BACKGROUND AND OBJECTIVE: The prevalence of pelvic floor muscle injuries induced by childbirth is higher than 23 % in the general women population. Such injuries can lead to prolapses and other pathologies in future female life. Leveraging computational biomechanics, the study implements an advanced female pelvic floor model for computing the maximum pelvic muscle strain, which serves as an injury risk indicator. The design of experiment method, abbreviated as DoE, is used to compute the maximum strain for boundary values of bony pelvis dimensions, namely the anterior-posterior diameter (abbreviated as APD) and the transverse diameter (abbreviated as TD). This is done in combination with small, medium and large percentiles of fetal head circumference (abbreviated as HC). METHODS: We utilized a previously developed finite element model of a female pelvic floor, as a reference, and enhanced it with new features, including a more detailed tissue geometry and advanced constitutive material models. The APD and TD dimensions were sourced from the set of MRI of 64 nulliparous women. This data was used to estimate the boundary dimensions of the female bony pelvis, combining both small and large values of APD and TD. Together with the 10th and the 95th percentiles for HC, a three-dimensional domain was constructed to assess the maximum pelvic muscle strain. In boundary cases, the maximum pelvic muscle strain was computed across 8 full-factorial design models (each situated at one corner of the domain, thereby combining the minimum and the maximum values of APD, TD and HC). This was done to define a response surface that predicts the maximum pelvic muscle strain within the domain. The accuracy of this response surface prediction was validated using 15 additional intermediate design models. These models were placed at the center of the domain (1 point), the centres of the domain boundary surfaces (6 points), and midway along each domain boundary edge (8 points). RESULTS: The maximum strain results for 8 combinations of APD, TD, and HC were employed to construct a linear response surface as a function of APD, TD, and HC. Tests at an additional 19 domain points served to evaluate the efficiency of the response surface prediction. The response surface demonstrated strong predictability, with an absolute average error of 1.52 %, an absolute median error of 1.52 %, and an absolute maximum error of 11.11 %. HC emerged as the most influencing dimension, accounting for 16 % of influence. CONCLUSIONS: The reference finite element pelvic floor model was scaled to 8 full-factorial female-specific pelvic floor models, which represent the combination of boundary values for APD, TD, and HC. The maximum pelvic floor muscle strain from these 8 models was used to design a response surface. When implementing the DoE approach to construct the response, there was consistent predictability for the maximum perineal muscle strain, as validated by the additional 19 intermediate design models. As a result, the response surface methodology can serve as an initial predictor for potential childbirth-induced pelvic floor muscle injury.
- MeSH
- kosterní svaly diagnostické zobrazování MeSH
- lidé MeSH
- magnetická rezonanční tomografie MeSH
- pánevní dno diagnostické zobrazování fyziologie MeSH
- porod * fyziologie MeSH
- těhotenství MeSH
- vedení porodu * MeSH
- Check Tag
- lidé MeSH
- těhotenství MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND AND OBJECTIVES: Prediction of patient deterioration is essential in medical care, and its automation may reduce the risk of patient death. The precise monitoring of a patient's medical state requires devices placed on the body, which may cause discomfort. Our approach is based on the processing of long-term ballistocardiography data, which were measured using a sensory pad placed under the patient's mattress. METHODS: The investigated dataset was obtained via long-term measurements in retirement homes and intensive care units (ICU). Data were measured unobtrusively using a measuring pad equipped with piezoceramic sensors. The proposed approach focused on the processing methods of the measured ballistocardiographic signals, Cartan curvature (CC), and Euclidean arc length (EAL). RESULTS: For analysis, 218,979 normal and 216,259 aberrant 2-second samples were collected and classified using a convolutional neural network. Experiments using cross-validation with expert threshold and data length revealed the accuracy, sensitivity, and specificity of the proposed method to be 86.51 CONCLUSIONS: The proposed method provides a unique approach for an early detection of health concerns in an unobtrusive manner. In addition, the suitability of EAL over the CC was determined.
