Mutlu Mete

A structural approach for finding functional modules from large biological networks

BackgroundBiological systems can be modeled as complex network systems with many interactions between the components. These interactions give rise to the function and behavior of that system. For example, the protein-protein interaction network is the physical basis of multiple cellular functions. One goal of emerging systems biology is to analyze very large complex biological networks such as protein-protein interaction networks, metabolic networks, and regulatory networks to identify functional modules and assign functions to certain components of the system. Network modules do not occur by chance, so identification of modules is likely to capture the biologically meaningful interactions in large-scale PPI data. Unfortunately, existing computer-based clustering methods developed to find those modules are either not so accurate or too slow.ResultsWe devised a new methodology called SCAN (Structural Clustering Algorithm for Networks) that can efficiently find clusters or functional modules in complex biological networks as well as hubs and outliers. More specifically, we demonstrated that we can find functional modules in complex networks and classify nodes into various roles based on their structures. In this study, we showed the effectiveness of our methodology using the budding yeast (Saccharomyces cerevisiae) protein-protein interaction network. To validate our clustering results, we compared our clusters with the known functions of each protein. Our predicted functional modules achieved very high purity comparing with state-of-the-art approaches. Additionally the theoretical and empirical analysis demonstrated a linear running-time of the algorithm, which is the fastest approach for networks.ConclusionWe compare our algorithm with well-known modularity based clustering algorithm CNM. We successfully detect functional groups that are annotated with putative GO terms. Top-10 clusters with minimum p-value theoretically prove that newly proposed algorithm partitions network more accurately then CNM. Furthermore, manual interpretations of functional groups found by SCAN show superior performance over CNM.

Automatic delineation of malignancy in histopathological head and neck slides

BackgroundHistopathology, which is one of the most important routines of all laboratory procedures used in pathology, is decisive for the diagnosis of cancer. Experienced histopathologists review the histological slides acquired from biopsy specimen in order to outline malignant areas. Recently, improvements in imaging technologies in terms of histological image analysis led to the discovery of virtual histological slides. In this technique, a computerized microscope scans a glass slide and generates virtual slides at a resolution of 0.25 μm/pixel. As the recognition of intrinsic cancer areas is time consuming and error prone, in this study we develop a novel method to tackle automatic squamous cell carcinoma of the head and neck detection problem in high-resolution, wholly-scanned histopathological slides.ResultsA density-based clustering algorithm improved for this study plays a key role in the determination of the corrupted cell nuclei. Using the Support Vector Machines (SVMs) Classifier, experimental results on seven head and neck slides show that the proposed algorithm performs well, obtaining an average of 96% classification accuracy.ConclusionRecent advances in imaging technology enable us to investigate cancer tissue at cellular level. In this study we focus on wholly-scanned histopathological slides of head and neck tissues. In the context of computer-aided diagnosis, delineation of malignant regions is achieved using a powerful classification algorithm, which heavily depends on the features extracted by aid of a newly proposed cell nuclei clustering technique. The preliminary experimental results demonstrate a high accuracy of the proposed method.

Lesion detection in demoscopy images with novel density-based and active contour approaches

BackgroundDermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Automated assessment tools for dermoscopy images have become an important field of research mainly because of inter- and intra-observer variations in human interpretation. One of the most important steps in dermoscopy image analysis is the detection of lesion borders, since many other features, such as asymmetry, border irregularity, and abrupt border cutoff, rely on the boundary of the lesion.ResultsTo automate the process of delineating the lesions, we employed Active Contour Model (ACM) and boundary-driven density-based clustering (BD-DBSCAN) algorithms on 50 dermoscopy images, which also have ground truths to be used for quantitative comparison. We have observed that ACM and BD-DBSCAN have the same border error of 6.6% on all images. To address noisy images, BD-DBSCAN can perform better delineation than ACM. However, when used with optimum parameters, ACM outperforms BD-DBSCAN, since ACM has a higher recall ratio.ConclusionWe successfully proposed two new frameworks to delineate suspicious lesions with i) an ACM integrated approach with sharpening and ii) a fast boundary-driven density-based clustering technique. ACM shrinks a curve toward the boundary of the lesion. To guide the evolution, the model employs the exact solution [27] of a specific form of the Geometric Heat Partial Differential Equation [28]. To make ACM advance through noisy images, an improvement of the model’s boundary condition is under consideration. BD-DBSCAN improves regular density-based algorithm to select query points intelligently.

An improved border detection in dermoscopy images for density based clustering

BackgroundDermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. In current practice, dermatologists determine lesion area by manually drawing lesion borders. Therefore, automated assessment tools for dermoscopy images have become an important research field mainly because of inter- and intra-observer variations in human interpretation. One of the most important steps in dermoscopy image analysis is automated detection of lesion borders. To our knowledge, in our 2010 study we achieved one of the highest accuracy rates in the automated lesion border detection field by using modified density based clustering algorithm. In the previous study, we proposed a novel method which removes redundant computations in well-known spatial density based clustering algorithm, DBSCAN; thus, in turn it speeds up clustering process considerably.FindingsOur previous study was heavily dependent on the pre-processing step which creates a binary image from original image. In this study, we embed a new distance measure to the existing algorithm. This provides twofold benefits. First, since new approach removes pre-processing step, it directly works on color images instead of binary ones. Thus, very important color information is not lost. Second, accuracy of delineated lesion borders is improved on 75% of 100 dermoscopy image dataset.ConclusionPrevious and improved methods are tested within the same dermoscopy dataset along with the same set of dermatologist drawn ground truth images. Results revealed that the improved method directly works on color images without any pre-processing and generates more accurate results than existing method.

