Physiological Information Research Articles

Wireless Pulse Wave Monitoring System Based on Reflective Flexible Probe and AFE4490

Pulse rate and blood oxygen levels are crucial physiological parameters that reflect physiological and pathological information within the human body. The system designs a wireless pulse wave monitoring system utilizing a flexible reflective probe and the AFE4490, which is capable of monitoring pulse wave and blood oxygen levels on the human forehead. The system is predominantly based on a reflective flexible probe, the AFE4490, a power supply module, a control microcontroller unit (MCU), and a Wi-Fi module. Post-processing by a slave computer, the collected pulse wave data is wirelessly transmitted to a smartphone. The real-time pulse waveform, pulse rate, and blood oxygen levels are displayed on an application. Following relevant tests and verifications, the system can accurately detect pulse wave signals, meet the requirements for wearable technology, and possesses significant market application potential.

Flexible wearable sensors for crop monitoring: a review.

Crops were the main source of human food, which have met the increasingly diversified demand of consumers. Sensors were used to monitor crop phenotypes and environmental information in real time, which will provide a theoretical reference for optimizing crop growth environment, resisting biotic and abiotic stresses, and improve crop yield. Compared with non-contact monitoring methods such as optical imaging and remote sensing, wearable sensing technology had higher time and spatial resolution. However, the existing crop sensors were mainly rigid mechanical structures, which were easy to cause damage to crop organs, and there were still challenges in terms of accuracy and biosafety. Emerging flexible sensors had attracted wide attention in the field of crop phenotype monitoring due to their excellent mechanical properties and biocompatibility. The article introduced the key technologies involved in the preparation of flexible wearable sensors from the aspects of flexible preparation materials and advanced preparation processes. The monitoring function of flexible sensors in crop growth was highlighted, including the monitoring of crop nutrient, physiological, ecological and growth environment information. The monitoring principle, performance together with pros and cons of each sensor were analyzed. Furthermore, the future opportunities and challenges of flexible wearable devices in crop monitoring were discussed in detail from the aspects of new sensing theory, sensing materials, sensing structures, wireless power supply technology and agricultural sensor network, which will provide reference for smart agricultural management system based on crop flexible sensors, and realize efficient management of agricultural production and resources.

Research on Biosensor Technology in Wearable Health Monitoring Equipment

In recent years, innovative and well-researched smart devices utilizing wearable biosensor systems for health monitoring have attracted much attention from society. These health monitoring devices, equipped with various transmission modules and miniature physiological sensors, are anticipated to alleviate the escalating healthcare expenses in the post-pandemic era by offering real-time, precise physiological information and persistent health status monitoring. Additionally, such health monitoring devices can provide tailored health advice and preventive measures for healthcare providers, potentially transforming the future of healthcare. Hence, their impact spans a broad and enduring spectrum in our daily lives. This paper aims to provide a comprehensive review of current technologies used for health monitoring and current trends, developments, and research in wearable biosensor systems for health monitoring. The focus is especially on the technical design of multiparameter physiological sensing systems and the challenges they face. Also, it discusses the ethical and data protection issues associated with these wearable biosensor systems. Finally, future research directions and perspectives on wearable biosensor devices are analyzed. Moreover, this paper serves as a resource for researchers and developers in this field, providing directions for future research advancements.

A pro-reparative bioelectronic device for controlled delivery of ions and biomolecules.

Wound healing is a complex physiological process that requires precise control and modulation of many parameters. Therapeutic ion and biomolecule delivery has the capability to regulate the wound healing process beneficially. However, achieving controlled delivery through a compact device with the ability to deliver multiple therapeutic species can be a challenge. Bioelectronic devices have emerged as a promising approach for therapeutic delivery. Here, we present a pro-reparative bioelectronic device designed to deliver ions and biomolecules for wound healing applications. The device incorporates ion pumps for the targeted delivery of H+ and zolmitriptan to the wound site. In vivo studies using a mouse model further validated the device's potential for modulating the wound environment via H+ delivery that decreased M1/M2 macrophage ratios. Overall, this bioelectronic ion pump demonstrates potential for accelerating wound healing via targeted and controlled delivery of therapeutic agents to wounds. Continued optimization and development of this device could not only lead to significant advancements in tissue repair and wound healing strategies but also reveal new physiological information about the dynamic wound environment.

