Stackwhitley0229

The resulting reconstruction errors of each image were then used to classify the images into two groups based on quality by training and testing an RFC. Using the SSIM based AE, the classifier showed an average accuracy of 71%±4.0% when classifying images based on user errors and an accuracy of 91%±1.0% when sorting images based on noise. The respective accuracies obtained from the AE using the MSE function were 76%±2.0% and 83%±2.0%. The results of this study demonstrate that an AE has the potential to differentiate good quality US images from those with poor quality, which could be used to help less experienced researchers and clinicians obtain a more objective measure of image quality when using US.Intratumor heterogeneity in glioblastoma (GBM) has been linked to adverse clinical outcomes including poor survival and sub-optimal response to therapies. Different techniques, such as radiomics, have been used to characterize GBM phenotype. However, the spatial diversity and the interaction between different sub-regions within the tumor (habitats) and its microenvironment has been relatively unexplored. Besides, existing approaches have mainly focused on the radiomic analysis within globally defined regions without considering local heterogeneity. In this paper, we developed a 3D spatial co-localization descriptor based on the adjacency of "habitats" to quantify the diversity of physiologically similar sub-regions on multi-protocol magnetic resonance imaging. We demonstrated the utility of this spatial phenotype descriptor in predicting overall patient survival. Our experimental results on N=236 treatment-naïve MRI scans suggest that the co-localization features in conjunction with traditional clinical measures, such as age and tumor volume, outperform texture based radiomic features. The presented descriptor provides a tool for more complete characterization of intratumor heterogeneity in solid cancers.Crawling Wave Sonoelastography (CWS) is an elastography ultrasound-based imaging approach that provides tissue stiffness information through the calculation of Shear Wave Speed (SWS). Many SWS estimators have been developed; however, they report important limitations such as the presence of artifacts, border effects or high computational cost. In addition, these techniques require a moving interference pattern which could be challenging for in vivo applications. In this study, a new estimator based on the Continuous Wavelet Transform (CWT) is proposed. This allows the generation of a SWS image for every sonoelasticity video frame. Testing was made with data acquired from experiments conducted on a gelatin phantom with a circular inclusion. It was excited with two vibration sources placed at both sides with frequencies ranging from 200 Hz to 360 Hz in steps of 20 Hz. Results show small variation of the SWS image across time. Additionally, images were compared with the Phase Derivative method (PD) and the Regularized Wavelength Average Velocity Estimator (R-WAVE). Similar SWS values were obtained for the three estimators within a certain region of interest in the inclusion (At 360 Hz, CWT 5.01±0.2m/s, PD 5.11±0.28m/s, R-WAVE 4.51±0.62m/s) and in the background (At 360 Hz, CWT 3.67±0.15m/s, PD 3.69±0.23m/s, R-WAVE 3.58±0.24m/s). CWT also presented the lowest coefficient of variation and the highest contrast-to-noise ratio for most frequencies, which allows better discrimination between regions.Clinical relevance-This study presents a new Shear Wave Speed estimator for Crawling Wave Sonoelastography, which can be useful to characterize soft tissue and detect lesions.Crawling Waves Sonoelastography (CWS) is an ultrasound elastography approach for the Shear Waves Speed (SWS) estimation. Several studies show promising results for tissue characterization. The algorithms used to calculate the SWS have been commonly implemented considering an opposing vibration sources to the side of the tissue of interest. However, implementing this mechanical setup has important limitations considering the geometry of the body. For that reason, a propagation from the top to the surface can be useful. Previous estimators such as Phase Derivative have been modified and tested in phantom studies, however, the presences of artifacts limited the performed of the SWS map. In this study, the Regularized Wavelength Average Velocity Estimator (R-WAVE) technique is modified and evaluated (RWm) to be used for normal propagation. The results of heterogeneous simulations and phantoms experiments showed consistent results with the literature (ie Simulations Max Bias PDm 11.64 % • RWm 10.21 %, Max CNR PDm 37.82 dB • RWm 44.42 dB, Phantom Experiments Max Bias PDm 15.42 % • RWm 13.99 %, Max CNR PDm 24.14 dB • RWm 26.40 dB). The result of this study shows the potential of RWm to characterize the stiffness of the tissue as well as to differentiate tumors on in vivo applications.Clinical relevance This study presents a modification of the regularized shear wave speed estimator based on crawling waves sonoelastography approach for medical tissue analysis. This technique can be used to discriminate benignant from malignant tumors.Tomography is a two step process in which the sample under test is first scanned by the hardware of the system to acquire data and then the operating software reconstruct images from the gathered information. The main objective of this work is to optimize the scanning process to acquire maximum amount of information in each measurement when the system is scanning the sample. By exploiting our prior information about the sample and using estimation theory, we developed a systematic approach to implement the optimal scanning protocol. Results