorescence-based methods such as fluorescence microscopy,1 spectroscopy,2 and flow cytometry,3 the quantification of fluorophore fractions is a key process for molecular characterization and analysis. The fraction information enables insights into cellular structures and molecular dynamics and activities3,4 in biological applications and is also used in material and environmental sciences to study molecular interactions.2 Depending on the application, samples are either labeled with exogenous fluorophores or analyzed based on their intrinsic autofluorescence. The fluorescence is typically distinguished by the ES or LT. Although exogenous fluorophores can be designed to differ to a certain degree in ES and LT, autofluorescence samples have intrinsic spectral and temporal characteristics and therefore fixed ES and LT. This inevitably results in spectral overlap5 and similar LT,4 making it challenging to accurately separate individual fluorophore fractions in fluorophore mixtures.
- 1 September 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 30 (09) , 095001-17
Open AccessPhasor and neural network approaches for rapid fluorophore fraction analysis in temporal–spectral multiplexed data
In fluorescence-based methods such as fluorescence microscopy,1 spectroscopy,2 and flow cytometry,3 the quantification of fluorophore fractions is a key process for molecular characterization and analysis. The fraction information enables insights into cellular structures and molecular dynamics and activities3,4 in biological applications and is also used in material and environmental sciences to study molecular interactions.2 Depending on the application, samples are either labeled with exogenous fluorophores or analyzed based on their intrinsic autofluorescence. The fluorescence is typically distinguished by the ES or LT. Although exogenous fluorophores can be designed to differ to a certain degree in ES and LT, autofluorescence samples have intrinsic spectral and temporal characteristics and therefore fixed ES and LT. This inevitably results in spectral overlap5 and similar LT,4 making it challenging to accurately separate individual fluorophore fractions in fluorophore mixtures.
- Open Access
- 1 April 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (2) , 026056
Prediction of impedance characteristic during electrical stimulation with microelectrode arrays
Objective. Modern neural devices allow to interact with degenerated tissue in order to restore sensoric loss function and to suppress symptoms of neurodegenerative diseases using microelectronic arrays (MEA). They have a bidirectional interface for performing electrical stimulation to write-in new information and for recording the neural activity to read-out a neural task, e.g. movement ambitions. For both applications, the electrical impedance of the electrode-tissue interface (ETI) is crucial. However, the ETI can change during run-time due to encapsulation effects and changes of the neuronal structures. We investigated if an impedance spectrum can be reliably extracted from recordings during stimulation with microelectrode arrays. Approach. We present a measurement method for characterizing the electrical impedance spectrum during stimulation. We performed charge-controlled stimulation with a penetrating microelectrode array in an electrolyte solution. From the stimulation recordings, we extracted the impedance. Furthermore, a numerical model (digital twin) of the stimulation electrodes is established. Main results. We obtained consistent results for relevant electrochemical using electrochemical impedance spectroscopy, time-domain analysis and Fourier-transform-based impedance estimation. Moreover, the numerical simulations confirmed that the measured microelectrode had the expected properties. Significance. Our results pave the way to enable a live assessment of the impedance in future MEA-based neural devices. This will enable adaptive electrical stimulation or (re-)selection of recording electrodes by taking the actual state of the electrode into account.
- 1 April 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (2) , 026056
Open AccessPrediction of impedance characteristic during electrical stimulation with microelectrode arrays
Objective. Modern neural devices allow to interact with degenerated tissue in order to restore sensoric loss function and to suppress symptoms of neurodegenerative diseases using microelectronic arrays (MEA). They have a bidirectional interface for performing electrical stimulation to write-in new information and for recording the neural activity to read-out a neural task, e.g. movement ambitions. For both applications, the electrical impedance of the electrode-tissue interface (ETI) is crucial. However, the ETI can change during run-time due to encapsulation effects and changes of the neuronal structures. We investigated if an impedance spectrum can be reliably extracted from recordings during stimulation with microelectrode arrays. Approach. We present a measurement method for characterizing the electrical impedance spectrum during stimulation. We performed charge-controlled stimulation with a penetrating microelectrode array in an electrolyte solution. From the stimulation recordings, we extracted the impedance. Furthermore, a numerical model (digital twin) of the stimulation electrodes is established. Main results. We obtained consistent results for relevant electrochemical using electrochemical impedance spectroscopy, time-domain analysis and Fourier-transform-based impedance estimation. Moreover, the numerical simulations confirmed that the measured microelectrode had the expected properties. Significance. Our results pave the way to enable a live assessment of the impedance in future MEA-based neural devices. This will enable adaptive electrical stimulation or (re-)selection of recording electrodes by taking the actual state of the electrode into account.
