Culturing Cardiac Tissue Slices Under Continuous Physiological Mechanical Stretches.

Testing drugs in vivo and in vitro have been essential elements for the discovery of new therapeutics. Due to the recent advances in in vitro cell culture models, such as human-induced pluripotent stem cell-derived cardiomyocytes and 3D multicell type organoid culture methods, the detection of adverse cardiac events prior to human clinical trials has improved. However, there are still numerous therapeutics whose adverse cardiac effects are not detected until human trials due to the inability of these cell cultures to fully model the complex multicellular organization of an intact human myocardium. Cardiac tissue slices are a possible alternative solution. Myocardial slices are a 300-micron thin snapshot of the myocardium, capturing a section of the adult heart in a 1 × 1 cm section. Using a culture method that incorporates essential nutrients and electrical stimulation, tissue slices can be maintained in culture for 6 days with full viability and functionality. With the addition of mechanical stimulation and humoral cues, tissue slices can be cultured for 12 days. Here we provide detailed methods for how to culture cardiac tissue slices under continuous mechanical stimulation in the cardiac tissue culture model (CTCM) device. The CTCM incorporates four essential factors for maintaining tissue slices in culture for 12 days: mechanical stimulation, electrical stimulation, nutrients, and humoral cues. The CTCM can also be used to model disease conditions, such as overstretch-induced cardiac hypertrophy. The versatility of the CTCM illustrates its potential to be a medium-throughput screening platform for personalized drug testing.

Study on the hemodynamic effects of different pulsatile working modes of a rotary blood pump using a microfluidic platform that realizes in vitro cell culture effectively.

Rotary blood pumps (RBPs) operating at a constant speed generate non-physiologic blood pressure and flow rate, which can cause endothelial dysfunction, leading to adverse clinical events in peripheral blood vessels and other organs. Notably, pulsatile working modes of the RBP can increase vascular pulsatility to improve arterial endothelial function. However, the laws and related mechanisms of differentially regulating arterial endothelial function under different pulsatile working modes are still unclear. This knowledge gap hinders the optimal selection of the RBP working modes. To address these issues, this study developed a multi-element in vitro endothelial cell culture system (ECCS), which could realize in vitro cell culture effectively and accurately reproduce blood pressure, shear stress, and circumferential strain in the arterial endothelial microenvironment. Performance of this proposed ECCS was validated with numerical simulation and flow experiments. Subsequently, this study investigated the effects of four different pulsation frequency modes that change once every 1-4-fold cardiac cycles (80, 40, 80/3, and 20 cycles per min, respectively) of the RBP on the expression of nitric oxide (NO) and reactive oxygen species (ROS) in endothelial cells. Results indicated that the 2-fold and 3-fold cardiac cycles significantly increased the production of NO and prevented the excessive generation of ROS, potentially minimizing the occurrence of endothelial dysfunction and related adverse events during the RBP support, and were consistent with animal study findings. In general, this study may provide a scientific basis for the optimal selection of the RBP working modes and potential treatment options for heart failure.

Numerical simulation analysis of multi-scale computational fluid dynamics on hemodynamic parameters modulated by pulsatile working modes for the centrifugal and axial left ventricular assist devices.

Continuous flow (CF) left ventricular assist devices (LVAD) operate at a constant speed mode, which could result in increased risk of adverse events due to reduced vascular pulsatility. Consequently, pump speed modulation algorithms have been proposed to augment vascular pulsatility. However, the quantitative local hemodynamic effects on the aorta when the pump is operating with speed modulation using different types of CF-LVADs are still under investigation. The computational fluid dynamics (CFD) study was conducted to quantitatively elucidate the hemodynamic effects on a clinical patient-specific aortic model under different speed patterns of CF-LVADs. Pressure distribution, wall shear stress (WSS), time-averaged wall shear stress (TAWSS), oscillatory shear index (OSI), relative residence time (RRT), and velocity were calculated to compare their differences at constant and pulsatile speeds under centrifugal and axial LVAD support. Results showed that pulse pressure on the aorta was significantly larger under pulsatile speed mode than that under constant speed mode for both CF-LVADs, indicating enhanced aorta pulsatility, as well as the higher peak blood flow velocity on some representative slices of aorta. Pulsatile speed modulation enhanced peak WSS compared to constant speed; high TAWSS region appeared near the branch of left common carotid artery and distal aorta regardless of speed modes and CF-LVADs but these regions also had low OSI; RRT was almost the same for all the cases. This study may provide a basis for the scientific and reasonable selection of the pulsatile speed patterns of CF-LVADs for treating heart failure patients.