- MeSH
- balistokardiografie * MeSH
- lidé MeSH
- lůžka MeSH
- neuronové sítě (počítačové) * MeSH
- srdeční frekvence MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND AND OBJECTIVES: Microscopic images are an important part for haematologists in diagnosing various diseases in the blood cell. Changes in blood cells are caused by malaria disease, and early diagnosis can prevent the disease from entering its severe stage. METHODS: In this paper, an automated non-invasive and efficient deep learning-based framework is developed for multi-class plasmodium vivax life cycle classification and malaria diagnosis. A multi-class microscopic blood cell of different plasmodium vivax life cycle stage dataset is analysed, and a diagnostic framework is designed. Several stages of the disease are examined and augmented through various techniques to make the framework robust in real-time. Generative adversarial network is specially designed to generate extended training samples of various life cycle stages to increase robustness of the resulting model. A special transformer-based neural network vision transformer is designed to improve generalisation capabilities. Microscopic images are classified into multi classes of plasmodium vivax life cycle stage, where the keystone transformer layers extract relevant disease features from microscopic colour images, and the extracted relevant features are used to make predictive diagnostic decisions. RESULTS: The capabilities of the vision transformer are computed and analysed by statistical parameters, and the performance of the vision transformer model is compared with baseline architectures, where it was evident that the performance of the vision transformer was significantly better, reaching 90.03% accuracy. CONCLUSIONS: A comprehensive comparison of the proposed framework to the state-of-the-art methods proves its efficiency in the classification of plasmodium vivax life cycle for malaria disease identification through thin blood smear microscopic images.
- MeSH
- histologické techniky MeSH
- malárie * MeSH
- Plasmodium vivax * MeSH
- stadia vývoje MeSH
- zvířata MeSH
- Check Tag
- zvířata MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND AND OBJECTIVE: Total knee arthroplasty (TKA) with modern all-polyethylene tibial (APT) components has shown high long-term survival rates and comparable results to those with metal-backed tibial components. Nevertheless, APT components are primarily recommended for older and low-demand patients. There are no evidence-based biomechanical guidelines for orthopaedic surgeons to determine the appropriate lower age limit for implantation of APT components. A biomechanical analysis was assumed to be suitable to evaluate the clinical results in patients under 70 years. The scope of this study was to determine biomechanically the appropriate lower age limit for implantation of APT components. METHODS: To generate data of the highest possible quality, the geometry of the computational models was created based on computed tomography (CT) images of a representative patient. The cortical bone tissue model distinguishes the change in mechanical properties described in three parts from the tibial cut. The cancellous bone material model has a heterogeneous distribution of mechanical properties. The values used to determine the material properties of the tissues were obtained from measurements of a CT dataset comprising 45 patients. RESULTS: Computational modeling showed that in the majority of the periprosthetic volume, the von Mises strain equivalent ranges from 200 to 2700 με; these strain values induce bone modeling and remodeling. The highest measured deformation value was 2910 με. There was no significant difference in the induced mechanical response between bone models of the 60-year and 70-year age groups, and there was <3% difference from the 65-year age group. CONCLUSIONS: Considering in silico limitations, we suggest that APT components could be conveniently used on a bone with mechanical properties of the examined age categories. Under defined loading conditions, implantation of TKA with APT components is expected to induce modeling and remodeling of the periprosthetic tibia. Following clinical validation, the results of our study could modify the indication criteria of the procedure, and lead to more frequent implantation of all-polyethylene TKA in younger patients.
- MeSH
- analýza metodou konečných prvků MeSH
- biomechanika MeSH
- kovy MeSH
- lidé MeSH
- mechanický stres MeSH
- polyethylen MeSH
- protézy - design MeSH
- protézy kolene * MeSH
- tibie diagnostické zobrazování chirurgie MeSH
- totální endoprotéza kolene * metody MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND AND OBJECTIVES: The lack of medical facilities in isolated areas makes many patients remain aloof from quick and timely diagnosis of cardiovascular diseases, leading to high mortality rates. A deep learning based method for automatic diagnosis of multiple cardiac diseases from Phonocardiogram (PCG) signals is proposed in this paper. METHODS: The proposed system is a combination of deep learning based convolutional neural network (CNN) and power spectrogram Cardi-Net, which can extract deep discriminating features of PCG signals from the power spectrogram to identify the diseases. The choice of Power Spectral Density (PSD) makes the model extract highly discriminatory features significant for the multi-classification of four common cardiac disorders. RESULTS: Data augmentation techniques are applied to make the model robust, and the model undergoes 10-fold cross-validation to yield an overall accuracy of 98.879% on the test dataset to diagnose multi heart diseases from PCG signals. CONCLUSION: The proposed model is completely automatic, where signal pre-processing and feature engineering are not required. The conversion time of power spectrogram from PCG signals is very low range from 0.10 s to 0.11 s. This reduces the complexity of the model, making it highly reliable and robust for real-time applications. The proposed architecture can be deployed on cloud and a low cost processor, desktop, android app leading to proper access to the dispensaries in remote areas.
