Multi-modal Monitoring Approach Research Articles

Crop Growth Analysis Using Automatic Annotations and Transfer Learning in Multi-Date Aerial Images and Ortho-Mosaics

Growth monitoring of crops is a crucial aspect of precision agriculture, essential for optimal yield prediction and resource allocation. Traditional crop growth monitoring methods are labor-intensive and prone to errors. This study introduces an automated segmentation pipeline utilizing multi-date aerial images and ortho-mosaics to monitor the growth of cauliflower crops (Brassica Oleracea var. Botrytis) using an object-based image analysis approach. The methodology employs YOLOv8, a Grounding Detection Transformer with Improved Denoising Anchor Boxes (DINO), and the Segment Anything Model (SAM) for automatic annotation and segmentation. The YOLOv8 model was trained using aerial image datasets, which then facilitated the training of the Grounded Segment Anything Model framework. This approach generated automatic annotations and segmentation masks, classifying crop rows for temporal monitoring and growth estimation. The study’s findings utilized a multi-modal monitoring approach to highlight the efficiency of this automated system in providing accurate crop growth analysis, promoting informed decision-making in crop management and sustainable agricultural practices. The results indicate consistent and comparable growth patterns between aerial images and ortho-mosaics, with significant periods of rapid expansion and minor fluctuations over time. The results also indicated a correlation between the time and method of observation which paves a future possibility of integration of such techniques aimed at increasing the accuracy in crop growth monitoring based on automatically derived temporal crop row segmentation masks.

Evaluation of an aPTT guided versus a multimodal heparin monitoring approach in patients on extra corporeal membrane oxygenation: A retrospective cohort study.

Bleeding and thrombotic complications are common in extracorporeal membrane oxygenation (ECMO) patients and are associated with increased mortality and morbidity. The optimal anticoagulation monitoring protocol in these patients is unknown. This study aims to compare the incidence of thrombotic and hemorrhagic complications before and after a protocol change. In addition, the association between hemostatic complications, coagulation tests and risk factors is evaluated. This is a retrospective single center cohort study of adult ECMO patients. We collected demographics, ECMO parameters and coagulation test results. Outcomes of the aPTT guided and multimodal protocol, including aPTT, anti-Xa assay and rotational thromboelastometry were compared and the association between coagulation tests, risk factors and hemostatic complications was determined using a logistic regression analysis for repeated measurements. In total, 250 patients were included, 138 in the aPTT protocol and 112 in the multimodal protocol. The incidence of thrombosis (aPTT: 14%; multimodal: 12%) and bleeding (aPTT: 36%; multimodal: 40%), did not significantly differ between protocols. In the aPTT guided protocol, the aPTT was associated with thrombosis (Odds Ratio [OR] 1.015; 95% confidence interval [CI] 1.004-1.027). In both protocols, surgical interventions were risk factors for bleeding and thrombotic complications (aPTT: OR 93.2, CI 39.9-217.6; multimodal OR 17.5, CI 6.5-46.9). The incidence of hemostatic complications was similar between both protocols and surgical interventions were a risk factor for hemostatic complications. Results from this study help to elucidate the role of coagulation tests and risk factors in predicting hemostatic complications in patients undergoing ECMO support.

Workflow of a Preclinical Robotic Magnetic Resonance Imaging-guided Focused Ultrasound Body System

Abstract Background: Establishing an efficient workflow is crucial for the success of magnetic resonance-guided focused ultrasound (MRgFUS) procedures. The current study provides a comprehensive description of the workflow of a customized MRgFUS robotic body device for preclinical use and accompanied software through experiments in excised porcine tissue. Methods: The employed system comprises a single-element spherically focused transducer of 2.6 MHz that can be moved along four PC-controlled axes. A detailed description of essential software functionalities and its integration with a 3T Siemens magnetic resonance imaging (MRI) scanner through Access-I for interactive remote control of the scanner and real-time access to imaging data is provided. Following treatment planning on preoperative MR images, porcine tissue samples were sonicated in rectangular and irregular grid patterns with varying ultrasonic parameters and spatial step under software-based monitoring. Results: MRgFUS ablations of ex vivo porcine tissue were successfully performed utilizing a multimodal monitoring approach combining MRI-based temperature, thermal dose, and necrotic area mapping, thus demonstrating an efficient procedural workflow. The simulated necrotic regions were in excellent agreement with the actual lesions revealed upon tissue dissection and highly consistent with the planned sonication patterns. The software’s ability to accurately identify regions where necrosis did not occur and indicate to the user the specific points to be re-sonicated was demonstrated. Conclusion: Overall, the study highlights critical aspects in accurately planning and executing preclinical MRgFUS protocols within an efficient workflow. The provided data could serve as the basis for other researchers in the field.

