Search

Context.— Pathologists may encounter extraneous pieces of tissue (tissue floaters) on glass slides because of specimen cross-contamination. Troubleshooting this problem, including performing molecular tests for tissue identification if available, is time consuming and often does not satisfactorily resolve the problem. Objective.— To demonstrate the feasibility of using an image search tool to resolve the tissue floater conundrum. Design.— A glass slide was produced containing 2 separate hematoxylin and eosin (H&E)-stained tissue floaters. This fabricated slide was digitized along with the 2 slides containing the original tumors used to create these floaters. These slides were then embedded into a dataset of 2325 whole slide images comprising a wide variety of H&E stained diagnostic entities. Digital slides were broken up into patches and the patch features converted into barcodes for indexing and easy retrieval. A deep learning-based image search tool was employed to extract features from patches via barcodes, hence enabling image matching to each tissue floater. Results.— There was a very high likelihood of finding a correct tumor match for the queried tissue floater when searching the digital database. Search results repeatedly yielded a correct match within the top 3 retrieved images. The retrieval accuracy improved when greater proportions of the floater were selected. The time to run a search was completed within several milliseconds. Conclusions.— Using an image search tool offers pathologists an additional method to rapidly resolve the tissue floater conundrum, especially for those laboratories that have transitioned to going fully digital for primary diagnosis.

Recent advances in medical imaging have created many possibilities for the exploitation of both microscopic images in digital form and the whole slide images (WSIs) for multiple tasks such as classification, prediction, and retrieval. This is mainly due to annotated datasets available through various research organizations. Magnification level is an important factor as pathologist views the biopsy samples at various magnifications to reach a diagnosis. Whereas WSIs generally do contain the magnification information, microscopic snapshots are often captured without attaching the magnification information. In this paper, we introduce a new dataset, Kimia-5MAG, consisting of 33,345 patches at 5 different magnification classes created from WSIs made publicly available by The Cancer Genome Atlas (TCGA). There exists a large number of microscopic snapshots captured from camera-mounted microscopes but are of little use for automatic processing due to lack of magnification information. One direction to make use of these datasets is learning the magnification level from high resolutions captured WSIs and transferring the knowledge to microscopic snapshots. We investigate combinations of several deep networks and classifiers to predict different magnification levels. The proposed framework achieves 93% classification accuracy. We also analyze the effect of rotation on magnification prediction.

Recent advances in digital imaging has transformed computer vision and machine learning to new tools for analyzing pathology images. This trend could automate some of the tasks in the diagnostic pathology and elevate the pathologist workload. The final step of any cancer diagnosis procedure is performed by the expert pathologist. These experts use microscopes with high level of optical magnification to observe minute characteristics of the tissue acquired through biopsy and fixed on glass slides. Switching between different magnifications, and finding the magnification level at which they identify the presence or absence of malignant tissues is important. As the majority of pathologists still use light microscopy, compared to digital scanners, in many instance a mounted camera on the microscope is used to capture snapshots from significant field-of-views. Repositories of such snapshots usually do not contain the magnification information. In this paper, we extract deep features of the images available on TCGA dataset with known magnification to train a classifier for magnification recognition. We compared the results with LBP, a well-known handcrafted feature extraction method. The proposed approach achieved a mean accuracy of 96% when a multi-layer perceptron was trained as a classifier., Comment: 4 pages, 3 figures, 1 table

The level set approach to segmentation of medical images has received considerable attention in recent years. Evolving an initial contour to converge to anatomical boundaries of an organ or tumor is a very appealing method, especially when it is based on a well-defined mathematical foundation. However, one drawback of such evolving method is its high computation time. It is desirable to design and implement algorithms that are not only accurate and robust but also fast in execution. Bresson et al. have proposed a variational model using both boundary and region information as well as shape priors. The latter can be a significant factor in medical image analysis. In this work, we combine the variational model of level set with a multi-resolution approach to accelerate the processing. The question is whether a multi-resolution context can make the segmentation faster without affecting the accuracy. As well, we investigate the question whether a premature convergence, which happens in a much shorter time, would reduce accuracy. We examine multiple semiautomated configurations to segment the prostate gland in T2W MR images. Comprehensive experimentation is conducted using a data set of a 100 patients (1,235 images) to verify the effectiveness of the multi-resolution level set with shape priors. The results show that the convergence speed can be increased by a factor of ≈ 2.5 without affecting the segmentation accuracy. Furthermore, a premature convergence approach drastically increases the segmentation speed by a factor of ≈ 17.9.