- Open Access
- 29 January 2025
- Published by IOP Publishing in Physiological Measurement
- Vol. 46 (1) , 015002
tinyHLS: a novel open source high level synthesis tool targeting hardware accelerators for artificial neural network inference
Objective. In recent years, wearable devices such as smartwatches and smart patches have revolutionized biosignal acquisition and analysis, particularly for monitoring electrocardiography (ECG). However, the limited power supply of these devices often precludes real-time data analysis on the patch itself. Approach. This paper introduces a novel Python package, tinyHLS (High Level Synthesis), designed to address these challenges by converting Python-based AI models into platform-independent hardware description language code accelerators. Specifically designed for convolutional neural networks, tinyHLS seamlessly integrates into the AI developer’s workflow in Python TensorFlow Keras. Our methodology leverages a template-based hardware compiler that ensures flexibility, efficiency, and ease of use. In this work, tinyHLS is first-published featuring templates for several layers of neural networks, such as dense, convolution, max and global average pooling. In the first version, rectified linear unit is supported as activation. It targets one-dimensional data, with a particular focus on time series data. Main results. The generated accelerators are validated in detecting atrial fibrillation on ECG data, demonstrating significant improvements in processing speed (62-fold) and energy efficiency (4.5-fold). Quality of code and synthesizability are ensured by validating the outputs with commercial ASIC design tools. Significance. Importantly, tinyHLS is open-source and does not rely on commercial tools, making it a versatile solution for both academic and commercial applications. The paper also discusses the integration with an open-source RISC-V and potential for future enhancements of tinyHLS, including its application in edge servers and cloud computing. The source code is available on GitHub: https://github.com/Fraunhofer-IMS/tinyHLS
- 29 January 2025
- Published by IOP Publishing in Physiological Measurement
- Vol. 46 (1) , 015002
Open AccesstinyHLS: a novel open source high level synthesis tool targeting hardware accelerators for artificial neural network inference
Objective. In recent years, wearable devices such as smartwatches and smart patches have revolutionized biosignal acquisition and analysis, particularly for monitoring electrocardiography (ECG). However, the limited power supply of these devices often precludes real-time data analysis on the patch itself. Approach. This paper introduces a novel Python package, tinyHLS (High Level Synthesis), designed to address these challenges by converting Python-based AI models into platform-independent hardware description language code accelerators. Specifically designed for convolutional neural networks, tinyHLS seamlessly integrates into the AI developer’s workflow in Python TensorFlow Keras. Our methodology leverages a template-based hardware compiler that ensures flexibility, efficiency, and ease of use. In this work, tinyHLS is first-published featuring templates for several layers of neural networks, such as dense, convolution, max and global average pooling. In the first version, rectified linear unit is supported as activation. It targets one-dimensional data, with a particular focus on time series data. Main results. The generated accelerators are validated in detecting atrial fibrillation on ECG data, demonstrating significant improvements in processing speed (62-fold) and energy efficiency (4.5-fold). Quality of code and synthesizability are ensured by validating the outputs with commercial ASIC design tools. Significance. Importantly, tinyHLS is open-source and does not rely on commercial tools, making it a versatile solution for both academic and commercial applications. The paper also discusses the integration with an open-source RISC-V and potential for future enhancements of tinyHLS, including its application in edge servers and cloud computing. The source code is available on GitHub: https://github.com/Fraunhofer-IMS/tinyHLS
- 1 January 2025
- Published by Springer Nature
- p. 439-454
Künstliche Intelligenz in der POCT-Diagnostik
- Open Access
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (3) , 2074-2087
Feature-Based Detection and Classification of Sleep Apnea and Hypopnea Using Multispectral Imaging
