Search

Electronic health record (EHR) analysis has become increasingly important in improving the quality of human healthcare. To leverage the full insights from the big EHRs, it is very important to define some application scenarios for which the relevant data can be extracted for training machine learning models to accomplish the expected goals. In this paper, we develop a system on how to recommend medical treatment solutions for patients living in the countryside and small cities when they happen to have schizophrenia but the doctors in the local hospitals do not have sufficient expertise to deal with such challenges. In the EHRs, we take the patients’ symptom descriptions as documents and then develop NLP and unsupervised machine learning techniques to analyze such documents to find the relevant and effective treatment solutions provided by medical experts. Extensive experimental results with different vector representations for documents show that the binary keyword vector representation works best to find relevant and effective medical treatment plans and solutions from the EHRs for any input symptom description.

The anisotropic diffusion techniques are in general efficient to preserve image edges when they are used to reduce noise. However, they are not very effective to denoise those images that are corrupted by a high level of noise mainly for the lack of a reliable edge-stopping criterion in the partial differential equation (PDE). In this paper, a new algorithm is developed to tackle this problem. The main contribution of this paper is in the construction of a new regularization method for the PDE by using the over-complete dyadic wavelet transform (DWT). It proposes to perform anisotropic diffusion in the more stationary DWT domain rather than directly in the raw noisy image domain. In the DWT domain, since noise tends to decrease as the scale increases, at each scale, noise has less influence on the PDE than that in the raw noisy image domain. As a result, the edge-stopping criterion and other partial derivative measurements in the PDE become more reliable. Furthermore, there is no need to do Gaussian smoothing or any other smoothing operations. Experiment results show that the proposed algorithm can significantly reduce noise while preserving image edges. Index Terms--Adaptive statistical analysis, image restoration, multiscale anisotropic diffusion, scale-space, wavelet transform.

It was recently reported that the real-time flat panel detector-based cone-beam computed tomography (CBCT) breast imaging can help improve the detectability of small breast tumors with an X-ray dose comparable to that of the conventional mammography. In this paper, an efficient denoising algorithm is proposed to further reduce the X-ray exposure level required by a CBCT scan to acquire acceptable image quality. The proposed wavelet-based denoising algorithm possesses three significant characteristics: 1) wavelet coefficients at each scale are classified into two categories: irregular coefficients, and edge-related and regular coefficients; 2) noise in irregular coefficients is reduced as much as possible without producing artifacts to the denoised images; and 3) for the edge-related and regular coefficients, if they are at the first decomposition level, they are further denoised, otherwise, no modifications are made to them so as to obtain good visual quality for diagnosis. By applying the proposed denoising algorithm to the filtered projection images, the X-ray exposure level necessary for the CBCT scan can be reduced by up to 60% while obtaining clinically acceptable image quality. This denoising result indicates that in the clinical application of CBCT breast imaging, the patient radiation dose can be significantly reduced. Index Terms--Cone beam CT breast imaging, image denoising, multiscale singularity detection, wavelet transform.

This paper presents a very efficient algorithm for image denoising based on wavelets and multifractals for singularity detection. A challenge of image denoising is how to preserve the edges of an image when reducing noise. By modeling the intensity surface of a noisy image as statistically self-similar multifractal processes and taking advantage of the multiresolution analysis with wavelet transform to exploit the local statistical self-similarity at different scales, the pointwise singularity strength value characterizing the local singularity at each scale was calculated. By thresholding the singularity strength, wavelet coefficients at each scale were classified into two categories: the edge-related and regular wavelet coefficients and the irregular coefficients. The irregular coefficients were denoised using an approximate minimum mean-squared error (MMSE) estimation method, while the edge-related and regular wavelet coefficients were smoothed using the fuzzy weighted mean (FWM) filter aiming at preserving the edges and details when reducing noise. Furthermore, to make the FWM-based filtering more efficient for noise reduction at the lowest decomposition level, the MMSE-based filtering was performed as the first pass of denoising followed by performing the FWM-based filtering. Experimental results demonstrated that this algorithm could achieve both good visual quality and high PSNR for the denoised images. [ABSTRACT FROM AUTHOR]