SegAnyNeuron: a neural image segmentation network with strong generalization performance by modeling image intensity variation.

Image segmentation is an important basis for extracting the structure characteristics of the rock. In order to solve the problem that the traditional image segmentation method does not segment the rock image accurately, the genetic algorithm is used to optimize the traditional back propagation (abbreviated as BP) neural network image segmentation method. The features of the rock image domain are extracted, and the training samples are further corrected. Using the improved back propagation neural network rock image segmentation method, the rock image is segmented for three aspects: connected domain, local domain and edge domain. The calculation results compared with ImageJ software and traditional BP neural network show that under the condition of small sample size, the improved BP neural network not only can autonomously learn the whole connected structure, local domain structure and edge structure in the rock image, but improve the accuracy and speed of the BP neural network for rock image segmentation.

The subject of research in the article are the processes of formalization of the pixel-by-pixel classification problem using the modified fuzzy neural production network of Wang-Mendel for segmentation of urban structures in the automated analysis of space and aerial photographs of the city. The purpose of the work is to develop the architecture of the modified fuzzy neural production network of Wang-Mendel as a classifier for image segmentation to increase the values of efficiency and reliability of urban monitoring. The following tasks are solved in the article: analysis of possibilities of Wang-Mendel network modification based on representation of membership functions in terms of interval fuzzy sets of the second type (IFST2) and realization of phasing, aggregation and activation operations using IFST 2 operations, development of the architecture of the modified fuzzy neural production network of Wang-Mendel as a classifier for image segmentation. The following methods and models are used: methods and models of fuzzy set theory (fuzzy Wang-Mendel neural network, interval fuzzy sets of the second type), methods and models of deep learning methodology (convolutional neural network for image segmentation (auto coder) U-net). The following results were obtained: the use of a fuzzy Wang-Mendel neural network as a classifier of a modified U-Net decoder based on the representation of membership functions in IFST2 and the implementation of phasing, aggregation and activation operations using operations on IFST2; introduction of an additional operation of type reduction in the phase of dephasification of the original variable based on the classical method of the center of gravity (centroid); introduction of several outputs of the network to recognize the appropriate number of classes (subclasses) of the subject area. To do this, the third layer is represented as a set of several pairs of adder neurons, and the fourth implements several normalizing neurons, the number of which corresponds to the number of pairs of the third layer. Conclusions: the use in the architecture of a convolutional neural network for segmentation of U-net images as a classifier of the modified fuzzy neural production network of Wang-Mendel will provide an additional increase in the accuracy of pixel-by-pixel classification of certain objects. Instead of fuzzy sets of the first type (FST1) in this network IFST2 are used. The proposed IFST2, on the one hand, provide a formalization of more additional degrees of uncertainty compared to FST1, on the other hand, are "implemented" in the development of fuzzy systems (models) and have less computational complexity, compared to fuzzy sets of the second type (FST2).

MH-Net: Model-data-driven hybrid-fusion network for medical image segmentation

Currently, neural networks are being widely implemented for the diagnosis of various diseases, including cancer of various localizations and stages. The vast majority of such solutions use supervised or unsupervised convolutional neural networks, which require a great deal of training data. Using unsupervised image segmentation algorithms can be considered the preferred trend since their use significantly reduces the complexity of neural network training. So, developing unsupervised image segmentation algorithms is one of the topical tasks of machine learning. This year, a team of developers from Google, MIT, and Cornell University developed the STEGO algorithm, which is an unsupervised and non-convolutional neural network. As its author stated, the STEGO algorithm performs well at image segmentation problems compared with other machine learning models. And this algorithm does not need a large amount of training data, unlike convolutional neural networks, which are widely used for medical image analysis. So, the aim of this work is to check the possibility of using this neural network for scintigraphy image segmentation by testing whether the STEGO algorithm is relevant when applied to a scintigraphy dataset. To achieve this goal, the intersection over union metric (IoU) was chosen for evaluating the correctness of the detection of the location of metastases. The training dataset consists of scintigraphic images of patients with various types of cancer and various metastasis appearances. Another version of this metric (mIoU, mean intersection over union) was also used by the creators of STEGO to assess the quality of the model to segment images with different kinds of content. Since the calculated metrics are not good enough, the use of this algorithm for scintigraphic image analysis is not possible or requires the development of a special methodology for this.