Sleep apnea syndrome (SAS) is a sleep-related breathing disorder characterized by repetitive breathing interruptions during sleep, resulting in daytime drowsiness, concentration difficulties, and increased risk of cardiovascular diseases. SAS is diagnosed in specialized sleep laboratories via polysomnography (PSG). PSG involves a high number of contact-based sensors, and it may cause patient discomfort and bias in measurement results. Therefore, contactless alternatives to PSG are a promising way to overcome these issues. This work introduces a novel featurebased method for detecting and classifying apneic events in terms of event amplitude (apneas and hypopneas) and event source (obstructive and central) by using multispectral imaging in the near-infrared (NIR) and far-infrared (FIR) spectra. In the NIR spectrum, remote photoplethysmography signals at 780 and 940 nm are extracted, while in the FIR spectrum, a respiratory airflow signal is extracted. The method is based on the extraction of explainable and medically significant features and the fusion of multiple data modalities (multispectral images, demographic patient data, interspectral correlation analysis, and time-series analysis). The classification accuracy between normal breathing, hypopneas, and apneas is 99.5%, while the differentiation between obstructive and central apneas achieves an accuracy of 98.8%. The estimations of the apnea-hypopnea index (AHI), obstructive apnea index (oAI), and central apnea index (cAI) result in a Pearson correlation of 0.9981, 0.9989, and 0.9950 respectively. A correct SAS stage prediction for 19 symptomatic patients in our dataset is accomplished. The results show that this method may be used as a PSG substitute for apnea and hypopnea detection and classification.
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (3) , 2074-2087
Open AccessFeature-Based Detection and Classification of Sleep Apnea and Hypopnea Using Multispectral Imaging
Sleep apnea syndrome (SAS) is a sleep-related breathing disorder characterized by repetitive breathing interruptions during sleep, resulting in daytime drowsiness, concentration difficulties, and increased risk of cardiovascular diseases. SAS is diagnosed in specialized sleep laboratories via polysomnography (PSG). PSG involves a high number of contact-based sensors, and it may cause patient discomfort and bias in measurement results. Therefore, contactless alternatives to PSG are a promising way to overcome these issues. This work introduces a novel featurebased method for detecting and classifying apneic events in terms of event amplitude (apneas and hypopneas) and event source (obstructive and central) by using multispectral imaging in the near-infrared (NIR) and far-infrared (FIR) spectra. In the NIR spectrum, remote photoplethysmography signals at 780 and 940 nm are extracted, while in the FIR spectrum, a respiratory airflow signal is extracted. The method is based on the extraction of explainable and medically significant features and the fusion of multiple data modalities (multispectral images, demographic patient data, interspectral correlation analysis, and time-series analysis). The classification accuracy between normal breathing, hypopneas, and apneas is 99.5%, while the differentiation between obstructive and central apneas achieves an accuracy of 98.8%. The estimations of the apnea-hypopnea index (AHI), obstructive apnea index (oAI), and central apnea index (cAI) result in a Pearson correlation of 0.9981, 0.9989, and 0.9950 respectively. A correct SAS stage prediction for 19 symptomatic patients in our dataset is accomplished. The results show that this method may be used as a PSG substitute for apnea and hypopnea detection and classification.
- Open Access
- 1 October 2024
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 21 (5) , 051003
Technical survey of end-to-end signal processing in BCIs using invasive MEAs
Modern brain-computer interfaces and neural implants allow interaction between the tissue, the user and the environment, where people suffer from neurodegenerative diseases or injuries.This interaction can be achieved by using penetrating/invasive microelectrodes for extracellular recordings and stimulation, such as Utah or Michigan arrays. The application-specific signal processing of the extracellular recording enables the detection of interactions and enables user interaction. For example, it allows to read out movement intentions from recordings of brain signals for controlling a prosthesis or an exoskeleton. To enable this, computationally complex algorithms are used in research that cannot be executed on-chip or on embedded systems. Therefore, an optimization of the end-to-end processing pipeline, from the signal condition on the electrode array over the analog pre-processing to spike-sorting and finally the neural decoding process, is necessary for hardware inference in order to enable a local signal processing in real-time and to enable a compact system for achieving a high comfort level. This paper presents a survey of system architectures and algorithms for end-to-end signal processing pipelines of neural activity on the hardware of such neural devices, including (i) on-chip signal pre-processing, (ii) spike-sorting on-chip or on embedded hardware and (iii) neural decoding on workstations. A particular focus for the hardware implementation is on low-power electronic design and artifact-robust algorithms with low computational effort and very short latency. For this, current challenges and possible solutions with support of novel machine learning techniques are presented in brief. In addition, we describe our future vision for next-generation BCIs.