Activity in Group-Housed Home Cages of Mice as a Novel Preclinical Biomarker in Oncology Studies.

Improving experimental conditions in preclinical animal research is a major challenge, both scientifically and ethically. Automated digital ventilated cages (DVC®) offer the advantage of continuous monitoring of animal activity in their home-cage. The potential utility of this technology remains understudied and deserves investigation in the field of oncology. Using the DVC® platform, we sought to determine if the continuous assessment of locomotor activity of mice in their home cages can serve as useful digital readout in the monitoring of animals treated with the reference oncology compounds cisplatin and cyclophosphamide. SCID mice of 14 weeks of age were housed in DVC® cages in groups of four and followed with standard and digital examination before and after treatment over a 17-day total period. DVC® detected statistically significant effects of cisplatin on the activity of mice in the short and long term, as well as trends for cyclophosphamide. The activity differences between the vehicle- and chemotherapy-treated groups were especially marked during the nighttime, a period when animals are most active and staff are generally not available for regular checks. Standard clinical parameters, such as body weight change and clinical assessment during the day, provided additional and complementary information. The DVC® technology enabled the home cage monitoring of mice and non-invasive detection of animal activity disturbances. It can easily be integrated into a multimodal monitoring approach to better capture the different effects of oncology drugs on anti-tumor efficacy, toxicity, and safety and improve translation to clinical studies.

Sleep problems predict next-day suicidal thinking among adolescents: A multimodal real-time monitoring study following discharge from acute psychiatric care

AbstractSuicidal thoughts and behaviors (STBs) are major public health concerns among adolescents, and research is needed to identify how risk is conferred over the short term (hours and days). Sleep problems may be associated with elevated risk for STBs, but less is known about this link in youth over short time periods. The current study utilized a multimodal real-time monitoring approach to examine the association between sleep problems (via daily sleep diary and actigraphy) and next-day suicidal thinking in 48 adolescents with a history of STBs during the month following discharge from acute psychiatric care. Results indicated that specific indices of sleep problems assessed via sleep diary (i.e., greater sleep onset latency, nightmares, ruminative thoughts before sleep) predicted next-day suicidal thinking. These effects were significant even when daily sadness and baseline depression were included in the models. Moreover, several associations between daily-level sleep problems and next-day suicidal thinking were moderated by person-level measures of the construct. In contrast, sleep indices assessed objectively (via actigraphy) were either not related to suicidal thinking or were related in the opposite direction from hypothesized. Together, these findings provide some support for sleep problems as a short-term risk factor for suicidal thinking in high-risk adolescents.

The role of rotational thromboelastometry during the COVID-19 pandemic: a narrative review.

The coronavirus disease 2019 (COVID-19) pandemic is currently recognized as a global health crisis. This viral infection is frequently associated with hypercoagulability, with a high incidence of thromboembolic complications that can be fatal. In many situations, the standard coagulation tests (SCT) fail to detect this state of hypercoagulability in patients with COVID-19 since clotting times are either not or only mildly affected. The role of viscoelastic tests such as rotational thromboelastometry (ROTEM®) during this pandemic is explored in this review. COVID-19-associated coagulopathy, as measured using the rotational thromboelastometry parameters, can vary from hypercoagulability due to increased fibrin polymerization and decreased fibrinolysis to bleeding from hypocoagulability. The use of a multimodal diagnostic and monitoring approach, including both rotational thromboelastometry and SCT, such as plasma fibrinogen and D-dimer concentrations, is recommended. Rotational thromboelastometry provides comprehensive information about the full coagulation status of each patient and detects individual variations. Since COVID-19-associated coagulopathy is a very dynamic process, the phenotype can change during the course of infection and in response to anticoagulation therapy. Data from published literature provide evidence that the combination of rotational thromboelastometry and SCT analysis is helpful in detecting hemostasis issues, guiding anticoagulant therapy, and improving outcomes in COVID-19 patients. However, more research is needed to develop evidence-based guidelines and protocols.