BACKGROUND AND OBJECTIVE: Estimating patient specific annual risk of rupture of abdominal aortic aneurysm (AAA) is currently based only on population. More accurate knowledge based on patient specific data would allow surgical treatment of only those AAAs with significant risk of rupture. This would be beneficial for both patients and health care system. METHODS: A methodology for estimating annual risk of rupture (EARR) of abdominal aortic aneurysms (AAA) that utilizes Bayesian statistics, mechanics and patient-specific blood pressure monitoring data is proposed. EARR estimation takes into consideration, peak wall stress in AAA computed by patient-specific finite element modeling, the probability distributions of wall thickness, wall strength, systolic blood pressure and the period of time that the patient is known to have already survived with the intact AAA. Initial testing of proposed approach was performed on fifteen patients with intact AAA (mean maximal diameter 51mm±8mm). They were equipped with a pressure holter and their blood pressure was recorded over 24 hours. Then, we calculated EARR values for four possible scenarios - without considering any days of survival prior identification of AAA at computed tomography scans (EARR_0), considering past survival of 30 (EARR_30), 90 (EARR_90) and 180 days (EARR_180). Finally, effect of patient-specific blood pressure variability was analyzed. RESULTS: Consideration of past survival does indeed significantly improve predictions of future risk: EARR_30 (1.04%± 0.87%), EARR_90 (0.67%± 0.56%) and EARR_180 (0.47%± 0.39%) which are unrealistically high otherwise (EARR_0 5.02%± 5.24%). Finally, EARR values were observed to vary by an order as a consequence of blood pressure variability and by factor of two as a consequence of neglected growth. CONCLUSIONS: Methodology for computing annual risk of rupture of AAA was developed for the first time. Sensitivity analyses showed respecting patient specific blood pressure is important factor and should be included in the AAA rupture risk assessment. Obtained EARR values were generally low and in good agreement with confirmed survival time of investigated patients so proposed method should be further clinically validated.
- MeSH
- aneurysma břišní aorty * diagnostické zobrazování MeSH
- Bayesova věta MeSH
- hodnocení rizik MeSH
- lidé MeSH
- mechanický stres MeSH
- modely kardiovaskulární MeSH
- počítačová rentgenová tomografie MeSH
- počítačové modelování podle konkrétního pacienta MeSH
- rizikové faktory MeSH
- ruptura aorty * diagnostické zobrazování MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND AND OBJECTIVE: Capturing the population variability of bone properties is of paramount importance to biomedical engineering. The aim of the present paper is to describe variability and correlations in bone mineral density with a spatial random field inferred from routine computed tomography data. METHODS: Random fields were simulated by transforming pairwise uncorrelated Gaussian random variables into correlated variables through the spectral decomposition of an age-detrended correlation matrix. The validity of the random field model was demonstrated in the spatiotemporal analysis of bone mineral density. The similarity between the computed tomography samples and those generated via random fields was analyzed with the energy distance metric. RESULTS: The random field of bone mineral density was found to be approximately Gaussian/slightly left-skewed/strongly right-skewed at various locations. However, average bone density could be simulated well with the proposed Gaussian random field for which the energy distance, i.e., a measure that quantifies discrepancies between two distribution functions, is convergent with respect to the number of correlation eigenpairs. CONCLUSIONS: The proposed random field model allows the enhancement of computational biomechanical models with variability in bone mineral density, which could increase the usability of the model and provides a step forward in in-silico medicine.
