Ahmed A. Othman

EFIS—Evolving Fuzzy Image Segmentation

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.

Evolving fuzzy image segmentation

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.

Segmentation of Breast Ultrasound Images Using Neural Networks

Medical image segmentation is considered a very important task for diagnostic and treatment-planning purposes. Accurate segmentation of medical images helps clinicians to clarify the type of the disease and facilitates the process of efficient treatment. In this paper, we propose two different approaches to segment breast ultrasound images using neural networks. In the first approach, we use scale invariant feature transform (SIFT) to calculate a set of descriptors for a set of points inside the image. These descriptors are used to train a supervised neural network. In the second approach, we use SIFT to detect a set of key points inside the image. Texture features are then extracted from a region around each point to train the network. This process is repeated multiple times to verify the generalization ability of the network. The average segmentation accuracy is calculated by comparing every segmented image with corresponding gold standard images marked by an expert.

Image classification using evolving fuzzy inference systems

Evolving fuzzy systems change by online updating of their parameters and structure; the number of fuzzy rules changes as long as there is new data. In literature, an evolving fuzzy system is mainly considered to be an unsupervised approach that builds and updates its clusters online as long as new data is available. In our previous works, we introduced a new supervised evolving fuzzy approach for segmenting medical images. In this paper, we demonstrate that this supervised evolving fuzzy approach can classify images. As an example we attempt to classify medical images based on their modalities. A set of features extracted from the image is used to train the fuzzy system with the modality class of the image as the fuzzy output. The proposed algorithm is applied to both ultrasound scans and magnetic reasoning images (MRI). The proposed algorithm is compared with the support vector machines (SVMs) and the K-nearest neighbour algorithm (KNN). The results show that evolving fuzzy systems can compete with well-establish clustering algorithms (and even surpass them) by delivering high classification rates.

N-cuts parameter adjustment using evolving fuzzy inferencing

Normalized cut (N-cut) is a rather recent approach to image segmentation representing the image as a graph and using eigenvalues to partition it. However, this method has several parameters that affect the segmentation accuracy. Using pre-set values for these parameters may generate good results for some images and bad results for others. Thus, to achieve maximum segmentation accuracy, these parameters may be manually finetuned for every set of images. This process, of course, would be impractical and lack generality. In this paper, a method is proposed to automatically determine N-cut parameters for every single image based on the image features using evolving fuzzy sets. The proposed method is applied to magnetic reasoning images (MRI) of bladder.

Neural image thresholding with SIFT-Controlled gabor features

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 thresholding using neural network

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.

Neural Image Thresholding Using SIFT: A Comparative Study

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.

Self-Configuring and Evolving Fuzzy Image Thresholding

Every segmentation algorithm has parameters that need to be adjusted in order to achieve good results. Evolving fuzzy systems for adjustment of segmentation parameters have been proposed recently (Evolving fuzzy image segmentation -- EFIS [1]). However, similar to any other algorithm, EFIS too suffers from a few limitations when used in practice. As a major drawback, EFIS depends on detection of the object of interest for feature calculation, a task that is highly application-dependent. In this paper, a new version of EFIS is proposed to overcome these limitations. The new EFIS, called self-configuring EFIS (SC-EFIS), uses available training data to auto-configure the parameters that are fixed in EFIS. As well, the proposed SCEFIS relies on a feature selection process that does not require the detection of a region of interest (ROI).

Medical image thresholding using online trained neural networks

Medical images are used mainly in the diagnosing process and as an aid in determining correct treatment. Therefore, the process of segmenting different regions of interests (ROIs) within the medical images is considered a critical one. When provided with a segment with high segmentation accuracy, the physician can easily detect the problem and determine the best treatment. In this paper, a neural network retrained on-line is proposed to automatically segment medical images using a global threshold. The network is initially trained off-line using a set of features extracted from a set of randomly selected training images, along with their best thresholds, as targets for the neural network. The features are extracted using Seeded Up Robust Feature (SURF) technique from a rectangle around the ROI. This network continues training on-line as new images arrive, based on a feedback correction done by the clinician to the segmented image. This process is repeated multiple times to verify the generalization ability of the network.