- 1 October 2024
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 21 (5) , 051003
Open AccessTechnical survey of end-to-end signal processing in BCIs using invasive MEAs
Modern brain-computer interfaces and neural implants allow interaction between the tissue, the user and the environment, where people suffer from neurodegenerative diseases or injuries.This interaction can be achieved by using penetrating/invasive microelectrodes for extracellular recordings and stimulation, such as Utah or Michigan arrays. The application-specific signal processing of the extracellular recording enables the detection of interactions and enables user interaction. For example, it allows to read out movement intentions from recordings of brain signals for controlling a prosthesis or an exoskeleton. To enable this, computationally complex algorithms are used in research that cannot be executed on-chip or on embedded systems. Therefore, an optimization of the end-to-end processing pipeline, from the signal condition on the electrode array over the analog pre-processing to spike-sorting and finally the neural decoding process, is necessary for hardware inference in order to enable a local signal processing in real-time and to enable a compact system for achieving a high comfort level. This paper presents a survey of system architectures and algorithms for end-to-end signal processing pipelines of neural activity on the hardware of such neural devices, including (i) on-chip signal pre-processing, (ii) spike-sorting on-chip or on embedded hardware and (iii) neural decoding on workstations. A particular focus for the hardware implementation is on low-power electronic design and artifact-robust algorithms with low computational effort and very short latency. For this, current challenges and possible solutions with support of novel machine learning techniques are presented in brief. In addition, we describe our future vision for next-generation BCIs.
- Open Access
- 1 June 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 29 (S3) , S33309-20
Leveraging 3D convolutional neural network and 3D visible-near-infrared multimodal imaging for enhanced contactless oximetry
Vital signs, such as body temperature, heart rate, respiratory rate, and blood pressure are standard indicators of an individual’s physiological functions in most medical settings.1 Monitoring these vital parameters is crucial for early diagnosis, medical treatment, risk assessment, and patient recovery monitoring.2,3 With the advancement of medical measurement technology, oxygen saturation has increasingly become recognized as an indispensable fifth vital sign.4 Oxygen saturation indicates the percentage of oxygenated hemoglobin () and hemoglobin (Hb) in the blood, in which the artery should be in the range of 95% to 100% in healthy individuals.5 Many pulmonary diseases cause abnormalities in oxygen saturation values, such as acute pneumonia, chronic obstructive pulmonary disease (COPD), and sleep apnea syndrome (SAS). Furthermore, the outbreak of coronavirus (COVID-19) has further underscored the critical importance of oxygen saturation measurement.- 1 June 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 29 (S3) , S33309-20
Open AccessLeveraging 3D convolutional neural network and 3D visible-near-infrared multimodal imaging for enhanced contactless oximetry
Vital signs, such as body temperature, heart rate, respiratory rate, and blood pressure are standard indicators of an individual’s physiological functions in most medical settings.1 Monitoring these vital parameters is crucial for early diagnosis, medical treatment, risk assessment, and patient recovery monitoring.2,3 With the advancement of medical measurement technology, oxygen saturation has increasingly become recognized as an indispensable fifth vital sign.4 Oxygen saturation indicates the percentage of oxygenated hemoglobin () and hemoglobin (Hb) in the blood, in which the artery should be in the range of 95% to 100% in healthy individuals.5 Many pulmonary diseases cause abnormalities in oxygen saturation values, such as acute pneumonia, chronic obstructive pulmonary disease (COPD), and sleep apnea syndrome (SAS). Furthermore, the outbreak of coronavirus (COVID-19) has further underscored the critical importance of oxygen saturation measurement.