In this paper, we proposed an hybrid optimal radial-basis function (RBF) neural network for approximation and illumination invariant image segmentation. Unlike other RBF learning algorithms, the proposed paradigm introduces a new way to train RBF models by using optimal learning factors (OLFs) to train the network parameters, i.e. spread parameter, kernel vector and a weighted distance measure (DM) factor to calculate the activation function. An efficient second order Newton's algorithm is proposed for obtaining multiple OLF's (MOLF) for the network parameters. The weights connected to the output layer are trained by a supervised-learning algorithm based on orthogonal least square (OLS). The error obtained is then back-propagated to tune the RBF parameters. By applying RBF network for approximation on some real-life datasets and classification to reduce illumination effects of image segmentation, the results show that the proposed RBF neural network has fast convergence rates combining with low computational time cost, allowing it a good choice for real-life application such as image segmentation.

Liver Segmentation on a Variety of Computed Tomography (CT) Images Based on Convolutional Neural Networks Combined with Connected Components

Terahertz digital holographic reconstructed images are vulnerable to noise pollution. This paper uses neural network to segment terahertz image, because this method is insensitive to noise. Firstly, the training sample image is decomposed into several sub-images, and the backward propagation(BP) neural network is trained by them. At the same time, the optimal number of hidden layer neurons is selected. Then the trained neural network is applied to the segmentation of terahertz image. Different segmentation results are obtained by changing the variance of noise in the training sample image. The best segmentation results and training samples are determined by using the mean structural similarity(MSSIM). Finally, compared with the classical image segmentation algorithm, the results show that the segmentation effect of the neural network is better.

Recent years have shown that deep learning neural networks are a valuable tool in the field of computer vision. Deep learning method can be used in applications like remote sensing such as Land cover Classification, Detection of Vehicle in Satellite Images, Hyper spectral Image classification. This paper addresses the use of the deep learning artificial neural network in Satellite image segmentation. Image segmentation plays an important role in image processing. The hue of the remote sensing image often has a large hue difference, which will result in the poor display of the images in the VR environment. Image segmentation is a pre processing technique applied to the original images and splits the image into many parts which have different hue to unify the color. Several computational models based on supervised, unsupervised, parametric, probabilistic region based image segmentation techniques have been proposed. Recently, one of the machine learning technique known as, deep learning with convolution neural network has been widely used for development of efficient and automatic image segmentation models. In this paper, we focus on study of deep neural convolution network and its variants for automatic image segmentation rather than traditional image segmentation strategies.

Deep Learning, refers to large set of neural network based algorithms, have emerged as promising machine- learning tools in the general imaging and computer vision domains. Convolutional neural networks (CNNs), a specific class of deep learning algorithms, have been extremely effective in object recognition and localization in natural images. A characteristic feature of CNNs, is the use of a locally connected multi layer topology that is inspired by the animal visual cortex (the most powerful vision system in existence). While CNNs, perform admirably in object identification and localization tasks, typically require training on extremely large datasets. Unfortunately, in medical image analysis, large datasets are either unavailable or are extremely expensive to obtain. Further, the primary tasks in medical imaging are organ identification and segmentation from 3D scans, which are different from the standard computer vision tasks of object recognition. Thus, in order to translate the advantages of deep learning to medical image analysis, there is a need to develop deep network topologies and training methodologies, that are geared towards medical imaging related tasks and can work in a setting where dataset sizes are relatively small. In this paper, we present a technique for stacked supervised training of deep feed forward neural networks for segmenting organs from medical scans. Each `neural network layer' in the stack is trained to identify a sub region of the original image, that contains the organ of interest. By layering several such stacks together a very deep neural network is constructed. Such a network can be used to identify extremely small regions of interest in extremely large images, inspite of a lack of clear contrast in the signal or easily identifiable shape characteristics. What is even more intriguing is that the network stack achieves accurate segmentation even when it is trained on a single image with manually labelled ground truth. We validate this approach,using a publicly available head and neck CT dataset. We also show that a deep neural network of similar depth, if trained directly using backpropagation, cannot acheive the tasks achieved using our layer wise training paradigm.

M3Net: A multi-model, multi-size, and multi-view deep neural network for brain magnetic resonance image segmentation

The article suggests an algorithm of graphical image segmentation. The suggested algorithm uses a neural network to identify one particular pixel as belonged to the certain segment of an image. As a segmentation method, is used a method of growing areas based on comparing the nearest neighbors of one particular pixel. To make a decision about the similarity of two pixels, a three-layer perceptron is used. Three RGB color components are compared during processing. Thus, there are 6 neurons in the input layer of the neural network, namely 3 for the RGB component of the first pixel and 3 for the RGB component of the second one. In a specific implementation there are 50 neurons in the middle layer of the neural network. In the output layer of the neural network there are 2 neurons that represent similarity or difference of the comparing pixels. A training set of the neural network is formed using a specially generated impulse noise. There is a linear congruent generator of pseudo-random number used for noise generation. This generator is used to generate both the color and the coordinates of the noisy pixel. To form a training set, the certain number of noisy pixels is generated. In the article, this number is 10% of all pixels in the image. Then, for each damaged pixel, the training sets are formed so that all the nearest neighbors are considered to be in different clusters with a damaged pixel. A computer experiment was carried out both in automatic mode and in interactive one. The results of the experiment have shown that the algorithm provides fairly good training neural network for image segmentation without involving additional images.