A personalized classification of behavioral severity of autism spectrum disorder using a comprehensive machine learning framework.

Autism Spectrum Disorder (ASD) is characterized as a neurodevelopmental disorder with a heterogeneous nature, influenced by genetics and exhibiting diverse clinical presentations. In this study, we dissect Autism Spectrum Disorder (ASD) into its behavioral components, mirroring the diagnostic process used in clinical settings. Morphological features are extracted from magnetic resonance imaging (MRI) scans, found in the publicly available dataset ABIDE II, identifying the most discriminative features that differentiate ASD within various behavioral domains. Then, each subject is categorized as having severe, moderate, or mild ASD, or typical neurodevelopment (TD), based on the behavioral domains of the Social Responsiveness Scale (SRS). Through this study, multiple artificial intelligence (AI) models are utilized for feature selection and classifying each ASD severity and behavioural group. A multivariate feature selection algorithm, investigating four different classifiers with linear and non-linear hypotheses, is applied iteratively while shuffling the training-validation subjects to find the set of cortical regions with statistically significant association with ASD. A set of six classifiers are optimized and trained on the selected set of features using 5-fold cross-validation for the purpose of severity classification for each behavioural group. Our AI-based model achieved an average accuracy of 96%, computed as the mean accuracy across the top-performing AI models for feature selection and severity classification across the different behavioral groups. The proposed AI model has the ability to accurately differentiate between the functionalities of specific brain regions, such as the left and right caudal middle frontal regions. We propose an AI-based model that dissects ASD into behavioral components. For each behavioral component, the AI-based model is capable of identifying the brain regions which are associated with ASD as well as utilizing those regions for diagnosis. The proposed system can increase the speed and accuracy of the diagnostic process and result in improved outcomes for individuals with ASD, highlighting the potential of AI in this area.

Passive performance evaluation and validation of a viscous impeller pump for subpulmonary fontan circulatory support.

Patients with single ventricle defects undergoing the Fontan procedure eventually face Fontan failure. Long-term cavopulmonary assist devices using rotary pump technologies are currently being developed as a subpulmonary power source to prevent and treat Fontan failure. Low hydraulic resistance is a critical safety requirement in the event of pump failure (0 RPM) as a modest 2 mmHg cavopulmonary pressure drop can compromise patient hemodynamics. The goal of this study is therefore to assess the passive performance of a viscous impeller pump (VIP) we are developing for Fontan patients, and validate flow simulations against in-vitro data. Two different blade heights (1.09 mm vs 1.62 mm) and a blank housing model were tested using a mock circulatory loop (MCL) with cardiac output ranging from 3 to 11 L/min. Three-dimensional flow simulations were performed and compared against MCL data. In-silico and MCL results demonstrated a pressure drop of < 2 mmHg at a cardiac output of 7 L/min for both blade heights. There was good agreement between simulation and MCL results for pressure loss (mean difference - 0.23 mmHg 95% CI [0.24-0.71]). Compared to the blank housing model, low wall shear stress area and oscillatory shear index on the pump surface were low, and mean washout times were within 2 s. This study demonstrated the low resistance characteristic of current VIP designs in the failed condition that results in clinically acceptable minimal pressure loss without increased washout time as compared to a blank housing model under normal cardiac output in Fontan patients.

Passive Performance Evaluation and Validation of a Viscous Impeller Pump for Subpulmonary Fontan Circulatory Support.

Patients with single ventricle defects undergoing the Fontan procedure eventually face Fontan failure. Long-term cavopulmonary assist devices using rotary pump technologies are currently being developed as a subpulmonary power source to prevent and treat Fontan failure. Low hydraulic resistance is a critical safety requirement in the event of pump failure (0 RPM) as a modest 2 mmHg cavopulmonary pressure drop can compromise patient hemodynamics. The goal of this study is therefore to assess the passive performance for a viscous impeller pump (VIP) we are developing for Fontan patients, and validate flow simulations against in-vitro data. Two different blade heights (1.09 mm vs 1.62 mm) and a blank housing model were tested using a mock circulatory loop (MCL) with cardiac output ranging from 3 to 11 L/min. Three-dimensional flow simulations were performed and compared against MCL data. In-silico and MCL results demonstrated a clinically insignificant pressure drop of $<$ 2 mmHg at a cardiac output of 7 L/min for both blade heights. There was good agreement between simulation and MCL results for pressure loss (mean difference -0.23 mmHg 95% CI [0.24 -0.71]). Compared to the blank housing model, low wall shear stress area and oscillatory shear index on the pump surface were low, and mean washout times were within 2 seconds. This study demonstrated the low resistance characteristic of current VIP designs in the failed condition that results in clinically acceptable minimal pressure loss with low risk of thrombosis.

