Background and Purpose—: We aimed to generate rigorous graphical and statistical reference data based on volumetric measurements for assessing the relative severity of white matter hyperintensities (WMHs) in patients with stroke. Methods—: We prospectively mapped WMHs from 2699 patients with first-ever ischemic stroke (mean age=66.8±13.0 years) enrolled consecutively from 11 nationwide stroke centers, from patient (fluid-attenuated-inversion-recovery) MRIs onto a standard brain template set. Using multivariable analyses, we assessed the impact of major (age/hypertension) and minor risk factors on WMH variability. Results—: We have produced a large reference data library showing the location and quantity of WMHs as topographical frequency-volume maps. This easy-to-use graphical reference data set allows the quantitative estimation of the severity of WMH as a percentile rank score. For all patients (median age=69 years), multivariable analysis showed that age, hypertension, atrial fibrillation, and left ventricular hypertrophy were independently associated with increasing WMH (0–9.4%, median=0.6%, of the measured brain volume). For younger (≤69) hypertensives (n=819), age and left ventricular hypertrophy were positively associated with WMH. For older (≥70) hypertensives (n=944), age and cholesterol had positive relationships with WMH, whereas diabetes mellitus, hyperlipidemia, and atrial fibrillation had negative relationships with WMH. For younger nonhypertensives (n=578), age and diabetes mellitus were positively related to WMH. For older nonhypertensives (n=328), only age was positively associated with WMH. Conclusions—: We have generated a novel graphical WMH grading (Kim statistical WMH scoring) system, correlated to risk factors and adjusted for age/hypertension. Further studies are required to confirm whether the combined data set allows grading of WMH burden in individual patients and a tailored patient-specific interpretation in ischemic stroke-related clinical practice.

Contrast enhancement is important and useful for consumer electronics. One widely accepted contrast enhancement method is global histogram equalization (GHE), which achieves comparatively better performance on almost all types of image but sometimes causes excessive visual deterioration. We propose a new extension of bi-histogram equalization called Bi-Histogram Equalization with Neighborhood Metric (BHENM). BHENM consists of two stages. First, large histogram bins that cause washout artifacts are divided into sub-bins using neighborhood metrics; the same intensities of the original image are arranged by neighboring information. In the second stage, the histogram of the original image is separated into two sub-histograms based on the mean of the histogram of the original image; the sub-histograms are equalized independently using refined histogram equalization, which produces flatter histograms. In an experimental trial, BHENM simultaneously preserved the brightness and enhanced the local contrast of the original image.

Background: In this study, we used a convolutional neural network (CNN) to classify Alzheimer’s disease (AD), mild cognitive impairment (MCI), and normal control (NC) subjects based on images of the hippocampus region extracted from magnetic resonance (MR) images of the brain. Materials and Methods: The datasets used in this study were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI). To segment the hippocampal region automatically, the patient brain MR images were matched to the International Consortium for Brain Mapping template (ICBM) using 3D-Slicer software. Using prior knowledge and anatomical annotation label information, the hippocampal region was automatically extracted from the brain MR images. Results: The area of the hippocampus in each image was preprocessed using local entropy minimization with a bi-cubic spline model (LEMS) by an inhomogeneity intensity correction method. To train the CNN model, we separated the dataset into three groups, namely AD/NC, AD/MCI, and MCI/NC. The prediction model achieved an accuracy of 92.3% for AD/NC, 85.6% for AD/MCI, and 78.1% for MCI/NC. Conclusion: The results of this study were compared to those of previous studies, and summarized and analyzed to facilitate more flexible analyses based on additional experiments. The classification accuracy obtained by the proposed method is highly accurate. These findings suggest that this approach is efficient and may be a promising strategy to obtain good AD, MCI and NC classification performance using small patch images of hippocampus instead of whole slide images.

Histogram equalization (GHE) is a simple and widely accepted method for contrast enhancement. Although there are extensions of GHE that can preserve the brightness of the original image better than the original method, these extensions sometimes fail to enhance the visualization of the original image. Therefore, we propose a new method called "Brightness Preserving Weight Clustering Histogram Equalization" (BPWCHE) that can simultaneously preserve the brightness of the original image and enhance visualization of the original image. BPWCHE assigns each non-zero bin of the original image's histogram to a separate cluster, and computes each cluster's weight. Then, to reduce the number of clusters, we use three criteria (cluster weight, weight ratio and widths of two neighboring clusters) to merge pairs of neighboring clusters. The clusters acquire the same partitions as the result image histogram. Finally, transformation functions for each cluster's sub-histogram are calculated based on the traditional GHE method in the new acquired partitions of the result image histogram, and the sub-histogram's gray levels are mapped to the result image by the corresponding transformation functions. We showed experimentally that BPWCHE can preserve image brightness and enhance visualization of images more effectively than GHE and other brightness preserving methods.

One of the most significant processes in cancer cell and tissue image analysis is the efficient extraction of features for grading purposes. This research applied two types of three-dimensional texture analysis methods to the extraction of feature values from renal cell carcinoma tissue images, and then evaluated the validity of the methods statistically through grade classification. First, we used a confocal laser scanning microscope to obtain image slices of four grades of renal cell carcinoma, which were then reconstructed into 3D volumes. Next, we extracted quantitative values using a 3D gray level cooccurrence matrix (GLCM) and a 3D wavelet based on two types of basis functions. To evaluate their validity, we predefined 6 different statistical classifiers and applied these to the extracted feature sets. In the grade classification results, 3D Haar wavelet texture features combined with principal component analysis showed the best discrimination results. Classification using 3D wavelet texture features was significantly better than 3D GLCM, suggesting that the former has potential for use in a computer-based grading system.

Microscopic biopsy images are coloured in nature because pathologists use the haematoxylin and eosin chemical colour dyes for biopsy examinations. In this study, biopsy images are used for histological grading and the analysis of benign and malignant prostate tissues. The following PCa grades are analysed in the present study: benign, grade 3, grade 4, and grade 5. Biopsy imaging has become increasingly important for the clinical assessment of PCa. In order to analyse and classify the histological grades of prostate carcinomas, pixel-based colour moment descriptor (PCMD) and gray-level co-occurrence matrix (GLCM) methods were used to extract the most significant features for multilayer perceptron (MLP) neural network classification. Haar wavelet transformation was carried out to extract GLCM texture features, and colour features were extracted from RGB (red/green/blue) colour images of prostate tissues. The MANOVA statistical test was performed to select significant features based on F-values and P-values using the R programming language. We obtained an average highest accuracy of 92.7% using level-1 wavelet texture and colour features. The MLP classifier performed well, and our study shows promising results based on multi-feature classification of histological sections of prostate carcinomas.