A Narrative Review of In‐Textile Sensors in Human Health Applications

AbstractSensors have become more versatile and sophisticated in recent years to fulfill the increasing demands for human health applications. Physiological information such as electrocardiogram, pulse rate, and respiration are essential indications of personal health, often collected as vitals, which are typically collected from medical‐grade electrocardiogram (ECG) machines. In‐textile sensors are a fast‐growing sub‐category of wearable sensors embedded in smart textiles to acquire physiological information and movement index and provide harmful chemical warnings without compromising the comfortable nature of clothing. Recent literature has shown that integrating new materials has greatly improved the stability, specificity, and selectivity of in‐textile sensors. For example, polyvinylidene fluoride nanofiber produced a highly stretchable sensor to measure ECG readings during movement without losing data quality. This review discusses a group of nanomaterial‐based in‐textile sensors for consumer use in the home, workplace, and healthcare environments. This review will focus on exploring and analyzing the latest developments in these nanomaterial‐based e‐textiles due to their ability to be more easily integrated for daily use and their great potential for medical applications. Future work will be necessary to incorporate recycled materials, improve the method of powering these sensors, and ultimately refine the designs to be appropriate for more sustainable use.

Hyperspectral retinal imaging biomarkers of ocular and systemic diseases.

Hyperspectral imaging is a frontier in the field of medical imaging technology. It enables the simultaneous collection of spectroscopic and spatial data. Structural and physiological information encoded in these data can be used to identify and localise typically elusive biomarkers. Studies of retinal hyperspectral imaging have provided novel insights into disease pathophysiology and new ways of non-invasive diagnosis and monitoring of retinal and systemic diseases. This review provides a concise overview of recent advances in retinal hyperspectral imaging.

Innovative Material-Based Wearable Non-Invasive Electrochemical Sweat Sensors towards Biomedical Applications.

Sweat is an accessible biofluid that provides useful physiological information about the body's biomolecular state and systemic health. Wearable sensors possess various advantageous features, such as lightweight design, wireless connectivity, and compatibility with human skin, that make them suitable for continuous monitoring. Wearable electrochemical sweat sensors can diagnose diseases and monitor health conditions by detecting biomedical signal changes in sweat. This paper discusses the state-of-the-art research in the field of wearable sweat sensors and the materials used in their construction. It covers biomarkers present in sweat, sensing modalities, techniques for sweat collection, and ways to power these sensors. Innovative materials are categorized into three subcategories: sweat collection, sweat detection, and self-powering. These include substrates for sensor fabrication, analyte detection electrodes, absorbent patches, microfluidic devices, and self-powered devices. This paper concludes by forecasting future research trends and prospects in material-based wearable non-invasive sweat sensors.

Origami-inspired highly stretchable and breathable 3D wearable sensors for in-situ and online monitoring of plant growth and microclimate

