Contour integration and segmentation with self-organized lateral connections

Contour integration in low-level vision is believed to occur based on lateral interaction between neurons with similar orientation tuning. How such interactions could arise in the brain has been an open question. Our model suggests that the interactions can be learned through input-driven self-organization, i.e., through the same mechanism that underlies many other developmental and functional phenomena in the visual cortex. The model also shows how synchronized firing mediated by these lateral connections can represent the percept of a contour, resulting in performance similar to that of human contour integration. The model further demonstrates that contour integration performance can differ in different parts of the visual field, depending on what kinds of input distributions they receive during development. The model thus grounds an important perceptual phenomenon onto detailed neural mechanisms so that various structural and functional properties can be measured and predictions can be made to guide future experiments.     

A network of coupled chaotic maps for adaptive multi-scale image segmentation

In this paper, a network of coupled chaotic maps for multi-scale image segmentation is proposed. Time evolutions of chaotic maps that correspond to a pixel cluster are synchronized with one another, while this synchronized evolution is desynchronized with respect to time evolution of chaotic maps corresponding to other pixel clusters in the same image. The number of pixel clusters is previously unknown and the adaptive pixel moving technique introduced in the model makes it robust enough to classify ambiguous pixels.     

Enhanced radial basis function neural network for tomato plant disease leaf image segmentation

Primary crop losses in agriculture are due to leaf diseases, which farmers cannot identify early. If the diseases are not detected early and correctly, then the farmer will have to undergo huge losses. Therefore, in the field of agriculture, the detection of leaf diseases in tomato crops plays a vital role. Recent advances in computer vision and deep learning techniques have made disease prediction easy in agriculture. Tomato crop front side leaf images are considered for research due to their high exposure to diseases. The image segmentation process assumes a significant role in identifying disease affected areas on tomato leaf images. Therefore, this paper develops an efficient tomato crop leaf disease segmentation model using an enhanced radial basis function neural network (ERBFNN). The proposed ERBFNN is enhanced using the modified sunflower optimization (MSFO) algorithm. Initially, the noise present in the images is removed by a Gaussian filter followed by CLAHE (contrast-limited adaptive histogram equalization) based on contrast enhancement and un-sharp masking. Then, color features are extracted from each leaf image and given to the segmentation stage to segment the disease portion of the input image. The performance of the proposed ERBFNN approach is estimated using different metrics such as accuracy, Jaccard coefficient (JC), Dice's coefficient (DC), precision, recall, F-Measure, sensitivity, specificity, and mean intersection over union (MIoU) and are compared with existing state-of-the-art methods of radial basis function (RBF), fuzzy c-means (FCM), and region growing (RG). The experimental results show that the proposed ERBFNN segmentation model outperformed with an accuracy of 98.92% compared to existing state-of-the-art methods like RBFNN, FCM, and RG, as well as previous research work.     

DeepMIB: User-friendly and open-source software for training of deep learning network for biological image segmentation

We present DeepMIB, a new software package that is capable of training convolutional neural networks for segmentation of multidimensional microscopy datasets on any workstation. We demonstrate its successful application for segmentation of 2D and 3D electron and multicolor light microscopy datasets with isotropic and anisotropic voxels. We distribute DeepMIB as both an open-source multi-platform Matlab code and as compiled standalone application for Windows, MacOS and Linux. It comes in a single package that is simple to install and use as it does not require knowledge of programming. DeepMIB is suitable for everyone interested of bringing a power of deep learning into own image segmentation workflows.     

Topological feature maps with self-organized lateral connections: a population-coded,one-layer model of associative memory

Guided by the neurobiological principles of self-organization and population coding, we develop a simple, neural, one-layer model for auto-association. Its core is a feature map endowed with self-organized lateral connections. Input patterns are coded by small spots of active neurons. The time evolution of neural activity then realizes an auto-association process by a recurrent attractor dynamics. Population coding is preserved due to a balance of diffusive spreading of activity and competitive refocusing. Because of its simplicity, the model allows a thorough qualitative and quantitative understanding. We show that the network is capable of performing a cluster analysis and hierarchical classification of data and, thus, qualifies as a tool for unsupervised statistical data analysis.     