A sensorless, physiologic feedback control strategy to increase vascular pulsatility for rotary blood pumps.

Continuous flow rotary blood pumps (RBP) operating clinically at constant rotational speeds cannot match cardiac demand during varying physical activities, are susceptible to suction, diminish vascular pulsatility, and have an increased risk of adverse events. A sensorless, physiologic feedback control strategy for RBP was developed to mitigate these limitations. The proposed algorithm used intrinsic pump speed to obtain differential pump speed (ΔRPM). The proposed gain-scheduled proportional-integral controller, switching of setpoints between a higher pump speed differential setpoint (ΔRPM Hr ) and a lower pump speed differential setpoint (ΔRPM Lr ), generated pulsatility and physiologic perfusion, while avoiding suction. The switching between ΔRPM Hr and ΔRPM Lr setpoints occurred when the measured ΔRPM reached the pump differential reference setpoint. In-silico tests were implemented to assess the proposed algorithm during rest, exercise, a rapid 3-fold pulmonary vascular resistance increase, rapid change from exercise to rest, and compared with maintaining a constant pump speed setpoint. The proposed control algorithm augmented aortic pressure pulsatility to over 35 mmHg during rest and around 30 mmHg during exercise. Significantly, ventricular suction was avoided, and adequate cardiac output was maintained under all simulated conditions. The performance of the sensorless algorithm using estimation was similar to the performance of sensor-based method. This study demonstrated that augmentation of vascular pulsatility was feasible while avoiding ventricular suction and providing physiological pump outflows. Augmentation of vascular pulsatility can minimize adverse events that have been associated with diminished pulsatility. Mock circulation and animal studies would be conducted to validate these results.

von Willebrand Factor and Angiopoietin-2 are Sensitive Biomarkers of Pulsatility in Continuous-Flow Ventricular Assist Device Patients.

Nonsurgical bleeding occurs in a significant proportion of patients implanted with continuous-flow ventricular assist devices (CF-VADs) and is associated with nonphysiologic flow with diminished pulsatility. An in vitro vascular pulse perfusion model seeded with adult human aortic endothelial cells (HAECs) was used to identify biomarkers sensitive to changes in pulsatility. Diminished pulsatility resulted in an ~45% decrease in von Willebrand factor (vWF) levels from 9.80 to 5.32 ng/ml (n = 5, p < 0.05) and a threefold increase in angiopoietin-2 (ANGPT-2) levels from 775.29 to 2471.93 pg/ml (n = 5, p < 0.05) in cultured HAECs. These changes are in agreement with evaluation of patient blood samples obtained pre-CF-VAD implant and 30-day postimplant: a decrease in plasma vWF level by 50% from ~45.59 to ~22.49 µg/ml (n = 15, p < 0.01) and a 64% increase in plasma ANGPT-2 level from 7,073 to 11,615 pg/ml (n = 8, p < 0.05). This study identified vWF and ANGPT-2 as highly sensitive to changes in pulsatility, in addition to interleukin-6 (IL-6), IL-8, and tumor necrosis-α (TNF-α). These biomarkers may help determine the optimal level of pulsatility and help identify patients at high risk of nonsurgical bleeding.

Loss of pulsatility with continuous-flow left ventricular assist devices and the significance of the arterial endothelium in von-Willebrand factor production and degradation.