The emerging wearable plant sensors demonstrate the capability of in-situ measurement of physiological and micro-environmental information of plants. However, the stretchability and breathability of current wearable plant sensors are restricted mainly due to their 2D planar structures, which interfere with plant growth and development. Here, origami-inspired 3D wearable sensors have been developed for plant growth and microclimate monitoring. Unlike 2D counterparts, the 3D sensors demonstrate theoretically infinitely high stretchability and breathability derived from the structure rather than the material. They are adjusted to 100% and 111.55 mg cm−2·h−1 in the optimized design. In addition to stretchability and breathability, the structural parameters are also used to control the strain distribution of the 3D sensors to enhance sensitivity and minimize interference. After integrating with corresponding sensing materials, electrodes, data acquisition and transmission circuits, and a mobile App, a miniaturized sensing system is produced with the capability of in-situ and online monitoring of plant elongation and microclimate. As a demonstration, the 3D sensors are worn on pumpkin leaves, which can accurately monitor the leaf elongation and microclimate with negligible hindrance to plant growth. Finally, the effects of the microclimate on the plant growth is resolved by analyzing the monitored data. This study would significantly promote the development of wearable plant sensors and their applications in the fields of plant phenomics, plant-environment interface, and smart agriculture.

A Perceptual and Interactive Integration Strategy Toward Telemedicine Healthcare Based on Electroluminescent Display and Triboelectric Sensing 3D Stacked Device

AbstractThe conventional medical assistive strategy for wearable devices involves sensing physiological signals and subsequent analysis while it lacks the capability for visual interaction and often necessitates the use of additional bulky devices for display. Herein, a perceptual and interaction strategy based on electroluminescent and triboelectric sensing 3D stacked wearable device (ETD) is proposed to address current issues. The ETD utilizes a bottom triboelectric sensor for tactile physiological information, which is processed and analyzed, ultimately triggering the selective illumination of the top electroluminescent array through external power circuitry. The ETD possesses the capability to generate a 100 V with 1.5 cm2 and stable visual interaction ability at 30 V drive voltage. Based on outstanding features of the ETD, two medical assistance scenarios are explored. I) The ETD captures physiological signals, such as pulse rate, respiratory rate, and special joint flexion, and in situ displays the corresponding physiological information, effectively assisting the patients/elders in self‐monitoring. II) A bidirectional interactive telemedicine assistive system utilizing ETDs is implemented, which not only gathers real‐time activity status from patients/elders but also realizes that remote physician assesses the safety status and the assessment results are wirelessly back‐communicated to the ETD, enabling real‐time interaction of the physician advice.

Rehabilitation Assessment System for Stroke Patients Based on Fusion-Type Optoelectronic Plethysmography Device and Multi-Modality Fusion Model: Design and Validation.

This study aimed to propose a portable and intelligent rehabilitation evaluation system for digital stroke-patient rehabilitation assessment. Specifically, the study designed and developed a fusion device capable of emitting red, green, and infrared lights simultaneously for photoplethysmography (PPG) acquisition. Leveraging the different penetration depths and tissue reflection characteristics of these light wavelengths, the device can provide richer and more comprehensive physiological information. Furthermore, a Multi-Channel Convolutional Neural Network-Long Short-Term Memory-Attention (MCNN-LSTM-Attention) evaluation model was developed. This model, constructed based on multiple convolutional channels, facilitates the feature extraction and fusion of collected multi-modality data. Additionally, it incorporated an attention mechanism module capable of dynamically adjusting the importance weights of input information, thereby enhancing the accuracy of rehabilitation assessment. To validate the effectiveness of the proposed system, sixteen volunteers were recruited for clinical data collection and validation, comprising eight stroke patients and eight healthy subjects. Experimental results demonstrated the system's promising performance metrics (accuracy: 0.9125, precision: 0.8980, recall: 0.8970, F1 score: 0.8949, and loss function: 0.1261). This rehabilitation evaluation system holds the potential for stroke diagnosis and identification, laying a solid foundation for wearable-based stroke risk assessment and stroke rehabilitation assistance.