Despite the large number of techniques proposed in recent years, accurate segmentation of digital images remains a challenging task for automated computer algorithms. Approaches based on machine learning hold particular promise in this regard, because in many applications, e.g., medical image analysis, frequent user intervention can be assumed to correct the results, thereby generating valuable feedback for algorithmic learning. In order to learn segmentation of new (unseen) images, such user feedback (correction of current or past results) seems indispensable. In this paper, we propose the formation and evolution of fuzzy rules for user-oriented environments in which feedback is captured by design. The evolving fuzzy image segmentation (EFIS) can be used to adjust the parameters of existing segmentation methods, switch between their results, or fuse their results. Specifically, we propose a single-parametric EFIS (SEFIS), apply its rule evolution to breast ultrasound images, and evaluate the results using three segmentation methods, namely, global thresholding, region growing, and statistical region merging. The results show increased accuracy across all tests and for all methods. For instance, the accuracy of statistical region merging can be improved from 59% ± 30% to 71% ± 22%. We also propose a multiparametric EFIS (MEFIS) for switching between or fusing the results of multiple segmentation methods. Preliminary results indicate that MEFIS can further increase overall segmentation accuracy. Three thresholding methods with accuracies of 62% ± 11%, 64% ± 16%, and 61% ± 9% were combined to reach an overall accuracy of 66% ± 15%. Finally, we compare our SEFIS scheme with five other thresholding methods to evaluate its overall performance.

In recent years, with the explosion of digital images on the Web, content-based retrieval has emerged as a significant research area. Shapes, textures, edges and segments may play a key role in describing the content of an image. Radon and Gabor transforms are both powerful techniques that have been widely studied to extract shape-texture-based information. The combined Radon-Gabor features may be more robust against scale/rotation variations, presence of noise, and illumination changes. The objective of this paper is to harness the potentials of both Gabor and Radon transforms in order to introduce expressive binary features, called barcodes, for image annotation/tagging tasks. We propose two different techniques: Gabor-of-Radon-Image Barcodes (GRIBCs), and Guided-Radon-of-Gabor Barcodes (GRGBCs). For validation, we employ the IRMA x-ray dataset with 193 classes, containing 12,677 training images and 1,733 test images. A total error score as low as 322 and 330 were achieved for GRGBCs and GRIBCs, respectively. This corresponds to $\approx 81\%$ retrieval accuracy for the first hit., Comment: To appear in proceedings of the 23rd International Conference on Pattern Recognition (ICPR 2016), Cancun, Mexico, December 2016

Medical images can be a valuable resource for reliable information to support medical diagnosis. However, the large volume of medical images makes it challenging to retrieve relevant information given a particular scenario. To solve this challenge, content-based image retrieval (CBIR) attempts to characterize images (or image regions) with invariant content information in order to facilitate image search. This work presents a feature extraction technique for medical images using stacked autoencoders, which encode images to binary vectors. The technique is applied to the IRMA dataset, a collection of 14,410 x-ray images in order to demonstrate the ability of autoencoders to retrieve similar x-rays given test queries. Using IRMA dataset as a benchmark, it was found that stacked autoencoders gave excellent results with a retrieval error of 376 for 1,733 test images with a compression of 74.61%.

Content-based medical image retrieval can support diagnostic decisions by clinical experts. Examining similar images may provide clues to the expert to remove uncertainties in his/her final diagnosis. Beyond conventional feature descriptors, binary features in different ways have been recently proposed to encode the image content. A recent proposal is “Radon barcodes” that employ binarized Radon projections to tag/annotate medical images with content-based binary vectors, called barcodes. In this paper, MinMax Radon barcodes are introduced which are superior to “local thresholding” scheme suggested in the literature. Using IRMA dataset with 14,410 x-ray images from 193 different classes, the advantage of using MinMax Radon barcodes over thresholded Radon barcodes are demonstrated. The retrieval error for direct search drops by more than 15%. As well, SURF, as a well-established non-binary approach, and BRISK, as a recent binary method are examined to compare their results with MinMax Radon barcodes when retrieving images from IRMA dataset. The results demonstrate that MinMax Radon barcodes are faster and more accurate when applied on IRMA images.