BACKGROUND: Patients on continuous flow ventricular assist devices (CF-VADs) are at high risk for the development of Acquired von-Willebrand Syndrome (AVWS) and non-surgical bleeding. von Willebrand Factor (vWF) plays an essential role in maintaining hemostasis via platelet binding to the damaged endothelium to facilitate coagulation. In CF-VAD patients, degradation of vWF into low MW multimers that are inefficient in facilitating coagulation occurs and has been primarily attributed to the supraphysiological shear stress associated with the CF-VAD impeller. METHODS: In this review, we evaluate information from the literature regarding the unraveling behavior of surface-immobilized vWF under pulsatile and continuous flow pertaining to: (A) the process of arterial endothelial vWF production and release into circulation, (B) the critical shear stress required to unravel surface bound versus soluble vWF which leads to degradation, and (C) the role of pulsatility in on the production and degradation of vWF. RESULTS AND CONCLUSION: Taken together, these data suggests that the loss of pulsatility and its impact on arterial endothelial cells plays an important role in the production, release, unraveling, and proteolytic degradation of vWF into low MW multimers, contributing to the development of AVWS. Restoration of pulsatility can potentially mitigate this issue by preventing AVWS and minimizing the risk of non-surgical bleeding.

Predicting Recurrence of Non-Muscle-Invasive Bladder Cancer: Current Techniques and Future Trends.

Bladder cancer (BC) is the 10th most common cancer globally and has a high mortality rate if not detected early and treated promptly. Non-muscle-invasive BC (NMIBC) is a subclassification of BC associated with high rates of recurrence and progression. Current tools for predicting recurrence and progression on NMIBC use scoring systems based on clinical and histopathological markers. These exclude other potentially useful biomarkers which could provide a more accurate personalized risk assessment. Future trends are likely to use artificial intelligence (AI) to enhance the prediction of recurrence in patients with NMIBC and decrease the use of standard clinical protocols such as cystoscopy and cytology. Here, we provide a comprehensive survey of the most recent studies from the last decade (N = 70 studies), focused on the prediction of patient outcomes in NMIBC, particularly recurrence, using biomarkers such as radiomics, histopathology, clinical, and genomics. The value of individual and combined biomarkers is discussed in detail with the goal of identifying future trends that will lead to the personalized management of NMIBC.

Special Issue "Computer Aided Diagnosis Sensors".

Sensors used to diagnose, monitor or treat diseases in the medical domain are known as medical sensors [...].

Biomimetic cardiac tissue culture model (CTCM) to emulate cardiac physiology and pathophysiology ex vivo.

There is need for a reliable in vitro system that can accurately replicate the cardiac physiological environment for drug testing. The limited availability of human heart tissue culture systems has led to inaccurate interpretations of cardiac-related drug effects. Here, we developed a cardiac tissue culture model (CTCM) that can electro-mechanically stimulate heart slices with physiological stretches in systole and diastole during the cardiac cycle. After 12 days in culture, this approach partially improved the viability of heart slices but did not completely maintain their structural integrity. Therefore, following small molecule screening, we found that the incorporation of 100 nM tri-iodothyronine (T3) and 1 µM dexamethasone (Dex) into our culture media preserved the microscopic structure of the slices for 12 days. When combined with T3/Dex treatment, the CTCM system maintained the transcriptional profile, viability, metabolic activity, and structural integrity for 12 days at the same levels as the fresh heart tissue. Furthermore, overstretching the cardiac tissue induced cardiac hypertrophic signaling in culture, which provides a proof of concept for the ability of the CTCM to emulate cardiac stretch-induced hypertrophic conditions. In conclusion, CTCM can emulate cardiac physiology and pathophysiology in culture for an extended time, thereby enabling reliable drug screening.

Acute Response of Human Aortic Endothelial Cells to Loss of Pulsatility as Seen during Cardiopulmonary Bypass.