A Divisive Hierarchical Structural Clustering Algorithm for Networks

Many systems in sciences, engineering and nature can be modeled as networks. Examples are internet, metabolic networks and social networks. Network clustering algorithms aimed to find hidden structures from networks are important to make sense of complex networked data. In this paper we present a new clustering method for networks. The proposed algorithm can find hierarchical structure of clusters without requiring any input parameters. The experiments using real data demonstrate an outstanding performance of the new method.

Dermoscopic diagnosis of melanoma in a 4D space constructed by active contour extracted features

Dermoscopy, also known as epiluminescence microscopy, is a major imaging technique used in the assessment of melanoma and other diseases of skin. In this study we propose a computer aided method and tools for fast and automated diagnosis of malignant skin lesions using non-linear classifiers. The method consists of three main stages: (1) skin lesion features extraction from images; (2) features measurement and digitization; and (3) skin lesion binary diagnosis (classification), using the extracted features. A shrinking active contour (S-ACES) extracts color regions boundaries, the number of colors, and lesions boundary, which is used to calculate the abrupt boundary. Quantification methods for measurements of asymmetry and abrupt endings in skin lesions are elaborated to approach the second stage of the method. The total dermoscopy score (TDS) formula of the ABCD rule is modeled as linear support vector machines (SVM). Further a polynomial SVM classifier is developed. To validate the proposed framework a dataset of 64 lesion images were selected from a collection with a ground truth. The lesions were classified as benign or malignant by the TDS based model and the SVM polynomial classifier. Comparing the results, we showed that the latter model has a better f-measure then the TDS-based model (linear classifier) in the classification of skin lesions into two groups, malignant and benign.

Analysis of density based and fuzzy c-means clustering methods on lesion border extraction in dermoscopy images

BackgroundComputer-aided segmentation and border detection in dermoscopic images is one of the core components of diagnostic procedures and therapeutic interventions for skin cancer. Automated assessment tools for dermoscopy images have become an important research field mainly because of inter- and intra-observer variations in human interpretation. In this study, we compare two approaches for automatic border detection in dermoscopy images: density based clustering (DBSCAN) and Fuzzy C-Means (FCM) clustering algorithms. In the first approach, if there exists enough density –greater than certain number of points- around a point, then either a new cluster is formed around the point or an existing cluster grows by including the point and its neighbors. In the second approach FCM clustering is used. This approach has the ability to assign one data point into more than one cluster.ResultsEach approach is examined on a set of 100 dermoscopy images whose manually drawn borders by a dermatologist are used as the ground truth. Error rates; false positives and false negatives along with true positives and true negatives are quantified by comparing results with manually determined borders from a dermatologist. The assessments obtained from both methods are quantitatively analyzed over three accuracy measures: border error, precision, and recall.ConclusionAs well as low border error, high precision and recall, visual outcome showed that the DBSCAN effectively delineated targeted lesion, and has bright future; however, the FCM had poor performance especially in border error metric.

Automatic boundary detection and symmetry calculation in dermoscopy images of skin lesions

This paper develops an approach and tool that automatically extracts skin lesions boundary used for symmetry and area calculation. An image enhancement approach prepares every image for active contour (AC) evolution. Further, the AC automatically extracts the lesions boundary used to measure symmetry applying minimal boundary box. Next, the lesions area is calculated. Thus, the lesions are mapped as points onto area - symmetry 2D space to determine the distribution of the lesions with cancer. To validate the theoretical concepts experiments were performed with 51 skin lesion images. A statistics measures the accuracy of boundary extraction with respect to a ground truth. The advantages, disadvantages and the contribution of this study are reported at the end of the paper.

Automatic identification of angiogenesis in double stained images of liver tissue

BackgroundTo grow beyond certain size and reach oxygen and other essential nutrients, solid tumors trigger angiogenesis (neovascularization) by secreting various growth factors. Based on this fact, several researches proposed that density of newly formed vessels correlate with tumor malignancy. Vessel density is known as a true prognostic indicator for several types of cancer. However, automated quantification of angiogenesis is still in its primitive stage, and deserves more intelligent methods by taking advantages accruing from novel computer algorithms.ResultsThe newly introduced characteristics of subimages performed well in identification of region-of-angiogenesis. The proposed technique was tested on 522 samples collected from two high-resolution tissues. Having 0.90 overall f-measure, the results obtained with Support Vector Machines show significant agreement between automated framework and manual assessment of microvessels.ConclusionThis study introduces a new framework to identify angiogenesis to measure microvessel density (MVD) in digitalized images of liver cancer tissues. The objective is to recognize all subimages having new vessel formations. In addition to region based characteristics, a set of morphological features are proposed to differentiate positive and negative incidences.

Statistical comparison of color model-classifier pairs in hematoxylin and eosin stained histological images

Color is the most critical information for assessing histological images. However, in literature, there is no standard color space in which a particular color points are represented for computer vision tasks. In this paper, we evaluated 11 color models with three different learning schemas for their performance in classifying tumor-related colors. The color models we studied are CIELAB, CIELUV, CIEXYZ, CMY, CMYK, HSL, HSV, Hunter-LAB, NRGB, RGB, and SCT. With 11 color models, prediction accuracies of three well-known classifiers, namely SVMs, C4.5, and Naïve Bayes, are statistically compared on a large dataset of 3494 Hematoxylin and Eosin (HE) stained histopathologic images. Surprisingly, experiment results show that in contrast to general assumptions, there is no single model that is better than others in every case. However, C4.5 outperformed other two classifiers by obtaining average F-measure of 0.9989. Of 11 color models, we suggest the pair of C4.5-SCT as the most accurate classification framework for tumor identification in HE stained histological images.