Incorporating physiological knowledge into correlative species distribution models minimizes bias introduced by the choice of calibration area

Correlative species distribution models (SDMs) are important tools to estimate species’ geographic distribution across space and time, but their reliability heavily relies on the availability and quality of occurrence data. Estimations can be biased when occurrences do not fully represent the environmental requirement of a species. We tested to what extent species’ physiological knowledge might influence SDM estimations. Focusing on the Japanese sea cucumber Apostichopus japonicus within the coastal ocean of East Asia, we compiled a comprehensive dataset of occurrence records. We then explored the importance of incorporating physiological knowledge into SDMs by calibrating two types of correlative SDMs: a naïve model that solely depends on environmental correlates, and a physiologically informed model that further incorporates physiological information as priors. We further tested the models’ sensitivity to calibration area choices by fitting them with different buffered areas around known presences. Compared with naïve models, the physiologically informed models successfully captured the negative influence of high temperature on A. japonicus and were less sensitive to the choice of calibration area. The naïve models resulted in more optimistic prediction of the changes of potential distributions under climate change (i.e., larger range expansion and less contraction) than the physiologically informed models. Our findings highlight benefits from incorporating physiological information into correlative SDMs, namely mitigating the uncertainties associated with the choice of calibration area. Given these promising features, we encourage future SDM studies to consider species physiological information where available.

Enhancing quality assessment of live Pacific oysters (Crassostrea gigas) using flexible sensors real‐time monitoring physiological signals

AbstractShell‐closing strength (SCS) is commonly used to assess oyster vigor and quality as an important physiological stress indicator of the oyster organism. In this study, a quality decision support system based on flexible wireless sensor network and web services was designed and developed to explore the application of SCS in the rapid assessment of vitality and quality. Based on physiological and environmental information collected by flexible wireless sensor networks, this study proposes a novel quantitative vitality assessment method to identify oyster life decline cycles and processes. Meanwhile, TVB‐N, TVC, and pH were selected as quality indicators, and a back‐propagation artificial neural network (BP‐ANN) was used to predict and evaluate oyster quality indicators. The results showed that the root mean square errors (RMSE) for TVB‐N, TVC, and pH were 0.4624, 0.8827, and 0.1941; the coefficients of determination (R2) were 0.8919, 0.8578, and 0.6249. Therefore, the rapid assessment of oyster vitality and quality based on a flexible wireless sensor network is a reliable and effective means.Practical applicationsThis study aims to explore the application of live oyster SCS for rapid quality evaluation. In this article, a quality decision support system based on a flexible wireless sensor network (WSN) and web services is developed to improve the quality and health of live oysters in the supply chain. The use of the multi‐sensor system enables the monitoring and collection of environmental and physiological signals of live oysters throughout the supply chain process. The evaluation of the quality of live oysters using physiological and environmental information collected by flexible wireless sensor networks is a reliable and efficient method. This will provide an effective and reliable quality evaluation and management for the oyster industry.

Mind-enlightenment and observation: Analysis of ancient and modern weird pulse diagrams in " Guidelines for Disease Detection "