Knowledge- and sample-based learning approaches play a pivotal role in image processing. However, the acquisition and integration of expert knowledge (for the former) and providing a sufficiently large number of training samples (for the latter) are generally hard to perform and time-consuming tasks. Hence, learning image processing tasks from a few gold/ground-truth samples, prepared by the user, is highly desirable. This paper demonstrates how the combination of an optimizer (e.g., genetic algorithm) and image processing tools (e.g., parameterized morphology operations) can be used to generate image processing procedures for image filtering and object extraction. For this purpose, the approach receives the original and the user-prepared image (filtered image or image with extracted target object) as a gold sample which reflects the user's expectations. After carrying out the training or optimization phase, the optimal procedure is generated and ready to be applied to new images. The feasibility of our approach is investigated for two individual image processing categories, namely filtering and object extraction, by well-prepared synthetic images. The proposed architecture and the employed methodologies are explained in detail. Experimental results are provided as well.The subject matter in this work is covered by a US provisional patent application.

The principal contribution of this work is to design a general framework for an intelligent system to extract one object of interest from ultrasound images. This system is based on reinforcement learning. The input image is divided into several sub-images, and the proposed system finds the appropriate local values for each of them so that it can extract the object of interest. The agent uses some images and their ground-truth (manually segmented) version to learn from. A reward function is employed to measure the similarities between the output and the manually segmented images, and to provide feedback to the agent. The information obtained can be used as valuable knowledge stored in the Q-matrix. The agent can then use this knowledge for new input images. The experimental results for prostate segmentation in trans-rectal ultrasound images show high potential of this approach in the field of ultrasound image segmentation.

Finding an optimal threshold in order to segment digital images is a difficult task in image processing. Numerous approaches to image thresholding already exist in the literature. In this work, a reinforced threshold fusion for image binarization is introduced which aggregates existing thresholding techniques. The reinforcement agent learns the optimal weights for different thresholds and segments the image globally. A fuzzy reward function is employed to measure object similarities between the binarized image and the original gray-level image, and provide feedback to the agent. The experiments show that promising improvement can be obtained. Three well-established thresholding techniques are combined by the reinforcement agent and the results are compared using error measurements based on ground-truth images.

Good results on image classification and retrieval using support vector machines (SVM) with local binary patterns (LBPs) as features have been extensively reported in the literature where an entire image is retrieved or classified. In contrast, in medical imaging, not all parts of the image may be equally significant or relevant to the image retrieval application at hand. For instance, in lung x-ray image, the lung region may contain a tumour, hence being highly significant whereas the surrounding area does not contain significant information from medical diagnosis perspective. In this paper, we propose to detect salient regions of images during training and fold the data to reduce the effect of irrelevant regions. As a result, smaller image areas will be used for LBP features calculation and consequently classification by SVM. We use IRMA 2009 dataset with 14,410 x-ray images to verify the performance of the proposed approach. The results demonstrate the benefits of saliency-based folding approach that delivers comparable classification accuracies with state-of-the-art but exhibits lower computational cost and storage requirements, factors highly important for big data analytics., To appear in proceedings of The 14th International Conference on Machine Learning and Applications (IEEE ICMLA 2015), Miami, Florida, USA, 2015

Accurate and fast segmentation and volume estimation of the prostate gland in magnetic resonance (MR) images are necessary steps in the diagnosis, treatment, and monitoring of prostate cancer. This paper presents an algorithm for the prostate gland volume estimation based on the semi-automated segmentation of individual slices in T2-weighted MR image sequences. The proposed sequential registration-based segmentation (SRS) algorithm, which was inspired by the clinical workflow during medical image contouring, relies on inter-slice image registration and user interaction/correction to segment the prostate gland without the use of an anatomical atlas. It automatically generates contours for each slice using a registration algorithm, provided that the user edits and approves the marking in some previous slices. We conducted comprehensive experiments to measure the performance of the proposed algorithm using three registration methods (i.e., rigid, affine, and nonrigid). Five radiation oncologists participated in the study where they contoured the prostate MR (T2-weighted) images of 15 patients both manually and using the SRS algorithm. Compared to the manual segmentation, on average, the SRS algorithm reduced the contouring time by 62 % (a speedup factor of 2.64×) while maintaining the segmentation accuracy at the same level as the intra-user agreement level (i.e., Dice similarity coefficient of 91 versus 90 %). The proposed algorithm exploits the inter-slice similarity of volumetric MR image series to achieve highly accurate results while significantly reducing the contouring time.

