PCa-RadHop: A transparent and lightweight feed-forward method for clinically significant prostate cancer segmentation.

Prostate Cancer is one of the most frequently occurring cancers in men, with a low survival rate if not early diagnosed. PI-RADS reading has a high false positive rate, thus increasing the diagnostic incurred costs and patient discomfort. Deep learning (DL) models achieve a high segmentation performance, although require a large model size and complexity.

The Novel Green Learning Artificial Intelligence for Prostate Cancer Imaging: A Balanced Alternative to Deep Learning and Radiomics.

The application of artificial intelligence (AI) on prostate magnetic resonance imaging (MRI) has shown promising results. Several AI systems have been developed to automatically analyze prostate MRI for segmentation, cancer detection, and region of interest characterization, thereby assisting clinicians in their decision-making process. Deep learning, the current trend in imaging AI, has limitations including the lack of transparency "black box", large data processing, and excessive energy consumption.

Image restoration using the W-slice method.

We propose the use of higher order statistics (HOS)-based methods to address the problem of image restoration. The restoration strategy is based on the fact that the phase information of the original image and its HOS are not distorted by some types of blurring. The difficulties associated with the combination of 2-D signals and their HOS are reduced by means of the Radon transform.

Comparison and testing of least-squares time domain inverse solutions in electrocardiography.

The use of several mathematical methods for estimating epicardial ECG potentials from arrays of body surface potentials has been reported in the literature; most of these methods are based on least-squares reconstruction principles and operate in the time-space domain. In this paper we introduce a general Bayesian maximum a posteriori (MAP) framework for time domain inverse solutions in the presence of noise. The two most popular previously applied least-squares methods, constrained (regularized) least-squares and low-rank approximation through the singular value decomposition, are placed in this framework, each of them requiring the a priori knowledge of a 'regularization parameter', which defines the degree of smoothing to be applied to the inversion.

Advanced signal-processing method for the detection, localization, and quantification of acute myocardial ischemia.

In this study of a canine heart model of localized reversible ischemia, a computer-based single-processing method is developed to detect and localize the epicardial projections of ischemic myocardial electrocardiograms (ECGs) during the cardiac activation, rather than the repolarization, phase. This is done by transforming ECG signals from an epicardial sensor array into the multichannel spectral domain and identifying three decision variables: (1) the frequency in hertz of the spectral peak (f0), its frequency band width 50% below the peak value (w0), and the maximum eigenvalue difference of the ECG signal's autocorrelation matrix (e0). With use of the histograms of the f0, w0, and e0 parameters of 3256 ECGs from normal and 957 from ischemic areas of myocardium obtained from 12 dogs, it was possible to predict ischemia in a new test group of nine animals from a Neyman-Pearson (NP) test in which the threshold probabilities of detecting ischemia for each decision variable are compared with those of detecting normality.