Improving the spatial and temporal monitoring of cyanotoxins in Iowa lakes using a multiscale and multi-modal monitoring approach

Cyanobacterial harmful algal blooms (CyanoHABs) are pervasive and negatively impact lake water quality, resulting in economic losses and public health risks through exposure to cyanotoxins. Therefore, it is critical to better monitor and understand the complexity of CyanoHABs, but current methods do not fully describe the spatial and temporal variability of bloom events. In this work, we developed a framework for a multiscale and multi-modal monitoring approach for CyanoHABs combining drone-based near-range remote sensing with analytical measurements of microcystin cyanotoxins and chlorophyll-a. We analyzed weekly beach monitoring samples from 37 lakes geographically distributed across the state of Iowa (USA) over a 15-week period in the summer of 2019 to quantify ELISA (bioassay), 12 microcystin congeners (LC-MS/MS), and chlorophyll-a. We developed a novel microcystin congener-normalized equivalent toxin metric to compare CyanoHAB impacted waters; this microcystin-LR normalized sum-of-congeners approach yields lower predicted toxicity than parallel ELISA results suggesting ELISA is conservative for assessment. A significant linear relationship existed between chlorophyll-a and microcystin for lakes throughout Iowa (R2 = 0.39, p < 0.001); lakes with low watershed:lake area ratio and long residence times exhibited a stronger correlation. We then developed a novel geometry-based image processing approach to allow for stitching over-water drone images, a previous barrier in photogrammetry. We applied our mutli-modal framework to a case study on Green Valley Lake to assess initial viability and predicted microcystin concentrations within 33%. We concluded that multispectral imaging is possible but may presently be insufficient for predicting microcystin concentrations due to limitations in the spectral capabilities of the multispectral camera, but technologies are quickly advancing, and lightweight hyperspectral imaging could soon become feasible for investigating spatial bloom variability on lakes.

Nutrition Therapy, Glucose Control, and Brain Metabolism in Traumatic Brain Injury: A Multimodal Monitoring Approach.

The goal of neurocritical care in patients with traumatic brain injury (TBI) is to prevent secondary brain damage. Pathophysiological mechanisms lead to loss of body mass, negative nitrogen balance, dysglycemia, and cerebral metabolic dysfunction. All of these complications have been shown to impact outcomes. Therapeutic options are available that prevent or mitigate their negative impact. Nutrition therapy, glucose control, and multimodality monitoring with cerebral microdialysis (CMD) can be applied as an integrated approach to optimize systemic immune and organ function as well as adequate substrate delivery to the brain. CMD allows real-time bedside monitoring of aspects of brain energy metabolism, by measuring specific metabolites in the extracellular fluid of brain tissue. Sequential monitoring of brain glucose and lactate/pyruvate ratio may reveal pathologic processes that lead to imbalances in supply and demand. Early recognition of these patterns may help individualize cerebral perfusion targets and systemic glucose control following TBI. In this direction, recent consensus statements have provided guidelines and recommendations for CMD applications in neurocritical care. In this review, we summarize data from clinical research on patients with severe TBI focused on a multimodal approach to evaluate aspects of nutrition therapy, such as timing and route; aspects of systemic glucose management, such as intensive vs. moderate control; and finally, aspects of cerebral metabolism. Research and clinical applications of CMD to better understand the interplay between substrate supply, glycemic variations, insulin therapy, and their effects on the brain metabolic profile were also reviewed. Novel mechanistic hypotheses in the interpretation of brain biomarkers were also discussed. Finally, we offer an integrated approach that includes nutritional and brain metabolic monitoring to manage severe TBI patients.

Hydroacoustic and Pressure Turbulence Analysis for the Assessment of Fish Presence and Behavior Upstream of a Vertical Trash Rack at a Run-of-River Hydropower Plant

The spatial distribution of fish upstream of a vertical trash rack was investigated at the hydropower plant Kirchbichl in the alpine River Inn (Tyrol, Austria). The objective of the research project “FIDET” was to establish a non-invasive methodology to study fish presence and flow characteristics at large hydro power sites. A new monitoring approach was developed combining hydroacoustic observations of fish locations with multivariate hydrodynamic data. This was accomplished by utilizing complementary observations from multiple underwater sensor technologies: First, an array of echosounders were deployed at a fixed cross-section upstream of the trash rack for long-term monitoring. Afterwards, detailed underwater surveys with “acoustic cameras” (DIDSON and ARIS) revealed that the spatial distributions of fish in front of the trash rack were highly heterogeneous. The spatial distribution of the flow field was assessed via the time-averaged velocity fields from acoustic Doppler current profiler (ADCP). Finally, a custom pressure-based flow turbulence probe was developed, providing spatial estimates of flow turbulence immediately upstream of the trash rack. The significant contribution of this work is to provide a multi-modal monitoring approach incorporating both fish position data and hydrodynamic information. This forms the starting point for a future objective, namely to create an automated, sonar-based detection and control systems to assist and monitor fish protection operations in near real-time.