Cardiopulmonary bypass (CPB) results in short-term (3-5 h) exposure to flow with diminished pulsatility often referred to as "continuous flow". It is unclear if short-term exposure to continuous flow influences endothelial function, particularly, changes in levels of pro-inflammatory and pro-angiogenic cytokines. In this study, we used the endothelial cell culture model (ECCM) to evaluate if short-term (≤5 h) reduction in pulsatility alters levels of pro-inflammatory/pro-angiogenic cytokine levels. Human aortic endothelial cells (HAECs) cultured within the ECCM provide a simple model to evaluate endothelial cell function in the absence of confounding factors. HAECs were maintained under normal pulsatile flow for 24 h and then subjected to continuous flow (diminished pulsatile pressure and flow) as observed during CPB for 5 h. The ECCM replicated pulsatility and flow morphologies associated with normal hemodynamic status and CPB as seen with clinically used roller pumps. Levels of angiopoietin-2 (ANG-2), vascular endothelial growth factor-A (VEGF-A), and hepatocyte growth factor were lower in the continuous flow group in comparison to the pulsatile flow group whereas the levels of endothelin-1 (ET-1), granulocyte colony stimulating factor, interleukin-8 (IL-8) and placental growth factor were higher in the continuous flow group in comparison to the pulsatile flow group. Immunolabelling of HAECs subjected to continuous flow showed a decrease in expression of ANG-2 and VEGF-A surface receptors, tyrosine protein kinase-2 and Fms-related receptor tyrosine kinase-1, respectively. Given that the 5 h exposure to continuous flow is insufficient for transcriptional regulation, it is likely that pro-inflammatory/pro-angiogenic signaling observed was due to signaling molecules stored in Weible-Palade bodies (ET-1, IL-8, ANG-2) and via HAEC binding/uptake of soluble factors in media. These results suggest that even short-term exposure to continuous flow can potentially activate pro-inflammatory/pro-angiogenic signaling in cultured HAECs and pulsatile flow may be a successful strategy in reducing the undesirable sequalae following continuous flow CPB.

Effect of pulsatility on shear-induced extensional behavior of Von Willebrand factor.

BACKGROUND: Patients with continuous flow ventricular assist devices (CF-VADs) are at high risk for non-surgical bleeding, speculated to associate with the loss of pulsatility following CF-VAD placement. It has been hypothesized that continuous shear stress causes elongation and increased enzymatic degradation of von Willebrand Factor (vWF), a key player in thrombus formation at sites of vascular damage. However, the role of loss of pulsatility on the unravelling behavior of vWF has not been widely explored. METHODS: vWF molecules were immobilized on the surface of microfluidic devices and subjected to various pulsatile flow profiles, including continuous flow and pulsatile flow of different magnitudes, dQ/dt (i.e., first derivative of flow rate) of pulsatility and pulse frequencies to mimic in vivo shear flow environments with and without CF-VAD support. VWF elongation was observed using total internal reflection fluorescence (TIRF) microscopy. Besides, the vWF level is measured from the patients' blood sample before and after CF-VAD implantation from a clinical perspective. To our knowledge, this work is the first in providing direct, visual observation of single vWF molecule extension under controlled-pulsatile shear flow. RESULTS: Unravelling of vWF (total sample size n ~ 200 molecules) is significantly reduced under pulsatile flow (p < 0.01) compared to continuous flow. An increase in the magnitude of pulsatility further reduces unravelling lengths, while lower frequency of pulsatility (20 vs. 60 pulses per min) does not have a major effect on the maximum or minimum unravelling lengths. Evaluation of CF-VAD patient blood samples (n = 13) demonstrates that vWF levels decreased by ~40% following CF-VAD placement (p < 0.01), which correlates to single-molecule observations from a clinical point of view. CONCLUSIONS: Pulsatile flow reduces unfolding of vWF compared to continuous flow and a lower pulse frequency of 20 pulses/minute yielded comparable vWF unfolding to 60 pulses/minute. These findings could shed light on non-surgical bleeding associated with the loss of pulsatility following CF-VAD placement.

Effects of a Short-Term Left Ventricular Assist Device on Hemodynamics in a Heart Failure Patient-Specific Aorta Model: A CFD Study.

Patients with heart failure (HF) or undergoing cardiogenic shock and percutaneous coronary intervention require short-term cardiac support. Short-term cardiac support using a left ventricular assist device (LVAD) alters the pressure and flows of the vasculature by enhancing perfusion and improving the hemodynamic performance for the HF patients. However, due to the position of the inflow and outflow of the LVAD, the local hemodynamics within the aorta is altered with the LVAD support. Specifically, blood velocity, wall shear stress, and pressure difference are altered within the aorta. In this study, computational fluid dynamics (CFD) was used to elucidate the effects of a short-term LVAD for hemodynamic performance in a patient-specific aorta model. The three-dimensional (3D) geometric models of a patient-specific aorta and a short-term LVAD, Impella CP, were created. Velocity, wall shear stress, and pressure difference in the patient-specific aorta model with the Impella CP assistance were calculated and compared with the baseline values of the aorta without Impella CP support. Impella CP support augmented cardiac output, blood velocity, wall shear stress, and pressure difference in the aorta. The proposed CFD study could analyze the quantitative changes in the important hemodynamic parameters while considering the effects of Impella CP, and provide a scientific basis for further predicting and assessing the effects of these hemodynamic signals on the aorta.