<p>脈診，是中醫重要的診斷方法。醫者手觸脈動引發主觀的判讀，因抽象體會難以言說，故歷來做了許多努力。早期以文字譬喻為主描述脈象，至宋代施發《察病指南》增見具象的脈象圖示。文章以七怪脈為主，比對古脈圖與現代脈儀圖，尋其特點與限制，或能為新世代的診斷尋找更合宜的時代範式。研究發現，古脈圖是傳統脈診心象運思的表徵，有輔助文字的重要作用。科技脈儀圖，則以心臟或血液動力學為基礎，如實記錄脈搏的波動訊號，從時域到高低頻譜以揭露生理病理的訊息。比較兩者，可各見特點與限制：古圖提供他人藉以揣摩，難以盡言的脈覺體會，其譬喻文圖的運用所載意義更為豐富固是優勢所在；然也因非邏輯性的傳訊而形成多樣的表達，這非客觀化的限制，正是當代醫家的修正努力與科診儀器強調的優處。另一方面，儀器診察雖有客觀、標準化的特點，但其測值是否能涵蓋生命的整體現象亦有質疑聲音。故兩者該並行析究：在傳統理論與現代儀器之間，嘗試建構一套能銜接古今的替代理論，或許能為新世代的脈診量測，提供一個較為周全的診斷依據。而中醫的脈圖分析能進入當代，參與W.J.T.Mitchell圖像轉向中，生物圖像研究的子題是無疑的。</p> <p> </p><p>This article mainly focuses on the seven weird pulses, compares ancient pulse diagrams and modern pulse diagrams, and seeks out their characteristics and limitations, hoping to find a more suitable paradigm for the diagnosis of the new generation. Research has found that ancient pulse diagrams are representations of mental images and thoughts in traditional pulse diagnosis, and play an important role in supporting text. The technological pulse chart is based on heart or hemodynamics and faithfully records pulse fluctuation signals from time domain to high and low frequency spectrum to reveal physiological and pathological information. Comparing the two, we can see the characteristics and limitations of each: the ancient pictures provide others with an indescribable pulse-sensing experience, and the use of metaphors and pictures contains richer meanings, which is an advantage; however, it is also illogical Forming diverse expressions through communication, this non-objectification limitation is exactly the advantage emphasized by the revision efforts of contemporary doctors and medical diagnostic equipment. On the other hand, although instrumental diagnosis has the characteristics of being objective and standardized, there are also doubts about whether its measured values can cover the overall phenomenon of life. Therefore, the two should be analyzed in parallel: between traditional theory and modern instruments, trying to construct an alternative theory that can connect ancient and modern times may provide a more comprehensive diagnostic basis for pulse diagnosis and measurement in the new generation. The pulse diagram analysis of TCM can enter the contemporary era and participate in W.J.T. Mitchell’s pictorial turn. There is no doubt that it is a sub-topic of biological image research.</p> <p> </p>

Valuable Predictors for Non-measurability of Fractional Flow Reserve Derived From Coronary Computed Tomography Angiography.

Background The fractional flow reserve (FFR) derived from coronary computed tomography (CT) angiography (FFRCT) is a variable tool for coronary disease diagnosis that non-invasively provides the value of FFR. It can add physiological information tocoronary CT angiography (CCTA) and reduce unnecessary invasive coronary angiography (CAG). However, it cannot be analyzed in some cases, which is also called "non-measurability." While FFRCT has become globally widespread, the current data on non-measurability are lacking. This study aimed to determine the rate of non-measurability and identify predictors thereof in routine clinical settings to explore potential approaches to reduce the non-measurability rate. Methods and results This retrospective observational single-center studyincluded consecutive patients who underwent FFRCTanalysis in Japan. The mean age of the overall population was 71.3 ± 10.6, and an FFRCTof ≤0.8 was seen in 47.6% of patients with a measurable FFRCT. Of the 307 enrolled patients, FFRCT analysis was not feasible in 21 cases (6.8%). Heart rate (HR) at a CT scan and coronary calcium scores (CCS) were significantly higher in patients with non-measurability than those in patients whose FFRCT was appropriately analyzed (HR: 69.6±8.9 bpm vs. 61.0±11.1 bpm; p < 0.01; CCS; 931.2 (290.8, 1451.3) vs. 322.9 (100.7, 850.0); p < 0.01). Multiplelogisticregression showed that HR was an independent predictor for non-measurability (odds ratio: 1.05; 95% confidential interval: 1.02, 1.09; p < 0.01)). Based on the receiver operating characteristic curve analysis, the optimal cut-off value of HR and CCS was 63 bpm (specificity: 67.1%; sensitivity: 76.2%) and 729.2 (specificity: 71.3%; sensitivity: 66.7%). In addition, the combination of two features (HR > 63 bpm and CCS > 729.2) showed a high negative predictive value (99.3%) for FFRCT non-measurability. Conclusions In this study, the rate of FFRCTnon-measurability was 6.8%. Higher HR at a CT scan and CCS were significantly associated with non-measurability, and in cases with both HR and CCS below a specified threshold, the likelihood of ruling out non-measurability could be significantly high. Our findings suggest that reducing the HR to ideally under 63 bpm at the time of the CT scan significantly ensures feasibility. Further study on large-scale cohorts is warranted.

