The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper proposes a method for construction of classifiers for discharge summaries. First, morphological analysis is applied to a set of summaries and a term matrix is generated. Second, correspond analysis is applied to the classification labels and the term matrix and generates two dimensional coordinates. By measuring the distance between categories and the assigned points, ranking of key words...
Iris nevus can be described as a growth commonly found on the iris, or regions surrounding the pupil. This growth is usually pigmented and non-cancerous, and therefore harmless; often requiring little medical attention. However, it has been established that there exists a relatively high risk of transformation of such growths into iris melanoma, which is cancerous or malignant. Furthermore, it has...
In this paper, we propose a self-training method which uses unlabeled regions in the original images obtained from a colorectal Narrow Band Imaging (NBI) zoom-videoendoscope. The proposed method first trims a number of patches from unlabeled regions in the original images and uses them as unlabeled training samples. Classifiers are trained with the available labeled samples, as well as with those...
The topic of deep-learning has recently received considerable attention in the machine learning research community, having great potential to liberate computer scientists from hand-engineering training datasets, because the method can learn the desired features automatically. This is particularly beneficial in medical research applications of machine learning, where getting good hand labelling of...
By Residual Analysis, the patient characteristics, characteristics of medical institutions, and quality of medical care can be used on prediction of health — related quality of life at different time points. Artificial neural network (ANN) and multiple regressions are used on the different fields, and they have their own advantages. If the doctors would like to know Health-Related Quality of Life...
This paper is focused on the automated identification of the clinical free-text records that contain useful information (e.g. symptoms, modifiers, diagnosis, etc) of a certain disease. We introduce a novel semi-supervised machine learning algorithm to address this problem, by training the set covering machine in a bootstrapping procedure. The advantage of the proposed technique is that not only can...
This paper proposes an artificial neural network (ANN) based approach to diagnose patients infected with hepatotropic virus and the stage of disease. The proposed method detects the disease and classifies its stage to be acute, chronic or cirrhosis. The input to the system is in the form of basic pathological data based on various liver function tests (LFTs) and specific virological markers. In addition,...
One of the important problems in medical imaging is two-class classification, for example determination of benign from malignant cases in breast cancer treatment. In this paper we present a new support vector machine method for two-class medical image classification. The key idea of this method is to construct an optimal hypersphere such that both the interior margin between the surface of this sphere...
This paper presents a set of technologies developed to exploit Grid infrastructures for breast cancer CAD, that include (1) federated repositories of mammography images and clinical data over Grid storage, (2) a workstation for mammography image analysis and diagnosis and (3) a framework for data analysis and training machine learning classifiers over Grid computing power specially tuned for medical...
Conformal Prediction provides a framework for extending traditional machine learning algorithms, in order to complement predictions with reliable measures of confidence. The provision of such measures is significant for medical diagnostic systems, as more informed diagnoses can be made by medical experts. In this paper, we introduce a conformal predictor based on genetic algorithms, and we apply our...
This paper represents a novel use of artificial neural networks in medical science. The proposed technique involves training an MLP with BP learning algorithm to recognize the pattern of diagnosing and predicting five blood disorders, through the results of blood tests. The blood test parameters and diagnosis of physician about the diseases for 450 cases of patients from Taleghani hospital in Kermanshah,...
This study aimed at training artificial neural networks (ANN) to predict survival time in cancer patients by using microarray and clinical data. We analyzed public microarrays and clinical data sets in different kinds of cancer. We selected 15-30 genes (correlation coefficient>0.4) as ANN variables to train networks. The results shows ANN can predict survival time from Microarray data gene expression...
Cervical cancer is one of the most preventable/treatable forms of cancer, due to the fact that precursor signs for the disease can be detected in microscopic examination of cervical cells. Currently these examinations are purely visual, but the project reported aims to process the visual images to present them in a complementary auditory form and thereby to improve diagnostic accuracy. Standard mean-shift...
This paper proposes a classification scheme of prostate cancer patients based on support vector machines (SVM) classifiers that allow including the diagnosed prostate cancer patients into risk classes, before performing radical prostatectomy, according to their medical parameters. Our objective is to assess the use of SVM in order to predict the individual result of radical prostatectomy performed...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.