Traditional image enhancement algorithms do not account for the subjective evaluation of human operators. Every observer has a different opinion of an ideally enhanced image. Automated Techniques for obtaining a subjectively ideal image enhancement are desirable, but currently do not exist. In this paper, we demonstrate that Reinforcement Learning is a potential method for solving this problem. We have developed an agent that uses the Q-learning algorithm. The agent modifies the contrast of an image with a simple linear point transformation based on the histogram of the image and feedback it receives from human observers. The results of several testing sessions have indicated that the agent performs well within a limited number of iterations.

Image thresholding is a necessary task in some image processing applications. However, due to disturbing factors, e.g. non-uniform illumination, or inherent image vagueness, the result of image thresholding is not always satisfactory. In recent years, various researchers have introduced new thresholding techniques based on fuzzy set theory to overcome this problem. Regarding images as fuzzy sets (or subsets), different fuzzy thresholding techniques have been developed to remove the grayness ambiguity/vagueness during the task of threshold selection. In this paper, a new thresholding technique is introduced which processes thresholds as type II fuzzy sets. A new measure of ultrafuzziness is also introduced and experimental results using laser cladding images are provided.

Detecting objects, a significant task in computer vision, is accompanied with many challenges. When we focus on medical images, the challenges of detecting an organ or a tumour exhibit their own specific difficulties. Automatic finding of the prostate gland in magnetic resonance (MR) images, for instance, is a needed task in some clinical procedures. In this paper we propose a novel method for detection of the prostate gland in MR images. We use a multi-stage intra-patient approach to the template matching which is based on a trained dataset. We conduct experiments with the images of 100 patients and report preliminary results that seem to be promising. 2013 IEEE. Scopus

Image thresholding is a very important phase in the image analysis process. In all traditional segmentation schemes, statically calculated thresholds or initial points are used to binarize images. Because of the differences in images characteristics, these techniques may generate high segmentation accuracy for some images and low accuracy for other images. Intelligent segmentation by “dynamic” determination of thresholds based on image properties may be a more robust solution. In this paper, we use the Gabor filter to generate features from regions of interest (ROIs) detected by the the SIFT technique (Scale-Invariant Feature Transform). These features are used to train a neural network for the task of image thresholding. The average of segmentation accuracies for a set of test images is calculated by comparing every segmented image with its gold standard image marked by human experts.

Image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label are connected and meaningful, and share certain visual characteristics. Pixels in a region are similar with respect to some features or property, such as color, intensity, or texture. Adjacent regions may be significantly different with respect to the same characteristics. Therefore, it is difficult for a static (non-learning) segmentation technique to accurately segment different images with different characteristics. In this paper, an evolving fuzzy system is used to segment medical images. The system uses some training images to build an initial fuzzy system which then evolves online as new images are encountered. Each new image is segmented using the evolved fuzzy system and may contribute to updating the system. This process provides better segmentation results for new images compared to static paradigms. The average of segmentation accuracy for test images is calculated by comparing every segmented image with its gold standard image prepared manually by an expert.

Image thresholding is a very important phase in the image analysis process. However, different images have different characteristics making the traditional process of thresholding by one algorithm a very challenging task. That is because any thresholding method may be perform well for some images but for sure it will not be suitable for all images. In this paper, intelligent thresholding by training a neural network is proposed. The neural network is trained using a set of features extracted from medical images randomly selected form a sample set and then tested using the remaining medical images. This process is repeated multiple times to verify the generalization ability of the network. The average of segmentation accuracy is calculated by comparing every segmented image with its gold standard image.

In many image processing applications, image thresholding is considered to be an important task. Opposition-Based Learning (OBL) was recently introduced and used to enhance different computation algorithms. In this paper, a new thresholding algorithm is proposed by utilizing the concept of opposite fuzzy sets. The algorithm is applied on general set of images and compared with the previous opposition-based thresholding algorithm [1] and a commonly used thresholding method, namely the Otsu method. The most reliable results on the test data are achieved using the proposed algorithm.

In this paper, a new neural-fuzzy approach is proposed for automated region segmentation in transrectal ultrasound images of the prostate. The goal of region segmentation is to identify suspicious regions in the prostate in order to provide decision support for the diagnosis of prostate cancer. The new automated region segmentation system uses expert knowledge as well as both textural and spatial features in the image to accomplish the segmentation. The textural information is extracted by two recurrent random pulsed neural networks trained by two sets of data (a suspicious tissues’ data set and a normal tissues’ data set). Spatial information is captured by the atlas-based reference approach and is represented as fuzzy membership functions. The textural and spatial features are synthesized by a fuzzy inference system, which provides a binary classification of the region to be evaluated.