Cerebral Function and Perfusion during Cardiopulmonary Bypass: A Plea for a Multimodal Monitoring Approach.

Postoperative neurological injury still represents a major cause of morbidity after cardiac surgery. Our objective was to compare the limits as well as advantages of routine monitoring tools for the detection of cerebral function and perfusion deficits during cardiopulmonary bypass in a daily clinical setting. Adult patients undergoing elective cardiac surgery with use of cardiopulmonary bypass were included. Patients received monitoring comprising Bispectral Index (BIS), Near Infrared Spectroscopy (NIRS) and assessment of middle cerebral artery flow velocity (MCAV) using transcranial Doppler (TCD) sonography. Measurements were taken after anesthesia induction (at baseline) and every 10 minutes during aortic cross-clamping. Relative deviation from baseline values was calculated. Values were compared with predefined, generally accepted threshold values identifying patients at risk for cerebral functional and perfusion deficits. 30 consecutive patients were included into data analysis. Compared to NIRS as well as BIS monitoring, there was a wide interindividual variability in relative MCAV values for the whole cohort (median 0.9, range 0.39-2.19). Out of 229 measurements in total, 82 BIS but only 30 NIRS and 12 TCD values were lying outside predefined limits. TCD monitoring identified two patients with disturbed cerebral autoregulation, while NIRS remained unremarkable. The latter was significantly associated with systemic hemoglobin levels. Finally, patients with relative MCAV values >1.0 had a higher risk of developing postoperative delirium. Our findings reveal inherent technical limitations of each individual monitoring component, such as high interindividual variability (TCD), low spatial resolution (NIRS), or interaction with anesthetics (BIS). We therefore argue for a multimodal neuromonitoring that combines several qualities. Such approach would help reducing these limitations while individual components complement each other, thus providing more patient safety during cardiac surgery. Furthermore, such an approach would be easily applicable in a routine clinical setting.

Monitoring the Neuroinflammatory Response Following Acute Brain Injury.

Traumatic brain injury (TBI) and subarachnoid hemorrhage (SAH) are major contributors to morbidity and mortality. Following the initial insult, patients may deteriorate due to secondary brain damage. The underlying molecular and cellular cascades incorporate components of the innate immune system. There are different approaches to assess and monitor cerebral inflammation in the neuro intensive care unit. The aim of this narrative review is to describe techniques to monitor inflammatory activity in patients with TBI and SAH in the acute setting. The analysis of pro- and anti-inflammatory cytokines in compartments of the central nervous system (CNS), including the cerebrospinal fluid and the extracellular fluid, represent the most common approaches to monitor surrogate markers of cerebral inflammatory activity. Each of these compartments has a distinct biology that reflects local processes and the cross-talk between systemic and CNS inflammation. Cytokines have been correlated to outcomes as well as ongoing, secondary injury progression. Alongside the dynamic, focal assay of humoral mediators, imaging, through positron emission tomography, can provide a global in vivo measurement of inflammatory cell activity, which reveals long-lasting processes following the initial injury. Compared to the innate immune system activated acutely after brain injury, the adaptive immune system is likely to play a greater role in the chronic phase as evidenced by T-cell-mediated autoreactivity toward brain-specific proteins. The most difficult aspect of assessing neuroinflammation is to determine whether the processes monitored are harmful or beneficial to the brain as accumulating data indicate a dual role for these inflammatory cascades following injury. In summary, the inflammatory component of the complex injury cascade following brain injury may be monitored using different modalities. Using a multimodal monitoring approach can potentially aid in the development of therapeutics targeting different aspects of the inflammatory cascade and improve the outcome following TBI and SAH.

The thermodynamic brain.