A watershed approach for improving medical image segmentation

In this paper, a novel watershed approach based on seed region growing and image entropy is presented which could improve the medical image segmentation. The proposed algorithm enables the prior information of seed region growing and image entropy in its calculation. The algorithm starts by partitioning the image into several levels of intensity using watershed multi-degree immersion process. The levels of intensity are the input to a computationally efficient seed region segmentation process which produces the initial partitioning of the image regions. These regions are fed to entropy procedure to carry out a suitable merging which produces the final segmentation. The latter process uses a region-based similarity representation of the image regions to decide whether regions can be merged. The region is isolated from the level and the residual pixels are uploaded to the next level and so on, we recall this process as multi-level process and the watershed is called multi-level watershed. The proposed algorithm is applied to challenging applications: grey matter–white matter segmentation in magnetic resonance images (MRIs). The established methods and the proposed approach are experimented by these applications to a variety of simulating immersion, multi-degree, multi-level seed region growing and multi-level seed region growing with entropy. It is shown that the proposed method achieves more accurate results for medical image oversegmentation.     

Confocal DNA cytometry: a contour-based segmentation algorithm for automated three-dimensional image segmentation

BACKGROUND: Confocal laser scanning microscopy (CLSM) presents the opportunity to perform three-dimensional (3D) DNA content measurements on intact cells in thick histological sections. So far, these measurements have been performed manually, which is quite time-consuming. METHODS: In this study, an intuitive contour-based segmentation algorithm for automatic 3D CLSM image cytometry of nuclei in thick histological sections is presented. To evaluate the segmentation algorithm, we measured the DNA content and volume of human liver and breast cancer nuclei in 3D CLSM images. RESULTS: A high percentage of nuclei could be segmented fully automatically (e.g., human liver, 92%). Comparison with (time-consuming) interactive measurements on the same CLSM images showed that the results were well correlated (liver, r = 1.00; breast, r = 0.92). CONCLUSIONS: Automatic 3D CLSM image cytometry enables measurement of volume and DNA content of large numbers of nuclei in thick histological sections within an acceptable time. This makes large-scale studies feasible, whereby the advantages of CLSM can be exploited fully. The intuitive modular segmentation algorithm presented in this study detects and separates overlapping objects, also in two-dimensional (2D) space. Therefore, this algorithm may also be suitable for other applications.     

A network model with auto-oscillating output and dynamic connections

A major problem that researchers attempting to elaborate mathematical models of neurophysiological and/or psychophysiological processes are confronted with is the identification of the mechanisms that give rise, in a neural network, to oscillatory behavior, either spontaneous or induced by external stimuli. The present work starts by considering a network model of a central pattern generator (CPG), introduced by Sompolinsky and co-authors. The present authors try to generalize this model to a wider range of biological situations, by introducing into it dynamic adjustments of connections among the processing units. Although the study performed so far is quite preliminary, some analytical considerations can be presented, supported by the results of numerical simulations, which show always a relaxation of the network toward specific stable states.     

CT image segmentation using FEM with optimized boundary condition

The authors propose a CT image segmentation method using structural analysis that is useful for objects with structural dynamic characteristics. Motivation of our research is from the area of genetic activity. In order to reveal the roles of genes, it is necessary to create mutant mice and measure differences among them by scanning their skeletons with an X-ray CT scanner. The CT image needs to be manually segmented into pieces of the bones. It is a very time consuming to manually segment many mutant mouse models in order to reveal the roles of genes. It is desirable to make this segmentation procedure automatic. Although numerous papers in the past have proposed segmentation techniques, no general segmentation method for skeletons of living creatures has been established. Against this background, the authors propose a segmentation method based on the concept of destruction analogy. To realize this concept, structural analysis is performed using the finite element method (FEM), as structurally weak areas can be expected to break under conditions of stress. The contribution of the method is its novelty, as no studies have so far used structural analysis for image segmentation. The method's implementation involves three steps. First, finite elements are created directly from the pixels of a CT image, and then candidates are also selected in areas where segmentation is thought to be appropriate. The second step involves destruction analogy to find a single candidate with high strain chosen as the segmentation target. The boundary conditions for FEM are also set automatically. Then, destruction analogy is implemented by replacing pixels with high strain as background ones, and this process is iterated until object is decomposed into two parts. Here, CT image segmentation is demonstrated using various types of CT imagery.     