Image thresholding (as the simplest form of segmentation) is a very challenging task because of the differences in the characteristics of different images such that different thresholds may be tried to obtain maximum segmentation accuracy. In this paper, a supervised neural network is used to "dynamically" threshold images by assigning a suitable threshold to each image. The network is trained using a set of simple features extracted from medical images randomly selected form a sample set and then tested using the remaining medical images. The results are compared with the Otsu algorithm and the active shape models (ASM) approach.

The task of image thresholding mainly classifies the image data into two regions, a necessary step in many image analysis and recognition applications. Different images, however, possess different characteristics making the thresholding by one single algorithm very difficult if not impossible. Hence, to optimally binarize a single image, one must usually try more than one threshold in order to obtain maximum segmentation accuracy. This approach could be very complex and time-consuming especially when a large number of images should be segmented in real time. Generally the challenge arises because any thresholding method may perform well for a certain image class but not for all images. In this paper, a supervised neural network is used to “dynamically” threshold images by learning the suitable threshold for each image type. The thresholds generated by the neural network can be used to binarize the images in two different ways. In the first approach, the scale-invariant feature transform (SIFT) method is used to assign a number of key points to the whole image. In the second approach,the SIFT is used to assign a number of key points within a rectangle around the region of interest. The results of each test are compared with the Otsu algorithm, active shape models (ASM), and level sets technique (LS). The neural network is trained using a set of features extracted from medical images randomly selected form a sample set and then tested using the remaining images. This process is repeated multiple times to verify the generalization ability of the network. The average of segmentation accuracy is calculated by comparing every segmented image with corresponding gold standard images.

λ-enhancement, introduced by Tizhoosh et al., is a contrast adjustment technique that uses involutive fuzzy complements to find the best gray-level transformation in order to increase the image contrast. Applied on medical images, λ-enhancement can provide good results with respect to visually perceived improvement of object-background discrimination. In this work, we provide two extensions of λ-enhancement. First we extend it to employ interval-valued fuzzy sets (special case of type II fuzzy sets), and second, we provide an adaptive version of both regular (type I) and interval-value (type II) fuzzy λ-enhancement. Using breast ultrasound images, we demonstrate the enhancement effect and compare them with the well-established CLAHE method (contrast-limited adaptive histogram equalization).

In many vision-based applications we need to segment an object of interest in digital images. For methods which rely on a learning process, the lack of sufficient number of training samples is usually an obstacle, especially when the samples need to be manually prepared by an expert. In addition, none of the existing methods uses online feedback from the user in order to evaluate the generated results and continuously improve them. Considering these factors, a new algorithm based on reinforcement learning is discussed in this chapter. The approach starts with a limited number of training samples and improves its performance in the course of time.

Image thresholding is a challenging task in image processing field. Many efforts have already been made to propose universal, robust methods to handle a wide range of images. Previously by the same authors, an optimization-based thresholding approach was introduced. According to the proposed approach, differential evolution (DE) algorithm, minimizes dissimilarity between the input grey-level image and the bi-level (thresholded) image. In the current paper, micro opposition-based differential evolution (micro-ODE), DE with very small population size and opposition-based population initialization, has been proposed. Then, it is compared with a well-known thresholding method, Kittler algorithm and also with its non-opposition-based version (micro-DE). In overall, the proposed approach outperforms Kittler method over 16 challenging test images. Furthermore, the results confirm that the micro-ODE is faster than micro-DE because of embedding the opposition-based population initialization.

Ultrasound images have low level of contrast and are corrupted with speckle noise. Due to these effects, segmentation of ultrasound images is very challenging. Because of their adaptive characteristics, active Contours or Snakes are a commonly used method for segmentation of this type of images. Even with this adaptive method which is made for this type of environment other challenges come across. With abundance of noise in ultrasound images, snakes cannot converge to the objectpsilas outline in some cases. As a result, the detected boundary will not be accurate enough. Therefore, some pre-processing methods are usually necessary. In this paper, contrast adjustment techniques and fusion of different filters have been implemented to help the snake algorithm converge. As a result, the boundaries of object of interest in this case prostate cancer will be identified. Then the accuracy is measured and compared with ground-truth images prepared by experts.