A Flow Sensor-Based Suction-Index Control Strategy for Rotary Left Ventricular Assist Devices.

Rotary left ventricular assist devices (LVAD) have emerged as a long-term treatment option for patients with advanced heart failure. LVADs need to maintain sufficient physiological perfusion while avoiding left ventricular myocardial damage due to suction at the LVAD inlet. To achieve these objectives, a control algorithm that utilizes a calculated suction index from measured pump flow (SIMPF) is proposed. This algorithm maintained a reference, user-defined SIMPF value, and was evaluated using an in silico model of the human circulatory system coupled to an axial or mixed flow LVAD with 5-10% uniformly distributed measurement noise added to flow sensors. Efficacy of the SIMPF algorithm was compared to a constant pump speed control strategy currently used clinically, and control algorithms proposed in the literature including differential pump speed control, left ventricular end-diastolic pressure control, mean aortic pressure control, and differential pressure control during (1) rest and exercise states; (2) rapid, eight-fold augmentation of pulmonary vascular resistance for (1); and (3) rapid change in physiologic states between rest and exercise. Maintaining SIMPF simultaneously provided sufficient physiological perfusion and avoided ventricular suction. Performance of the SIMPF algorithm was superior to the compared control strategies for both types of LVAD, demonstrating pump independence of the SIMPF algorithm.

Demonstration of proof-of-concept of StrokeShield system for complete closure and occlusion of the left atrial appendage for non-valvular atrial fibrillation therapy.

In the US, the most significant morbidity and mortality associated with non-valvular atrial fibrillation (NVAF) is embolic stroke, with 90% of thrombus originating from the left atrial appendage (LAA). Anticoagulation is the preferred treatment for the prevention of stroke in NVAF patients, but clinical studies have demonstrated high levels of non-compliance and increased risk of bleeding or ineligibility for anticoagulation therapy, especially in the elderly population where the incidence of NVAF is highest. Alternatively, stroke may be preventing using clinically approved surgical and catheter-based devices to exclude or occlude the LAA, but these devices continue to be plagued by peri-device leaks and thrombus formation because of residual volume. To overcome these limitations, Cor Habere (Louisville, KY) and the University of Louisville are developing a LAA closure device (StrokeShield) that completely occludes and collapses the LAA to minimize the risk of stroke. The StrokeShield device is a collapsible occluder (nitinol reinforced membrane) that completely covers the LAA orifice with an expandable conical coil anchor that attaches to the myocardium. The device is designed for catheter-based delivery and expands to completely occlude the LAA orifice and collapse the LAA. The primary advantages of the StrokeShield system are a completely sealed LAA (no peri-device flow or residual space) and smooth endothelialized connection to the left atrial wall with minimal risk of cardiac bleeding and tamponade. We tested proof-of-concept of a prototype StrokeShield device in acute (n = 2) and chronic 60-day (n = 2) healthy canine models. Acute results demonstrated that the conical coil securely attached to the myocardium (5N pull-out force) and the Nitinol umbrella fully deployed and covered the LAA ostium. Results from the chronic implants demonstrated long-term feasibility of device placement with no procedural or device-related intra- or post-operative complications, secure placement and correct positioning of the device with no device migration. The device successfully occluded the LAA ostium and collapsed the LAA with no interference with the mitral valve, circumflex coronary artery, or pulmonary veins. Necropsy demonstrated no gross signs of thrombus or end-organ damage and the device was encapsulated in the LAA. Histology demonstrated mature neointima covering the device with expected foreign body inflammatory response. These early positive results will help to guide the iterative design process for the continued development of the StrokeShield system.

A novel computer-aided diagnostic system for accurate detection and grading of liver tumors.