The paper provides the method of the improved genetic neural network for image segmentation. The method uses improved genetic algorithm BP neural network weights and thresholds to optimize, and use the definition of bipolar fitness function mapping compression to speed up neural network training speed, and then use iterative improved neural network algorithm to achieve image segmentation. The results of experimental show that the improved genetic neural network can better achieve the image segmentation, compared with the traditional method; Compared with BP neural network training speed is greatly improved.

Background and Objectives: medical image Segmentation is a challenging task due to low contrast between Region of Interest and other textures, hair artifacts in dermoscopic medical images, illumination variations in images like Chest-Xray and various imaging acquisition conditions.Methods: In this paper, we have utilized a novel method based on Convolutional Neural Networks (CNN) for medical image Segmentation and finally, compared our results with two famous architectures, include U-net and FCN neural networks. For loss functions, we have utilized both Jaccard distance and Binary-crossentropy and the optimization algorithm that has used in this method is SGD+Nestrov algorithm. In this method, we have used two preprocessing include resizing image’s dimensions for increasing the speed of our process and Image augmentation for improving the results of our network. Finally, we have implemented threshold technique as postprocessing on the outputs of neural network to improve the contrast of images. We have implemented our model on the famous publicly, PH2 Database, toward Melanoma lesion segmentation and chest Xray images because as we have mentioned, these two types of medical images contain hair artifacts and illumination variations and we are going to show the robustness of our method for segmenting these images and compare it with the other methods.Results: Experimental results showed that this method could outperformed two other famous architectures, include Unet and FCN convolutional neural networks. Additionally, we could improve the performance metrics that have used in dermoscopic and Chest-Xray segmentation which used before.Conclusion: In this work, we have proposed an encoder-decoder framework based on deep convolutional neural networks for medical image segmentation on dermoscopic and Chest-Xray medical images. Two techniques of image augmentation, image rotation and horizontal flipping on the training dataset are performed before feeding it to the network for training. The predictions produced from the model on test images were postprocessed using the threshold technique to remove the blurry boundaries around the predicted lesions.

This work proposes Group method Data Handling (GMDH) neural network for the segmentation of liver and liver tumor on abdomen CT images. The structure of the GMDH neural network is automatically structured using heuristic self-organization. Prior to segmentation, Nonlinear Tensor Diffusion (NLTD) filter was used for the preprocessing of input images. Feature extraction was performed by first order statistics and local binary pattern. The parameters of neural network like the number of useful input variables, the number of neurons in each layer and the selection of optimum neural network architecture are determined by using the error criterion derived from AIC (Akaike's Information Criterion). The performance of the GMDH algorithm was evaluated by success and error rates, similarity measures and the results outperform the back propagation neural network algorithm. The algorithms are developed in Matlab 2013a and tested on real time abdomen CT datasets. The satisfactory results were obtained by GMDH algorithm and are useful for computer aided diagnosis of liver cancer.

In accordance with the inability of various hair artefacts subjected to dermoscopic medical images, undergoing illumination challenges that include chest-Xray featuring conditions of imaging acquisi-tion situations built with clinical segmentation. The study proposed a novel deep-convolutional neural network (CNN)-integrated methodology for applying medical image segmentation upon chest-Xray and dermoscopic clinical images. The study develops a novel technique of segmenting medical images merged with CNNs with an architectural comparison that incorporates neural networks of U-net and fully convolutional networks (FCN) schemas with loss functions associated with Jaccard distance and Binary-cross entropy under optimised stochastic gradient descent + Nesterov practices. Digital image over clinical approach significantly built the diagnosis and determination of the best treatment for a patient’s condition. Even though medical digital images are subjected to varied components clarified with the effect of noise, quality, disturbance, and precision depending on the enhanced version of images segmented with the optimised process. Ultimately, the threshold technique has been employed for the output reached under the pre- and post-processing stages to contrast the image technically being developed. The data source applied is well-known in PH2 Database for Melanoma lesion segmentation and chest X-ray images since it has variations in hair artefacts and illumination. Experiment outcomes outperform other U-net and FCN architectures of CNNs. The predictions produced from the model on test images were post-processed using the threshold technique to remove the blurry boundaries around the predicted lesions. Experimental results proved that the present model has better efficiency than the existing one, such as U-net and FCN, based on the image segmented in terms of sensitivity = 0.9913, accuracy = 0.9883, and dice coefficient = 0.0246.