Background Among different medical image modalities, ultrasound imaging has a very widespread clinical use. But, due to some factors, such as poor image contrast, noise and missing or diffuse boundaries, the ultrasound images are inherently difficult to segment. An important application is estimation of the location and volume of the prostate in transrectal ultrasound (TRUS) images. For this purpose, manual segmentation is a tedious and time consuming procedure. Methods We introduce a new method for the segmentation of the prostate in transrectal ultrasound images, using a reinforcement learning scheme. This algorithm is used to find the appropriate local values for sub-images and to extract the prostate. It contains an offline stage, where the reinforcement learning agent uses some images and manually segmented versions of these images to learn from. The reinforcement agent is provided with reward/punishment, determined objectively to explore/exploit the solution space. After this stage, the agent has acquired knowledge stored in the Q-matrix. The agent can then use this knowledge for new input images to extract a coarse version of the prostate. Results We have carried out experiments to segment TRUS images. The results demonstrate the potential of this approach in the field of medical image segmentation. Conclusion By using the proposed method, we can find the appropriate local values and segment the prostate. This approach can be used for segmentation tasks containing one object of interest. To improve this prototype, more investigations are needed.

Type II fuzzy sets are high-level representation of vague data with, compared to ordinary fuzzy sets, greater capability for uncertainty management. Theoretical aspects of type II fuzzy systems have been extensively investigated, and the research is still ongoing. Many image processing tasks accompanied with different types of imperfection. In this chapter, the applications of type II fuzzy sets for image segmentation will be discussed. Global and spatial type II segmentation schemes will be systematically introduced and examples will be provided.

In this paper a method for image segmentation using an opposition-based reinforcement learning scheme is introduced. We use this agent-based approach to optimally find the appropriate local values and segment the object. The agent uses an image and its manually segmented version and takes some actions to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal as reward/punishment. The agent uses this information to explore/exploit the solution space. The values obtained can be used as valuable knowledge to fill the Q-matrix. The results demonstrate potential for applying this new method in the field of medical image segmentation

This paper presents window memoization, a performance optimization technique for convolution-based image processing algorithms. Window memoization exploits the repetitive nature of image data to reduce the number of calculations required for image processing algorithms and hence, it improves the performance. We applied window memoization to a chain of image processing algorithms that includes median filter, Kirsch edge detector and local edge filling. We found that a large portion of the calculations performed on pixel neighborhoods can be skipped and instead, previously calculated results can be reused. The typical speedups were in the range of 1.6times to 2.8times.

A new robust image thresholding technique is introduced in this paper. Comprehensive experiments show that a single thresholding method can not be successful for all kind of images. The proposed approach uses fusion of some well-known thresholding methods by applying weighted voting at the decision level. The main objective is improving robustness of thresholding approach by participating several methods. Although, the proposed approach can not guaranty the best result for all kind of images but it shows higher performance and consistent/smoother behavior in overall. The performance of the new approach and nine well-established thresholding methods are compared by applying to an image set with high image diversity. The comparison results show that the proposed approach outperforms other nine well-established thresholding approaches. The proposed approach has been explained in details and experimental results are provided.

This paper presents an active contour model to accurately detect pupil boundary in order to improve the performance of iris recognition systems. The contour model takes into consideration that an actual pupil boundary is a near-circular contour rather than a perfect circle. Two types of controlling force models, introduced as internal and external forces, are designed to properly activate the contour and locate it over the pupil boundary. The internal forces are designed to smooth the curve as well as to keep it close to a circular shape by pushing the contour vertices to their local radial mean. The external forces, which are responsible for pulling the contour vertices toward the pupil boundary, are designed based on a circular-curve gradient measurement with a proper angular range with respect to the contour center. In addition, an iterative algorithm has been developed in order to capture limbus and eyelids. The developed algorithm iteratively searches the limbus and eyelids boundaries and excludes the detected eyelids areas that cover the iris. Excluding the eyelids leads to a more precise search for limbus in the next iteration and the search is completed when the circular parameters of the limbus converge to fixed values. The eyelid contours are modeled as elliptic curves considering the spherical shape of an eyeball and the search is based on the expected contour in different degrees of eye openness.

In this paper a new approach to object extraction and recognition based on reinforcement learning is presented. We use this novel idea as a method to optimally segment the image and increase the recognition rate. The success rate is compared with a classical approach. Preliminary results demonstrate increase in recognition rate.