Liver cancer is a major cause of morbidity and mortality in the world. The primary goals of this manuscript are the identification of novel imaging markers (morphological, functional, and anatomical/textural), and development of a computer-aided diagnostic (CAD) system to accurately detect and grade liver tumors non-invasively. A total of 95 patients with liver tumors (M = 65, F = 30, age range = 34-82 years) were enrolled in the study after consents were obtained. 38 patients had benign tumors (LR1 = 19 and LR2 = 19), 19 patients had intermediate tumors (LR3), and 38 patients had hepatocellular carcinoma (HCC) malignant tumors (LR4 = 19 and LR5 = 19). A multi-phase contrast-enhanced magnetic resonance imaging (CE-MRI) was collected to extract the imaging markers. A comprehensive CAD system was developed, which includes the following main steps: i) estimation of morphological markers using a new parametric spherical harmonic model, ii) estimation of textural markers using a novel rotation invariant gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) models, and iii) calculation of the functional markers by estimating the wash-in/wash-out slopes, which enable quantification of the enhancement characteristics across different CE-MR phases. These markers were subsequently processed using a two-stages random forest-based classifier to classify the liver tumor as benign, intermediate, or malignant and determine the corresponding grade (LR1, LR2, LR3, LR4, or LR5). The overall CAD system using all the identified imaging markers achieved a sensitivity of 91.8%±0.9%, specificity of 91.2%±1.9%, and F[Formula: see text] score of 0.91±0.01, using the leave-one-subject-out (LOSO) cross-validation approach. Importantly, the CAD system achieved overall accuracies of [Formula: see text], 85%±2%, 78%±3%, 83%±4%, and 79%±3% in grading liver tumors into LR1, LR2, LR3, LR4, and LR5, respectively. In addition to LOSO, the developed CAD system was tested using randomly stratified 10-fold and 5-fold cross-validation approaches. Alternative classification algorithms, including support vector machine, naive Bayes classifier, k-nearest neighbors, and linear discriminant analysis all produced inferior results compared to the proposed two stage random forest classification model. These experiments demonstrate the feasibility of the proposed CAD system as a novel tool to objectively assess liver tumors based on the new comprehensive imaging markers. The identified imaging markers and CAD system can be used as a non-invasive diagnostic tool for early and accurate detection and grading of liver cancer.

Early assessment of lung function in coronavirus patients using invariant markers from chest X-rays images.

The primary goal of this manuscript is to develop a computer assisted diagnostic (CAD) system to assess pulmonary function and risk of mortality in patients with coronavirus disease 2019 (COVID-19). The CAD system processes chest X-ray data and provides accurate, objective imaging markers to assist in the determination of patients with a higher risk of death and thus are more likely to require mechanical ventilation and/or more intensive clinical care.To obtain an accurate stochastic model that has the ability to detect the severity of lung infection, we develop a second-order Markov-Gibbs random field (MGRF) invariant under rigid transformation (translation or rotation of the image) as well as scale (i.e., pixel size). The parameters of the MGRF model are learned automatically, given a training set of X-ray images with affected lung regions labeled. An X-ray input to the system undergoes pre-processing to correct for non-uniformity of illumination and to delimit the boundary of the lung, using either a fully-automated segmentation routine or manual delineation provided by the radiologist, prior to the diagnosis. The steps of the proposed methodology are: (i) estimate the Gibbs energy at several different radii to describe the inhomogeneity in lung infection; (ii) compute the cumulative distribution function (CDF) as a new representation to describe the local inhomogeneity in the infected region of lung; and (iii) input the CDFs to a new neural network-based fusion system to determine whether the severity of lung infection is low or high. This approach is tested on 200 clinical X-rays from 200 COVID-19 positive patients, 100 of whom died and 100 who recovered using multiple training/testing processes including leave-one-subject-out (LOSO), tenfold, fourfold, and twofold cross-validation tests. The Gibbs energy for lung pathology was estimated at three concentric rings of increasing radii. The accuracy and Dice similarity coefficient (DSC) of the system steadily improved as the radius increased. The overall CAD system combined the estimated Gibbs energy information from all radii and achieved a sensitivity, specificity, accuracy, and DSC of 100%, 97% ± 3%, 98% ± 2%, and 98% ± 2%, respectively, by twofold cross validation. Alternative classification algorithms, including support vector machine, random forest, naive Bayes classifier, K-nearest neighbors, and decision trees all produced inferior results compared to the proposed neural network used in this CAD system. The experiments demonstrate the feasibility of the proposed system as a novel tool to objectively assess disease severity and predict mortality in COVID-19 patients. The proposed tool can assist physicians to determine which patients might require more intensive clinical care, such a mechanical respiratory support.