A thresholding method for automatic cell image segmentation.

An algorithm for automatic segmentation of PAP-stained cell images and its digital implementation is described. First, the image is filtered in order to eliminate the granularily and small objects in the image which may upset the segmentation procedure. In a second step, information on gradient and compactness is extracted from the filtered image and stored in three histograms as functions of the extinction. From these histograms, two extinction thresholds are computed. These thresholds are suitable to separate the nucleus from the cytoplasm, and the cytoplasm from the background in the filtered image. Masks are determined in this way, and finally used to analyse the nucleus and the cytoplasm in the original image.     

A dynamical neural network for hitting an approaching object

Besides making contact with an approaching ball at the proper place and time, hitting requires control of the effector velocity at contact. A dynamical neural network for the planning of hitting movements was derived in order to account for both these requirements. The model in question implements continuous required velocity control by extending the Vector Integration To Endpoint model while providing explicit control of effector velocity at interception. It was shown that the planned movement trajectories generated by the model agreed qualitatively with the kinematics of hitting movements as observed in two recent experiments. Outstanding features of this comparison concerned the timing and amplitude of the empirical backswing movements, which were largely consistent with the predictions from the model. Several theoretical implications as well as the informational basis and possible neural underpinnings of the model were discussed.     

Mobile image sensors for object detection using color segmentation

The intelligent mobile robot with sensors and image processing embedded system combines the suction and aerodynamic attraction to achieve good balance between strong adhesion force and high mobility. Experimental results showed that the robot can move upward on the wall at the speed of 2.9 m/min and carry 5 kg payload in addition to 2.5 kg self-weight, which record the highest payload capacity among climbing robots of similar size. It also implements object detection ability using effective color transform and segmentation technique for the exact target detection on the wall using a embedded camera system, communication module and several active sensors.     

Oscillatory lunatic fringe activity is crucial for segmentation of the anterior but not posterior skeleton

The Notch pathway plays multiple roles during vertebrate somitogenesis, functioning in the segmentation clock and during rostral/caudal (R/C) somite patterning. Lunatic fringe (Lfng) encodes a glycosyltransferase that modulates Notch signaling, and its expression patterns suggest roles in both of these processes. To dissect the roles played by Lfng during somitogenesis, a novel allele was established that lacks cyclic Lfng expression within the segmentation clock, but that maintains expression during R/C somite patterning (Lfng(DeltaFCE1)). In the absence of oscillatory Lfng expression, Notch activation is ubiquitous in the PSM of Lfng(DeltaFCE1) embryos. Lfng(DeltaFCE1) mice exhibit severe segmentation phenotypes in the thoracic and lumbar skeleton. However, the sacral and tail vertebrae are only minimally affected in Lfng(DeltaFCE1) mice, suggesting that oscillatory Lfng expression and cyclic Notch activation are important in the segmentation of the thoracic and lumbar axial skeleton (primary body formation), but are largely dispensable for the development of sacral and tail vertebrae (secondary body formation). Furthermore, we find that the loss of cyclic Lfng has distinct effects on the expression of other clock genes during these two stages of development. Finally, we find that Lfng(DeltaFCE1) embryos undergo relatively normal R/C somite patterning, confirming that Lfng roles in the segmentation clock are distinct from its functions in somite patterning. These results suggest that the segmentation clock may employ varied regulatory mechanisms during distinct stages of anterior/posterior axis development, and uncover previously unappreciated connections between the segmentation clock, and the processes of primary and secondary body formation.     

Feature-based image segmentation in human vision

Experiments are described which indicate that the integration of high-precision shape information along a bright line is blocked by the presence of certain image features. All the features involved have three properties: (1) they are points where contours are not smooth (i.e. not twice differentiable) within the limits set by the finite space constants of visual processes; (2) they are all points that are emphasized in the responses of certain classes of circularly symmetric bandpass spatial filter; and (3) they are all significant for three-dimensional shape analysis. The results are interpreted as implying an inflexible segmentation of the contour image before detailed shape analysis.     