This paper is an investigation of the application of ant colony optimization to image thresholding. It presents an approach where ants are assigned to each pixel of an image and they move around the image seeking low grayscale regions. The proposed ant-based method performs better than three other established thresholding algorithms. Further work must be conducted to optimize parameters, select the best cost function, improve the analysis of the pheromone data and reduce computation time. The study indicates that an ant-based approach has the potential of becoming an established image thresholding technique.

This study is an investigation of the application of ant colony optimization to image thresholding. This paper presents an approach where one ant is assigned to each pixel of an image and then moves around the image seeking low grayscale regions. Experimental results demonstrate that the proposed ant-based method performs better than other two established thresholding algorithms. Further work must be conducted to optimize the algorithm parameters, improve the analysis of the pheromone data and reduce computation time. However, the study indicates that an ant-based approach has the potential of becoming an established image thresholding technique.

This paper introduces a new method to medical image segmentation using a reinforcement learning scheme. We use this novel idea as an effective way to optimally find the appropriate local thresholding and structuring element values and segment the prostate in ultrasound images. Reinforcement learning agent uses an ultrasound image and its manually segmented version and takes some actions (i.e., different thresholding and structuring element values) to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal determined objectively. The agent uses these objective reward/punishment to explore/exploit the solution space. The values obtained using this way can be used as valuable knowledge to fill a Q-matrix. The reinforcement learning agent can use this knowledge for similar ultrasound images as well. The results demonstrate high potential for applying reinforcement learning in the field of medical image segmentation.

This paper deals with the design of a semi-automated noise filtering approach, which receives just original noisy image and corresponding gold (user manipulated) image to learn filtering task. It tries to generate an optimized mathematical morphology procedure for image filtering by applying a genetic algorithm as an optimizer. After training and generating a morphological procedure, the approach is ready to apply the learned procedure on new noisy images. The main advantage of this approach is that it takes just one gold sample to learn filtering and does not need any prior context knowledge. Using the morphological operators makes the filtering procedure robust, effective, and computationally efficient. Furthermore, the proposed filter shows little distortion on the noise free parts of an image and it can extract objects from heavily noisy environments. Architecture of the system and details of implementation are presented. The approach feasibility is tested by well-prepared synthetic noisy images and results are given and discussed.

Background In this paper a novel method for prostate segmentation in transrectal ultrasound images is presented. Methods A segmentation procedure consisting of four main stages is proposed. In the first stage, a locally adaptive contrast enhancement method is used to generate a well-contrasted image. In the second stage, this enhanced image is thresholded to extract an area containing the prostate (or large portions of it). Morphological operators are then applied to obtain a point inside of this area. Afterwards, a Kalman estimator is employed to distinguish the boundary from irrelevant parts (usually caused by shadow) and generate a coarsely segmented version of the prostate. In the third stage, dilation and erosion operators are applied to extract outer and inner boundaries from the coarsely estimated version. Consequently, fuzzy membership functions describing regional and gray-level information are employed to selectively enhance the contrast within the prostate region. In the last stage, the prostate boundary is extracted using strong edges obtained from selectively enhanced image and information from the vicinity of the coarse estimation. Results A total average similarity of 98.76%(± 0.68) with gold standards was achieved. Conclusion The proposed approach represents a robust and accurate approach to prostate segmentation.

In this paper a novel method for automatic prostate segmentation in transrectal ultrasound images is presented. Morphological grey level transformations are first used to generate an image with enough bright intensity around the prostate. This image is then thresholded to produce a binary image. Then by finding and using a point as the inside point for the prostate, a Kalman estimator is used to isolate the prostate boundary from any irrelevant parts and produce a roughly segmented version (as coarse estimation). Consequently, a fuzzy inference system describing regional and gray level information is employed to enhance the contrast of the prostate with respect to the background. Using strong edges obtained from this enhanced image and information from pixels gradients and also the characteristics in the vicinity of the coarse estimation, the final boundary is extracted. A number of experiments are conducted to validate this method.

This paper introduces a reinforcement-learning concept to find the optimal threshold for digital images. The proposed approach can integrate human expert knowledge in an objective or subjective way to overcome the shortcomings of existing methods.

Image quality evaluation by human observers is heavily subjective in nature. Individual observers judge the image quality differently. In previous works, an observer-dependent system for subjective image enhancement, which is based on fusion of different algorithms, was introduced. In this paper, the system configuration for sharpness/smoothness is discussed and experimental results are provided.