Deep neural network-based plant protection strategy in rural garden landscape construction

Rural landscaping enhances the quality of the environment in rural areas by planting trees and flowers and plants and at the same time can contribute to the protection of plants in rural areas. The occurrence and development of landscape plant diseases are very insidious, which may lead to poor tree growth and affect the annual growth of timber, or even lead to the death of the whole forest and the reverse succession of the forest. Plant leaf disease lesion location is random, and plant leaf image shooting is susceptible to light, background, angle and other objective factors can only rely on artificial identification, but the traditional artificial identification and physiological information extraction methods such as low accuracy, low efficiency and cumbersome. The rapid development of deep neural networks provides an effective solution for plant leaf recognition based on image analysis. In this paper, a DCA-ResNet model is constructed based on ResNet101 to recognize plant leaves by introducing the attention mechanism and optimizing the model structure. The validation of the DCA-ResNet model using public datasets on three species of plant leaves and plant leaf diseases achieved accuracy rates of 96.79%, 96.64%, and 96.44%, respectively.

Exploring functional metabolites and proteomics biomarkers in late-preterm and natural-born pigs.

Pigs are often used to study the intestinal development of newborns, particularly as preterm pig models that mimic the intestinal growth of human preterm infants. Neonatology's study of delivery mode's impact on neonatal development is crucial. We established 14 newborn pigs delivered via cesarean sections (C-section, at 113 days of gestational age, CS group) and 8 naturally born pigs were used as controls (at 114 days of gestational age, NF group). The impact of two alternative delivery procedures (C-section and natural birth) on the levels of short-chain fatty acids (SCFAs) and organic acids in the hepatic and intestines of newborn pigs were compared using metabolomics. The underlying molecular pathways are examined at the "protein-metabolite" level by integrating proteomic data. The findings demonstrated that the mode of delivery changed the metabolism of SCFAs in newborn pigs, perhaps by affecting the physiology levels of cyclic intermediates such as lactate and malate in the pyruvate metabolic pathway. Additionally, by participating in the fatty acid metabolism pathway, two distinct proteins (FASN and HSD17B4) may impact the physiological concentration of these tiny metabolites. In conclusion, this study provided reliable animal model data for understanding the physiological SCFA metabolic information and its affecting mechanism of large-gestational age preterm infants.

Exploring neural motion transfer for unsupervised remote physiological measurement: A practicality study

Remote Photoplethysmography (rPPG) is a method to measure cardiac activity without the need for any contact-based sensors, garnering attention due to its non-invasive and convenient nature. Addressing the issue of substantial missing data in large-scale datasets, current research is inclined towards unsupervised learning methods. However, prevailing unsupervised learning methods often prioritize inter-sample comparative learning while neglecting individual sample features, severely impacting performance and generalizability. Meanwhile, body movement is one of the most important influencing factors when attempting to extract the rPPG signal from videos. Hence, we embarked on the inaugural exploration of integrating Neural Motion Transfer into unsupervised learning methods for remote physiological measurements, aiming to enrich the inherent motion characteristics and diversity of samples. Employing Neural Motion Transfer, we synthesized videos encompassing diverse movements as a means of data augmentation. Through an in-depth comparison with other synthetic video methods, we extensively analyzed the physiological information within motion-enhanced synthetic videos. We investigated the applicability of these motion-enhanced synthetic videos to unsupervised learning methods and various associated impacts. We conducted extensive experiments on four benchmark datasets. After utilizing motion-enhanced synthetic videos to aid unsupervised training, our approach achieved an improvement of approximately 52% in intra-dataset testing and up to 97% in cross-dataset testing compared to the baseline unsupervised method, achieving the state-of-the-art (SOTA) performance among current unsupervised methods. Our research underscores the importance of neural motion networks in enhancing unsupervised learning methods and highlights the significant potential of synthetic videos.

