When treating a brain tumor, a doctor needs to know the site and the size of the tumor. Positron emission tomography (PET) can be effectively applied to diagnose such cancers based on the heightened glucose metabolism of early-stage cancer cells. The purpose of this research is to extract the regions of skull, brain tumor, and brain tissue from a series of PET brain images and then a three-dimensional (3D) model is reconstructed from the extracted skulls, brain tumors, and brain tissues. Knowing the relative site and size of a tumor within the skull is helpful to a doctor. The contours obtained by the segmentation method proposed in this study are quantitatively compared with the contours drawn by doctors on the same image set since the ground truth is unknown. The experimental results are impressive.

Abstract The stock market is a capitalistic haven where the issued shares are transferred, traded, and circulated. It bases stock prices on the issue market, however, the structure and trading activities of the stock market are much more complicated than the issue market itself. Therefore, making an accurate prediction becomes an intricate as well as highly difficult task. On the other hand, because of the potential benefits of stock prediction, it attracts generation after generation of scholars as well as investors to continuously develop various prediction methods from different perspectives, a myriad of theories, a multitude of investment strategies, and different practical experiences. In this article, aiming at the task of time series (financial) feature extraction and prediction of price movements, a new convolutional novel neural network that can be called a framework to improve the prediction accuracy of stock trading is proposed. The method that is proposed is called SSACNN, a short form of stock sequence array convolutional neural network. SSACNN collects data including historical data of prices and its leading indicators (options/futures) for a stock to take an array as the input graph of the convolutional neural network framework. In our experimental results, five Taiwanese and American stocks were used as a benchmark to compare with the previous algorithms and proposed algorithm, the motion prediction performance of SSACNN has been improved significantly and proved that it has the potential to be applied in the real financial market.

Abstract Stroke is one of the leading causes of death as well as results in a massive economic burden for society. Stroke is a cerebrovascular disease mainly divided into two types: ischemic stroke and hemorrhagic stroke, which, respectively, refer to the partial blockage and bleeding inside brain blood vessels. Both stroke types lead to nutrient and oxygen deprivation in the brain, which ultimately cause brain damage or death. This study focuses on ischemic stroke in rats with middle cerebral artery occlusion (MCAO) as experimental subjects, and the volumes of infarct and atrophy are calculated based on the brain slice images of rat brains stained with 2,3,5-triphenyl tetrazolium chloride. In this study, a stroke rat brain infarct and atrophy volumes computation system (SRBIAVC system) is developed to segment the infarcts and atrophies from the rat brain slice images. Based on the segmentation results, the infarct and atrophy volumes of a rat brain can be computed. In this study, 168 images of brain slices cut from 28 rat brains with MCAO are used as the test samples. The experimental results show that the segmentation results obtained by the SRBIAVC system are close to those obtained by experts.

A microarray analysis generally contains expression data of thousands of genes, but most of them are irrelevant to the disease of interest, making analyzing the genes concerning specific diseases complicated. Therefore, filtering out a few essential genes as well as their regulatory networks is critical, and a disease can be easily diagnosed just depending on the expression profiles of a few critical genes. In this study, a target gene screening (TGS) system, which is a microarray-based information system that integrates F-statistics, pattern recognition matching, a two-layer K-means classifier, a Parameter Detection Genetic Algorithm (PDGA), a genetic-based gene selector (GBG selector) and the association rule, was developed to screen out a small subset of genes that can discriminate malignant stages of cancers. During the first stage, F-statistic, pattern recognition matching, and a two-layer K-means classifier were applied in the system to filter out the 20 critical genes most relevant to ovarian cancer from 9600 genes, and the PDGA was used to decide the fittest values of the parameters for these critical genes. Among the 20 critical genes, 15 are associated with cancer progression. In the second stage, we further employed a GBG selector and the association rule to screen out seven target gene sets, each with only four to six genes, and each of which can precisely identify the malignancy stage of ovarian cancer based on their expression profiles. We further deduced the gene regulatory networks of the 20 critical genes by applying the Pearson correlation coefficient to evaluate the correlationship between the expression of each gene at the same stages and at different stages. Correlationships between gene pairs were calculated, and then, three regulatory networks were deduced. Their correlationships were further confirmed by the Ingenuity pathway analysis. The prognostic significances of the genes identified via regulatory networks were examined using online tools, and most represented biomarker candidates. In summary, our proposed system provides a new strategy to identify critical genes or biomarkers, as well as their regulatory networks, from microarray data.

MOTIVATION: Ovarian cancer is the fifth leading cause of cancer deaths in women in the western world for 2013. In ovarian cancer, benign tumors turn malignant, but the point of transition is difficult to predict and diagnose. The 5-year survival rate of all types of ovarian cancer is 44%, but this can be improved to 92% if the cancer is found and treated before it spreads beyond the ovary. However, only 15% of all ovarian cancers are found at this early stage. Therefore, the ability to automatically identify and diagnose ovarian cancer precisely and efficiently as the tissue changes from benign to invasive is important for clinical treatment and for increasing the cure rate. This study proposes a new ovarian carcinoma classification model using two algorithms: a novel discretization of food sources for an artificial bee colony (DfABC), and a support vector machine (SVM). For the first time in the literature, oncogene detection using this method is also investigated. RESULTS: A novel bio-inspired computing model and hybrid algorithms combining DfABC and SVM was applied to ovarian carcinoma and oncogene classification. This study used the human ovarian cDNA expression database to collect 41 patient samples and 9600 genes in each pathological stage. Feature selection methods were used to detect and extract 15 notable oncogenes. We then used the DfABC-SVM model to examine these 15 oncogenes, dividing them into eight different classifications according to their gene expressions of various pathological stages. The average accuracyof the eight classification experiments was 94.76%. This research also found some oncogenes that had not been discovered or indicated in previous scientific studies. The main contribution of this research is the proof that these newly discovered oncogenes are highly related to ovarian or other cancers. AVAILABILITY AND IMPLEMENTATION: http://mht.mis.nchu.edu.tw/moodle/course/view.php?id=7.