In many image processing applications the image quality should be improved to support the human perception. The image quality evaluation by the human observers is, however, heavily subjective in the nature. Different observers judge the image quality differently. In many cases the relevant part of image information which is perceived by the observer should reach a maximum. In this work we present a new approach to image enhancement which is based on fusion of different algorithms. We use fuzzy measure theory to represent the human subjectivity, and fuzzy integrals to aggregate this subjectivity with objective criteria. We also apply the Dempster aggregation rule to define a degree of compromise. Finally, we use a fuzzy rule-based approach to construct an aggregation matrix that allow us to generate enhanced images for each individual observer. As an example, we apply this approach to increase the quality of portal images that are used in radiation therapy.

In many image-processing applications the image quality should be improved to support the human perception. Image quality evaluation by human observers is, however, heavily subjective in nature. Individual observers judge the image quality differently. In many cases, the quality of the relevant part of image information, which is perceived by the observer, should reach a maximum. In previous works, an overall system for subjective image enhancement, which is based on fusion of different algorithms, was introduced. In this paper, more details of the overall-system structure are provided. Furthermore, the test results for contrast and sharpness/smoothness as interesting image qualities are also presented.

The contrast improvement of the digital images is an important task in image processing and machine vision. The gray-level modification is one of the most popular methods to perform image enhancement because it is simple in implementation and fast in computing. Since the selection of a suitable mathematical function for the gray-level transformation depends on the specific grayness properties of the image, it is necessary to develop some techniques for automatic selection of an appropriate function. In this work, we introduce a new algorithm for contrast adaptation (/spl lambda/-enhancement) which is based on involutive fuzzy complements and measures of fuzziness. Regarding to the amount of grayness ambiguity the proposed technique detects the suitable form of the gray-level modification in the set of involutive membership function generated by parameter /spl lambda/.

Medical images in radiation therapy, especially electronic portal images, are often very poor in quality because of imaging physics. For a reliable patient set-up verification by tracking of relevant features, better in-treatment images are necessary. In this work, we present the prototype of an additive fuzzy system for a locally adaptive image enhancement and a modified associative memory for image restoration. Using a-priori knowledge and the advantages of this hybrid neural-fuzzy system, a much better quality for the in-treatment image can be achieved.

The megavoltage electronic portal imaging is a very important task for cancer treatment in radiation therapy. The megavoltage images (MVIs), however, are very poor in quality because of imaging physics. For a reliable patient set-up verification we need better in-treatment images to track relevant features. In recent years, some researchers have applied the concept of fuzzy set theory to develop new image enhancement algorithms. In this work we investigate three existing fuzzy approaches to enhancement of MVIs. We develop also a simple fuzzy rule based approach to image enhancement. Further, we demonstrate the results of the locally adaptive implementation of these methods. Finally, a comparison of the performance of the investigated algorithms is given by the use of some measures of fuzziness. Some general notes on these methods is also given.

The electronic portal imaging device has become an important tool for the clinician to verify the shape and the location of the therapy beam with respect to the patient's anatomy. Normally, a visual comparison of the real patient position related to the beam with the planned treatment field is performed. This treatment field is defined during diagnostics and treatment planning. For this purpose, a treatment simulation takes place as a result of which a simulator image (SI) is captured. Because of the imaging physics the unprocessed electronic portal images (EPIs) are very poor in quality compared with the SI that is usually an X-ray image from CT. The conventional EPI allows only a rough verification of patient position relative to bony structures. The state of the art conventional enhancement techniques can be applied to EPIs to give some improvement for further visual analysis after the treatment (off-line). This paper presents an approach that combines an associative restoration algorithm with a fuzzy image enhancement technique to reach a new quality. The main idea of the associative restoration is the merger of the EPI with the SI to generate a much better in-treatment image than obtained by simple enhancement and to allow a more reliable feature matching. Firstly, the images are enhanced by the fuzzy image enhancement as a result of which the visibility of structures like bones is improved. This is important also for the following alignment of corresponding structures in the images. A specially structured artificial neural network that we call modified associative memory is trained by the enhanced SI.

Image enhancement is one of the fundamental tasks in image processing. Fuzzy techniques offer a suitable framework for the development of new methods because they are nonlinear and knowledge-based. In this work, we give an overview of existing fuzzy image enhancement techniques, where contrast adaptation methods and filtering techniques are considered.