Application of artificial intelligence digital holography technology based on medical sensors in the development of medical image fusion

With the rapid development of artificial intelligence and medical technology, sensor technology, as an important tool to obtain medical data, provides a wealth of physiological parameter information, but the traditional medical image fusion methods are difficult to make full use of the information provided by sensors. Therefore, this paper aims to explore the application of artificial intelligence digital holographic technology based on medical sensor in medical image fusion, and improve the accuracy and effect of medical image diagnosis and treatment. Based on the physiological parameter data obtained by medical sensor, combined with deep learning and image processing algorithm, a medical image fusion method based on artificial intelligence digital holography technology was proposed. The method uses the physiological parameter information provided by the sensor and combines multiple medical image sources to realize holographic medical image presentation. The experimental results show that the artificial intelligence digital holographic technology based on medical sensor can effectively improve the resolution and information content of medical image fusion. Compared with traditional medical image fusion methods, this method has higher image quality and more accurate diagnosis results.

The Role of High-Resolution Manometry Prior to and Following Antireflux Surgery: The Padova Consensus.

In the last two decades the development of high-resolution manometry (HRM) has changed and revolutionized the diagnostic assessment of patients complain foregut symptoms. The role of HRM before and after antireflux procedure remains unclear, especially in surgical practice, where a clear understanding of esophageal physiology and hiatus anatomy is essential for optimal outcome of antireflux surgery (ARS). Surgeons and gastroenterologists (GIs) agree that assessing patients following antireflux procedures can be challenging. Although endoscopy and barium-swallow can reveal anatomic abnormalities, physiologic information on HRM allowing insight into the cause of eventually recurrent symptoms could be key to clinical decision making. A multi-disciplinary international working group (14 surgeons and 15 GIs) collaborated to develop consensus on the role of HRM pre- and post- ARS, and to develop a postoperative classification to interpret HRM findings. The method utilized was detailed literature review to develop statements, and the RAND/University of California, Los Angeles Appropriateness Methodology (RAM) to assess agreement with the statements. Only statements with an approval rate >80% or a final ranking with a median score of 7 were accepted in the consensus. The working groups evaluated the role of HRM prior to ARS and the role of HRM following ARS. This international initiative developed by surgeons and GIs together, summarizes the state of our knowledge of the use of HRM pre- and post-ARS. The Padova Classification was developed to facilitate the interpretation of HRM studies of patients underwent ARS.

Deep learned triple-tracer multiplexed PET myocardial image separation.

In multiplexed positron emission tomography (mPET) imaging, physiological and pathological information from different radiotracers can be observed simultaneously in a single dynamic PET scan. The separation of mPET signals within a single PET scan is challenging due to the fact that the PET scanner measures the sum of the PET signals of all the tracers. The conventional multi-tracer compartment modeling (MTCM) method requires staggered injections and assumes that the arterial input functions (AIFs) of each tracer are known. In this work, we propose a deep learning-based method to separate triple-tracer PET images without explicitly knowing the AIFs. A dynamic triple-tracer noisy MLEM reconstruction was used as the network input, and dynamic single-tracer noisy MLEM reconstructions were used as training labels. A simulation study was performed to evaluate the performance of the proposed framework on triple-tracer ([ ]FDG+ +[ ]sestamibi) PET myocardial imaging. The results show that the proposed methodology substantially reduced the noise level compared to the results obtained from single-tracer imaging. Additionally, it achieved lower bias and standard deviation in the separated single-tracer images compared to the MTCM-based method at both the voxel and region of interest (ROI) levels. As compared to MTCM separation, the proposed method uses spatiotemporal information for separation, which improves the separation performance at both the voxel and ROI levels. The simulation study also demonstrates the feasibility and potential of the proposed DL-based method for the application to pre-clinical and clinical studies.