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

https://www.onlinemedicalimages.com/images/medical/publications/8.%20Blood%20vessel%20segmentation%20methodologies.pdf

Blood vessel segmentation methodologies in retinal images - A survey

Blood vessel segmentation algorithms — Review of methods, datasets and evaluation metrics

http://www2.siit.tu.ac.th/bunyarit/publications/2012_Moazam_Elsevier_bitplanes.pdf

An approach to localize the retinal blood vessels using bit planes and centerline detection

RESULTS. The algorithm was able to assign cup, rim, and background correctly to 88% of all pixels. Correlations of the LCDR estimates of glaucoma fellows with those of the reference standard were 0.73 (95% CI, 0.58‐0.83), 0.81 (95% CI, 0.70‐ 0.89), and 0.86 (95% CI, 0.78‐0.91), respectively, whereas the correlation of the algorithm with the reference standard was 0.93 (95% CI, 0.89‐0.96; n 58). CONCLUSIONS. The pixel feature classification algorithm allows objective segmentation of the optic disc from conventional color stereo photographs automatically without human input. The performance of the disc segmentation and LCDR calculation of the algorithm was comparable to that of glaucoma fellows in training and is promising for objective evaluation of optic disc cupping. (Invest Ophthalmol Vis Sci. 2007;48: 1665‐1673) DOI:10.1167/iovs.06-1081

/pdf/automated-segmentation-of-the-optic-disc-from-stereo-color-3jwe8mlfvn.pdf

Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features.

Brain tumor classification is a crucial task to evaluate the tumors and make a treatment decision according to their classes. There are many imaging techniques used to detect brain tumors. However, MRI is commonly used due to its superior image quality and the fact of relying on no ionizing radiation. Deep learning (DL) is a subfield of machine learning and recently showed a remarkable performance, especially in classification and segmentation problems. In this paper, a DL model based on a convolutional neural network is proposed to classify different brain tumor types using two publicly available datasets. The former one classifies tumors into (meningioma, glioma, and pituitary tumor). The other one differentiates between the three glioma grades (Grade II, Grade III, and Grade IV). The datasets include 233 and 73 patients with a total of 3064 and 516 images on T1-weighted contrast-enhanced images for the first and second datasets, respectively. The proposed network structure achieves a significant performance with the best overall accuracy of 96.13% and 98.7%, respectively, for the two studies. The results indicate the ability of the model for brain tumor multi-classification purposes.

/pdf/multi-classification-of-brain-tumor-images-using-deep-neural-5g8sxmwykf.pdf

Multi-Classification of Brain Tumor Images Using Deep Neural Network

In this paper, segmentation of blood vessels from colour retinal images using a novel clustering algorithm with a partial supervision strategy is proposed. The proposed clustering algorithm, which is a RAdius based Clustering ALgorithm (RACAL), uses a distance based principle to map the distributions of the data by utilising the premise that clusters are determined by a distance parameter, without having to specify the number of clusters. Additionally, the proposed clustering algorithm is enhanced with a partial supervision strategy and it is demonstrated that it is able to segment blood vessels of small diameters and low contrasts. Results are compared with those from the KNN classifier and show that the proposed RACAL performs better than the KNN in case of abnormal images as it succeeds in segmenting small and low contrast blood vessels, while it achieves comparable results for normal images. For automation process, RACAL can be used as a classifier and results show that it performs better than the KNN classifier in both normal and abnormal images.

/pdf/segmentation-of-retinal-blood-vessels-using-a-novel-4rydoa2w3f.pdf

Segmentation of retinal blood vessels using a novel clustering algorithm (RACAL) with a partial supervision strategy

A new pre-processing method for colour fundus images with adaptive contribution of the red channel is proposed. Based on a condition that is developed in this paper, this method utilises the intensity information from both red and green channels instead of using only the green channel as in the usual practice. The histogram matching is used to modify the histogram of the green channel by using the histogram of the red channel (of the same retinal image) to obtain a new processed image having the advantages of both channels. This method can be used to correct non-uniform illumination in colour fundus images or as a pre-processing step in the automatic analysis of retinal images. Results show that the use of histogram matched (HM) image give better performance than using the green channel image when employing the two-dimensional matched filter to detect retinal blood vessels. At specificity of 90%, in case of abnormal images, sensitivity increased from 76% when using the green channel image to 82% when using the HM image compared with 81% when using the piece-wise threshold probing method. In case of normal images, at the same specificity, the sensitivity obtained when using green channel image or HM image was 87% compared with 88% for the piece-wise threshold probing method.

/pdf/novel-and-adaptive-contribution-of-the-red-channel-in-pre-425luvkacu.pdf

Novel and adaptive contribution of the red channel in pre-processing of colour fundus images

In this paper, a comprehensive approach for digital video watermarking is introduced, where a binary watermark image is embedded into the video frames. Each video frame is decomposed into sub-images using 3 level discrete wavelet transform then the Principle Component Analysis (PCA) transformation is applied for some selected blocks. The selection of the blocks depends on calculating the entropy of each block then the maximum entropy blocks were selected. The watermark is embedded into the maximum coefficient of the PCA block. The proposed scheme is tested using a number of video sequences. Experimental results show high imperceptibility and high robustness against several attacks. The computed PSNR achieves high score which is 47.1078 db.

/pdf/entropy-based-video-watermarking-scheme-using-wavelet-1p9qcr5b3h.pdf

Entropy based video watermarking scheme using wavelet transform and Principle Component Analysis

In this paper, a new segmentation scheme for the white blood cells from microscopic images is proposed. The method is based on the K-means clustering technique. The RGB test images are converted to the L∗a∗b color space, and then the two color components (a and b) are used as features to the K-means clustering algorithm. The proposed method is tested and evaluated using blood cell images from publicly available dataset. Experiments demonstrate that the proposed method performs well and able to segment white blood cells from microscopic images.

Nancy M. Salem

Papers

Multi-Classification of Brain Tumor Images Using Deep Neural Network

Segmentation of retinal blood vessels using a novel clustering algorithm (RACAL) with a partial supervision strategy

Novel and adaptive contribution of the red channel in pre-processing of colour fundus images

Entropy based video watermarking scheme using wavelet transform and Principle Component Analysis

Segmentation of white blood cells from microscopic images using K-means clustering