Apart from its complex functionality, the brain is a robust thermodynamic machine; the tissue metabolic rate is high and it is thermally shielded by a skull. Therefore, if there is no high-volume blood flow to cool and stabilize the brain temperature, the possibility of unstable behavior seems to be high. Inflowing arterial blood is normally cooler than the brain tissue temperature, and outflowing venous blood is normally warmer than arterial blood but cooler than the brain tissue. Brain blood flow can thus be understood as a cooler for the brain. Pros and cons of clinical measurement, with clear indication for a multimodal monitoring approach, are discussed along with a brief review of basic facts known about temperature, cerebral blood flow and volume, intracranial pressure, and compartmental compliances of the brain.

The Balance Between Effective Opioid-Based Pain Management and Patient Safety: Can It Be Achieved?

The Balance Between Effective Opioid-Based Pain Management and Patient Safety: Can It Be Achieved?

89. Facial nerve monitoring during cerebellopontine angle surgery: Our experience

Intraoperative facial nerve neuromonitoring (FN-IOM) has been established as one of the methods by which neurosurgery can improve surgical results while reducing morbidity. Despite routine use of FN-IOM, FN injury is still a complication of major concern due to severe impact on patient’s quality of life. Currently, standard monitoring techniques comprise direct electrical stimulation (DES), free-running electromyography (EMG) and facial motor evoked potential (FMEP). Recently, intraoperative recording of Blink Reflex (BR) can also be used. We report our experience of FN-IOM in 56 patients who underwent surgery for cerebellopontine angle tumors, trigeminal neuralgias or hemifacial spasms. FN was monitored with DES, EMG and, in 19 patients, also with BR. Facial nerve outcomes were evaluated one week and six months after surgery using the House–Brackmann scale (HB). Nine patients (16,1%) had HB grade III–VI function at 6 months after surgery. Individually, DES and EMG can predict FN function at 6 months, but used together, in a multimodal monitoring approach, the sensibility is higher. BR can predict FN function only one week after surgery. With our experience we want to emphasize the role of multimodal FN monitoring and its impact on facial nerve function preservation.

Interactive Multimodal Ambulatory Monitoring to Investigate the Association between Physical Activity and Affect

Although there is a wealth of evidence that physical activity has positive effects on psychological health, a large proportion of people are inactive. Data regarding counts, steps, and movement patterns are limited in their ability to explain why people remain inactive. We propose that multimodal ambulatory monitoring, which combines the assessment of physical activity with the assessment of psychological variables, helps to elucidate real world physical activity. Whereas physical activity can be monitored continuously, psychological variables can only be assessed at discrete intervals, such as every hour. Moreover, the assessment of psychological variables must be linked to the activity of interest. For example, if an inactive and overweight person is physically active once a week, psychological variables should be assessed during this episode. Linking the assessment of psychological variables to episodes of an activity of interest can be achieved with interactive monitoring. The primary aim of our interactive multimodal ambulatory monitoring approach was to intentionally increase the number of e-diary assessments during “active” episodes. We developed and tested an interactive monitoring algorithm that continuously monitors physical activity in everyday life. When predefined thresholds are surpassed, the algorithm triggers a signal for participants to answer questions in their electronic diary. Using data from 70 participants wearing an accelerative device for 24 h each, we found that our algorithm quadrupled the frequency of e-diary assessments during the activity episodes of interest compared to random sampling. Multimodal interactive ambulatory monitoring appears to be a promising approach to enhancing our understanding of real world physical activity and movement.

Modeling and performance monitoring of multivariate multimodal processes

A multimodal modeling and monitoring approach based on maximum likelihood principal component analysis and a component‐wise identification of operating modes are presented. Analyzing each principal component individually allows separating components describing the variation within the individual modes from those capturing variation which the modes commonly share. On the basis of the former set, a Gaussian mixture model produces a statistical fingerprint that describes the production modes. The advantage of the component‐wise analysis is a simple identification of the mixture model parameters, which does not rely on the computationally cumbersome expectation maximization. The proposed method diagnoses abnormal process conditions by defining statistics relating to the components describing (1) between‐cluster variation, (2) within cluster variation, and (3) model residuals. The article demonstrates the benefits of this approach over existing work by an application to a continuous stirred tank reactor (CSTR) simulator and the analysis of recorded data from a furnace and a chemical reaction process. © 2012 American Institute of Chemical Engineers AIChE J, 59: 1557–1569, 2013