- MeSH
- kosti a kostní tkáň * MeSH
- kostní denzita * MeSH
- počítačová rentgenová tomografie MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND AND OBJECTIVE: The geodesic ray-tracing method has shown its effectiveness for the reconstruction of fibers in white matter structure. Based on reasonable metrics on the spaces of the diffusion tensors, it can provide multiple solutions and get robust to noise and curvatures of fibers. The choice of the metric on the spaces of diffusion tensors has a significant impact on the outcome of this method. Our objective is to suggest metrics and modifications of the algorithms leading to more satisfactory results in the construction of white matter tracts as geodesics. METHODS: Starting with the DTI modality, we propose to rescale the initially chosen metric on the space of diffusion tensors to increase the geodetic cost in the isotropic regions. This change should be conformal in order to preserve the angles between crossing fibers. We also suggest to enhance the methods to be more robust to noise and to employ the fourth order tensor data in order to handle the fiber crossings properly. RESULTS: We propose a way to choose the appropriate conformal class of metrics where the metric gets scaled according to tensor anisotropy. We use the logistic functions, which are commonly used in statistics as cumulative distribution functions. To prevent deviation of geodesics from the actual paths, we propose a hybrid ray-tracing approach. Furthermore, we suggest how to employ diagonal projections of 4th order tensors to perform fiber tracking in crossing regions. CONCLUSIONS: The algorithms based on the newly suggested methods were succesfuly implemented, their performance was tested on both synthetic and real data, and compared to some of the previously known approaches.
BACKGROUND AND OBJECTIVES: Research in Multiple Sclerosis (MS) has recently focused on extracting knowledge from real-world clinical data sources. This type of data is more abundant than data produced during clinical trials and potentially more informative about real-world clinical practice. However, this comes at the cost of less curated and controlled data sets. In this work we aim to predict disability progression by optimally extracting information from longitudinal patient data in the real-world setting, with a special focus on the sporadic sampling problem. METHODS: We use machine learning methods suited for patient trajectories modeling, such as recurrent neural networks and tensor factorization. A subset of 6682 patients from the MSBase registry is used. RESULTS: We can predict disability progression of patients in a two-year horizon with an ROC-AUC of 0.85, which represents a 32% decrease in the ranking pair error (1-AUC) compared to reference methods using static clinical features. CONCLUSIONS: Compared to the models available in the literature, this work uses the most complete patient history for MS disease progression prediction and represents a step forward towards AI-assisted precision medicine in MS.
- MeSH
- lidé MeSH
- neuronové sítě (počítačové) MeSH
- roztroušená skleróza * MeSH
- strojové učení * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
Background and Objectives Automatic detection of breathing disorders plays an important role in the early signalization of respiratory diseases. Measuring methods can be based on electrocardiogram (ECG), sound, oximetry, or respiratory analysis. However, these approaches require devices placed on the human body or they are prone to disturbance by environmental influences. To solve these problems, we proposed a heart contraction mechanical trigger for unobtrusive detection of respiratory disorders from the mechanical measurement of cardiac contractions. We designed a novel method to calculate this mechanical trigger purely from measured mechanical signals without the use of ECG. Methods The approach is a built-on calculation of the so-called euclidean arc length from the signals. In comparison to previous researches, this system does not require any equipment attached to a person. This is achieved by locating the tensometers on the bed. Data from sensors are fused by the Cartan curvatures method to beat-to-beat vector input for the Convolutional neural network (CNN) classifier. Results In sum, 2281 disordered and 5130 normal breathing samples was collected for analysis. The experiments with use of 10-fold cross validation show that accuracy, sensitivity, and specificity reach values of 96.37%, 92.46%, and 98.11% respectively. Conclusions By the approach for detection, the system offers a novel way for a completely unobtrusive diagnosis of breathing-related health problems. The proposed solution can effectively be deployed in all clinical or home environments.
- MeSH
- algoritmy MeSH
- elektrokardiografie * MeSH
- lidé MeSH
- nemoci dýchací soustavy * MeSH
- neuronové sítě (počítačové) MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