of this study provide strong evidence that the developed algorithms can speed up data acquisition. Also it is shown that the proposed method can reduce the impact of noise as well as improving the reconstruction error while performing less number of measurements.Clinical relevance- The proposed method can enhance data acquisition time, exposure dosage and cost of operation in medical applications of tomography.Histopathological images are widely used to diagnose diseases such as skin cancer. As digital histopathological images are typically of very large size, in the order of several billion pixels, automated identification of abnormal cell nuclei and their distribution within multiple tissue sections would enable rapid comprehensive diagnostic assessment. In this paper, we propose a deep learning-based technique to segment the melanoma regions in Hematoxylin and Eosin-stained histopathological images. In this technique, the nuclei in an image are first segmented using a deep learning neural network. The segmented nuclei are then used to generate the melanoma region masks. Experimental results show that the proposed method can provide nuclei segmentation accuracy of around 90% and the melanoma region segmentation accuracy of around 98%. The proposed technique also has a low computational complexity.Controlling the dynamics of large-scale neural circuits might play an important role in aberrant cognitive functioning as found in Alzheimer's disease (AD). Analyzing the disease trajectory changes is of critical relevance when we want to get an understanding of the neurodegenerative disease evolution. Advanced control theory offers a multitude of techniques and concepts that can be easily translated into the dynamic processes governing disease evolution at the patient level, treatment response evaluation and revealing some central mechanisms in brain connectomic networks that drive alterations in these diseases. Two types of controllability - the modal and average controllability - have been applied in brain research to provide the mechanistic explanation of how the brain operates in different cognitive states. In this paper, we apply the concept of target controllability to structural (MRI) connectivity graphs for control (CN), mild cognitive impairment (MCI) and Alzheimer's disease (AD) subjects. In targetr disease evolution.The major cause of serious or even fatal injury for the elderly is a fall. Among various technologies developed for detecting falls, the camera-based approach provides a non-invasive and reliable solution for fall detection. This paper introduces a confidence-based fall detection system using multiple surveillance cameras. BTK inhibitor supplier First, a model for predicting the confidence of fall detection on a single camera is constructed using a set of simple yet useful features. Then, the detection results from multiple cameras are fused based on their confidence levels. The proposed confidence prediction model can be easily implemented and integrated with single-camera fall detectors, and the proposed system improves the accuracy of fall detection through effective data fusion.Pneumonia is a common complication associated with COVID-19 infections. Unlike common versions of pneumonia that spread quickly through large lung regions, COVID-19 related pneumonia starts in small localized pockets before spreading over the course of several days. This makes the infection more resilient and with a high probability of developing acute respiratory distress syndrome. Because of the peculiar spread pattern, the use of pulmonary computerized tomography (CT) scans was key in identifying COVID-19 infections. Identifying uncommon pulmonary diseases could be a strong line of defense in early detection of new respiratory infection-causing viruses. In this paper we describe a classification algorithm based on hyperdimensional computing for the detection of COVID-19 pneumonia in CT scans. We test our algorithm using three different datasets. The highest reported accuracy is 95.2% with an F1 score of 0.90, and all three models had a precision of 1 (0 false positives).Modeling the rich, dynamic spatiotemporal variations captured by human brain functional magnetic resonance imaging (fMRI) data is a complicated task. Analysis at the brain's regional and connection levels provides more straightforward biological interpretation for fMRI data and has been instrumental in characterizing the brain thus far. Here we hypothesize that spatiotemporal learning directly in the four-dimensional (4D) fMRI voxel-time space could result in enhanced discriminative brain representations compared to widely used, pre-engineered fMRI temporal transformations, and brain regional and connection-level fMRI features. Motivated by this, we extend our recently reported structural MRI (sMRI) deep learning (DL) pipeline to additionally capture temporal variations, training the proposed 4D DL model end-to-end on preprocessed fMRI data. Results validate that the complex non-linear functions of the used deep spatiotemporal approach generate discriminative encodings for the studied learning task, outperforming both standard machine learning (SML) and DL methods on the widely used fMRI voxel/region/connection features, except the relatively simplistic measure of central tendency - the temporal mean of the fMRI data. Additionally, we identify the fMRI features for which DL significantly outperformed SML methods for voxel-level fMRI features. Overall, our results support the efficiency and potential of DL models trainable at the voxel level fMRI data and highlight the importance of developing auxiliary tools to facilitate interpretation of such flexible models.