Relaxation network for Gabor image decomposition

The so-called simple cells in layer IV of feline primary visual cortex have been shown to have Gabor function spatial receptive field profiles (RFP's). Since Gabor functions are not mutually orthogonal, the decomposition of an image into Gabor function coefficients is usually performed by minimising some measure of the error between the original image and that reconstructed from the coefficients. A cortical relaxation model is proposed which performs this minimisation implicitly, and is used to examine the biological relevance and feasibility of reconstruction error minimisation.     

TRUS image segmentation with non-parametric kernel density estimation shape prior

Due to noises, speckles, etc., automatic prostate segmentation is rather challenging, and using only low-level information such as intensity gradient is insufficient and unable to tackle the problem. In this paper, we propose an automatic prostate segmentation method combining intrinsic properties of TRUS images with the high-level shape prior information. First, intrinsic properties of TRUS images, such as the intensity transition near the prostate boundary as well as the speckle induced texture features obtained by Gabor filter banks, are integrated to deform the model to the target contour. These properties make our method insensitive to high gradient regions introduced by noises and speckles. Then, the preliminary segmentation is fine-tuned by the non-parametric shape prior, which is optimally distilled by non-parametric kernel density estimation as it can approximate arbitrary distributions. The refinement is along the direction of mean shift vector, and considerably strengthens the robustness of the method. The performance of our method is validated by experimental results. Compared with the state of the art, the accuracy and robustness of the method is quite promising, and the mean absolute distance is only 1.21 ± 0.85 mm.     

Topology-based fluorescence image analysis for automated cell identification and segmentation

Cell segmentation refers to the body of techniques used to identify cells in images and extract biologically relevant information from them; however, manual segmentation is laborious and subjective. We present Topological Boundary Line Estimation using Recurrence Of Neighbouring Emissions (TOBLERONE), a topological image analysis tool which identifies persistent homological image features as opposed to the geometric analysis commonly employed. We demonstrate that topological data analysis can provide accurate segmentation of arbitrarily-shaped cells, offering a means for automatic and objective data extraction. One cellular feature of particular interest in biology is the plasma membrane, which has been shown to present varying degrees of lipid packing, or membrane order, depending on the function and morphology of the cell type. With the use of environmentally-sensitive dyes, images derived from confocal microscopy can be used to quantify the degree of membrane order. We demonstrate that TOBLERONE is capable of automating this task.     

Oscillatory neural network for pattern recognition: trajectory based classification and supervised learning

Computer algorithms that match human performance in recognizing written text or spoken conversation remain elusive. The reasons why the human brain far exceeds any existing recognition scheme to date in the ability to generalize and to extract invariant characteristics relevant to category matching are not clear. However, it has been postulated that the dynamic distribution of brain activity (spatiotemporal activation patterns) is the mechanism by which stimuli are encoded and matched to categories. This research focuses on supervised learning using a trajectory based distance metric for category discrimination in an oscillatory neural network model. Classification is accomplished using a trajectory based distance metric. Since the distance metric is differentiable, a supervised learning algorithm based on gradient descent is demonstrated. Classification of spatiotemporal frequency transitions and their relation to a priori assessed categories is shown along with the improved classification results after supervised training. The results indicate that this spatiotemporal representation of stimuli and the associated distance metric is useful for simple pattern recognition tasks and that supervised learning improves classification results.     

Automatic image segmentation with linear clustering for quantification of neointimal formation after surgical vein grafting

OBJECTIVE: To identify extracellular matrix deposition on combined Masson elastin stains from cross-sectional, fixed vein grafts. STUDY DESIGN: Source vectors from RGB components of color images are transformed into new vectors with most of the energy concentrated in fewer coefficients based on the eigenvalues and eigenvectors of their co-variance matrix so their dimension can be reduced for efficient computation and analysis. The vectors are distributed in a triangular shape in which most vectors are located in a long, narrow strip that can be approximated by a straight line while a separate group of vectors from collagen areas form a loose cluster away from the line. An iterative procedure has been developed for the representative vectors in the 2 centroids for linear and circular clusters. The linear centroid consists of all vectors in a straight line, and the centroid of the circular cluster is a single vector. Vector classification is based on the measure of its distance to each of the 2 centroids. RESULTS: The automatic segmentation of the collagen content pixels in green-blue matches the image background color. CONCLUSION: The procedure automatically quantifies and characterizes the neointimal deposition after surgical vein grafting in mice.