Many gel electrophoresis image segmentation methods have been proposed. However, most of the proposed methods cannot provide a satisfying performance since a gel electrophoresis image is a manually captured image often with various noise and poor quality. This paper presents a one-dimensional-gel image segmentation method (1DGISM) to cut the bands off from a one-dimensional gel electrophoresis image (1D-gel image). The experimental results showed that 1DGISM can give an impressive segmentation performance even if the band boundaries are very indistinct. Moreover, the authors suggest that a low exposure for imaging be helpful in segmenting bright bands. Alternatively, taking the image at a high exposure is useful if the bands are dark.

BACKGROUND: Leukocytes play an important role in the human immune system. The family of leukocytes is comprised of lymphocytes, monocytes, eosinophils, basophils, and neutrophils. Any infection or acute stress may increase or decrease the number of leukocytes. An increased percentage of neutrophils may be caused by an acute infection, while an increased percentage of lymphocytes can be caused by a chronic bacterial infection. It is important to realize an abnormal variation in the leukocytes. The five types of leukocytes can be distinguished by their cytoplasmic granules, staining properties of the granules, size of cell, the proportion of the nuclear to the cytoplasmic material, and the type of nucleolar lobes. The number of lobes increased when leukemia, chronic nephritis, liver disease, cancer, sepsis, and vitamin B12 or folate deficiency occurred. Clinical neutrophil hypersegmentation has been widely used as an indicator of B12 or folate deficiency.Biomedical technologists can currently recognize abnormal leukocytes using human eyes. However, the quality and efficiency of diagnosis may be compromised due to the limitations of the biomedical technologists' eyesight, strength, and medical knowledge. Therefore, the development of an automatic leukocyte recognition system is feasible and necessary. It is essential to extract the leukocyte region from a blood smear image in order to develop an automatic leukocyte recognition system. The number of lobes increased when leukemia, chronic nephritis, liver disease, cancer, sepsis, and vitamin B12 or folate deficiency occurred. Clinical neutrophil hypersegmentation has been widely used as an indicator of B12 or folate deficiency. RESULTS: The purpose of this paper is to contribute an automatic leukocyte nuclei image segmentation method for such recognition technology. The other goal of this paper is to develop the method of counting the number of lobes in a cell nucleus. The experimental results demonstrated impressive segmentation accuracy. CONCLUSIONS: Insensitive to the variance of images, the LNS (Leukocyte Nuclei Segmentation) method functioned well to isolate the leukocyte nuclei from a blood smear image with much better UR (Under Segmentation Rate), ER (Overall Error Rate), and RDE (Relative Distance Error). The presented LC (Lobe Counting) method is capable of splitting leukocyte nuclei into lobes. The experimental results illuminated that both methods can give expressive performances. In addition, three advanced image processing techniques were proposed as weighted Sobel operator, GDW (Gradient Direction Weight), and GBPD (Genetic-based Parameter Detector).

Otsupsilas thresholding method (OTM) is one of the most commonly used thresholding methods. Unfortunately, the threshold obtained by OTM is biased in favor of the class, whose standard deviation or quantity of data is larger. Besides, one may adopt distinct thresholds in different applications for a same data set. Accordingly, this paper proposes an adaptable threshold decision method (ATDM) to provide the most appropriate thresholds for assorted applications. This paper also proposes a PSO (particle swarm optimization) based parameter detector (PBPD) to decide the fittest parameters which are used by ATDM. Image segmentation extracts the regions of interest from an image for follow-up analyses, and thresholding is one important technique for image segmentation. This paper will employ ATDM to detect the object contours in an image in order to investigate the performance of ATDM. The experiments show that ATDM can give impressive segmentation results.

In this paper we present some performance comparisons of several unsupervised clustering techniques include: Self-Organizing Map (SOM), Fuzzy C-means (FCM) and hierarchical clustering, and they are employed to analyze the ovarian cancer microarray data. The data includes 15 samples with 9,600 genes and these samples include 5 benign ovarian tumors (OVT), 1 borderline ovarian malignancy (OVTT), 4 ovarian cancers at stage I (OVCAI), and 5 ovarian cancers at stage III (OVCAIII). A regression analysis is used to reduce the dimension and get 9600 residuals of genes. The genes with 100 largest and 100 smallest residual are picked to analyze using analysis of variance (ANOVA). After the ANOVA, 12 gene markers are got and can be used to distinguish OVT, OVTT, OVCAI and OVCAIII samples. The 12 gene markers are performed clustering by the SOM, FCM and hierarchical clustering techniques and to compare the results between these clustering techniques. Our experimental results show that the hierarchical clustering can get best performance of clustering and users do not need to define the number of clusters.