Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

"Graefe's Archive" is a distinguished international journal that presents original clinical reports and clinically relevant experimental studies. Founded in 1854 by Albrecht von Graefe to serve as a source of useful clinical information and a stimulus for discussion, the journal has published articles by leading ophthalmologists and vision research scientists for more than a century. With peer review by an international Editorial Board and prompt English-language publication, "Graefe's Archive" provides rapid dissemination of clinical and clinically related experimental information.

Graefe's archive for clinical and experimental ophthalmology

Computer-aided diagnosis of diabetic retinopathy: A review

Diabetes is a chronic end organ disease that occurs when the pancreas does not secrete enough insulin or the body is unable to process it properly. Over time, diabetes affects the circulatory system, including that of the retina. Diabetic retinopathy is a medical condition where the retina is damaged because fluid leaks from blood vessels into the retina. Ophthalmologists recognize diabetic retinopathy based on features, such as blood vessel area, exudes, hemorrhages, microaneurysms and texture. In this paper we review algorithms used for the extraction of these features from digital fundus images. Furthermore, we discuss systems that use these features to classify individual fundus images. The classifications efficiency of different DR systems is discussed. Most of the reported systems are highly optimized with respect to the analyzed fundus images, therefore a generalization of individual results is difficult. However, this review shows that the classification results improved has improved recently, and it is getting closer to the classification capabilities of human ophthalmologists.

Algorithms for the Automated Detection of Diabetic Retinopathy Using Digital Fundus Images: A Review

In this article, we focus on the complementary role of watermarking with respect to medical information security (integrity, authenticity ) and management We review sample cases where watermarking has been deployed, we conclude that watermarking has found a niche role in healthcare systems, as an instrument for protection of medical information, for secure sharing and handling of medical images The concern of medical experts on the preservation of documents diagnostic integrity remains paramount

A Review of Image Watermarking Applications in Healthcare

Diabetes mellitus is a major cause of visual impairment and blindness. Twenty years after the onset of diabetes, almost all patients with type 1 diabetes and over 60% of patients with type 2 diabetes will have some degree of retinopathy. Prolonged diabetes retinopathy leads to maculopathy, which impairs the normal vision depending on the severity of damage of the macula. This paper presents a computer-based intelligent system for the identification of clinically significant maculopathy, non-clinically significant maculopathy and normal fundus eye images. Features are extracted from these raw fundus images which are then fed to the classifier. Our protocol uses feed-forward architecture in an artificial neural network classifier for classification of different stages. Three different kinds of eye disease conditions were tested in 350 subjects. We demonstrated a sensitivity of more than 95% for these classifiers with a specificity of 100%, and results are very promising. Our systems are ready to run clinically on large amounts of datasets.

Automatic identification of diabetic maculopathy stages using fundus images.

Analysis of speech has become a popular non-invasive tool for assessing the speech abnormalities. Acoustic nature of the abnormal speech gives relevant information about the type of disorder in the speech production system. These signals are essentially non-stationary; may contain indicators of current disease, or even warnings about impending diseases. The indicators may be present at all times or may occur at random — during certain intervals of the day. However, to study and pinpoint abnormalities in voluminous data collected over several hours is strenuous and time consuming. Therefore, computer based analytical tools for in-depth study and classification of data over daylong intervals can be very useful in diagnostics. This paper deals with the classification of certain diseases using artificial neural network, and then analyzed. This analysis is carried out using continuous wavelet transformation patterns. The results for various types of subjects discussed in detail and it is evident that the classifier presented in this paper has a remarkable efficiency in the range of 80–85% of accuracy.

Classification and analysis of speech abnormalities

A new method for compact storage and transmission of medical images with concealed patient information in noisy environment is evinced Digital watermarking is the technique adapted here for interleaving patient information with medical images The patient information, which comprises of text data and signal graph, is encrypted to prevent unauthorized access of data The latest encryption algorithm (Rijndael) is used for encrypting the text information Signal graphs (ECG, EEG EMG etc) are compressed using DPCM technique To enhance the robustness of the embedded information, the patient information is coded by error correcting codes (ECC) Reed Solomon (RS) codes The noisy scenario is simulated by adding salt and pepper (S&P) noise to the embedded image For different signal to noise ratio (SNR) of the image, bit error rate (BER) and number of character altered (NOCA) for text data and percentage distortion (PDIST) for the signal graph is evaluated It is elicited that coded systems can perform better than the uncoded systems

Reliable transmission and storage of medical images with patient information using error control codes

This paper attempts to identify pathological disorders of larynx using wavelet analysis. Speech samples carry symptoms of disorder in the place of their origin. The speech signal is subjected to wavelet analysis, and the coefficients are used to identify disorders such as vocal fold paralysis. Multilayer artificial neural network is used for classification of normal and affected signals.

Identification of voice disorders using speech samples

The electrocardiogram (ECG) is a representative signal containing information about the condition of the heart. The shape and size of the P-QRS-T wave, the time intervals between its various peaks etc may contain useful information about the nature of disease afflicting the heart. However, the human observer can not directly monitor these subtle details. Besides, since bio-signals are highly subjective, the symptoms may appear at random in the time scale. Therefore, the heart rate variability signal is used as the base signal for the highly useful in diagnostics. This paper deals with the analysis of eight cardiac abnormalities using Auto Regressive (AR), modeling technique. The results are tabulated below for specific example.

P.S. Bhat

Papers

Automatic identification of diabetic maculopathy stages using fundus images.

Classification and analysis of speech abnormalities

Reliable transmission and storage of medical images with patient information using error control codes

Identification of voice disorders using speech samples

AR modeling of heart rate signals