Cancer causes deviations in the distribution of cells, leading to changes in biological structures that they form. Correct localization and characterization of these structures are crucial for accurate cancer diagnosis and grading. In this paper, we introduce an effective hybrid model that employs both structural and statistical pattern recognition techniques to locate and characterize the biological structures in a tissue image for tissue quantification. To this end, this hybrid model defines an attributed graph for a tissue image and a set of query graphs as a reference to the normal biological structure. It then locates key regions that are most similar to a normal biological structure by searching the query graphs over the entire tissue graph. Unlike conventional approaches, this hybrid model quantifies the located key regions with two different types of features extracted using structural and statistical techniques. The first type includes embedding of graph edit distances to the query graphs whereas the second one comprises textural features of the key regions. Working with colon tissue images, our experiments demonstrate that the proposed hybrid model leads to higher classification accuracies, compared against the conventional approaches that use only statistical techniques for tissue quantification.

In recent years, there has been a great effort in the research of implementing automated diagnostic systems for tissue images. One major challenge in this implementation is to design systems that are robust to image variations. In order to meet this challenge, it is important to learn the systems on a large number of labeled images from a different range of variation. However, acquiring labeled images is quite difficult in this domain, and hence, the labeled training data are typically very limited. Although the issue of having limited labeled data is acknowledged by many researchers, it has rarely been considered in the system design. This paper successfully addresses this issue, introducing a new resampling framework to simulate variations in tissue images. This framework generates multiple sequences from an image for its representation and models them using a Markov process. Working with colon tissue images, our experiments show that this framework increases the generalization capacity of a learner by increasing the size and variation of the training data and improves the classification performance of a given image by combining the decisions obtained on its sequences.

In this study, we propose a novel method for a travel path inference problem from sparse GPS trajectory data. This problem involves localization of GPS samples on a road network and reconstruction of the path that a driver might have been following from a low rate of sampled GPS observations. Particularly, we model travel path inference as an optimization problem in both the spatial and temporal domains and propose a novel hybrid hidden Markov model (HMM) that uses a uniform cost search (UCS)-like novel combinational algorithm. We provide the following improvements over the previous studies that use HMM-based methods: (1) for travel path inference between matched GPS positions, the proposed hybrid HMM algorithm evaluates all candidate paths to find the most likely path for both the temporal and spatial domains. In contrast, previous studies either create interpolated trajectories or connect matched GPS positions using the shortest path assumption, which might not be true, especially in urban road networks (Goh et al. 2012;Lou et al. 2009). (2) The proposed algorithm uses legal speed limits for the evaluation of discrepancy in the temporal domain as in Goh et al. (2012), andLou et al. (2009) only if there is not sufficient historical average speed data; otherwise, we use historical average speed computed from data. Our experiments with real datasets show that our algorithm performs better than the state of the art VTrack algorithm (Thiagarajan et al. 2009), especially for cases where GPS data is sampled infrequently.

En yaygın kanser türlerinden biri olan kolon kanserinin tedavisi erken tanı ile mümkün olabilmektedir. Günümüzde kanser tanısında kolonoskopi, sigmoidoskopi ve stool testi gibi görüntüleme yöntemleri kullanılmakta ise de, en yaygın kullanılan ve geçerli yöntem, dokulardan biyopsi işlemi ile doku kesitlerinin alınması ve bu kesitlerin mikroskop altında incelenmesidir. Ancak bu inceleme, görsel yorumlamaya dayalı oldugundan dolayı, patologlar arasındaöznel kararların verilmesine neden olabilmekte ve tanı farklılıklarına yol açabilmektedir. Patologlar arasındaki kararlardaki degişkenligi azaltma ihtiyacı, bilgisayar yardımı ile biyopsi görüntülerï uzerindeöznitelik çıkarımı ve nesnel kararlar verilmesini saglayacak algoritmaların geliştirilmesi için çalışmalara yol açmıştır. Bu bildiride, biyopsi görüntü gösterimi içinögreticisiz olarak belirlenen görüntü bölgelerinin birlikteligini modelleyen histogramların tanımlanması ve bunlarüzerinde çıkarılacaköznitelikler ile kolon doku görüntülerinin otomatik sınıflandırılması için bir yöntemönerilmiştir. Literatürde kelime histogramı (bag-of-words) modeli olarak da bilinen bu yöntem ile, kolon doku görüntüleriüzerinde yaptıgımız deneysel çalışmalar,önerilen bu yöntemin benzer yöntemlerle karşılaştırıldıgında daha başarılı sonuçlar verdigini göstermiştir. Bununla beraber,öznitelik tanımlamasında piksel renk yogunluk degerlerini kullanan yöntemimizin, farklıözniteliklerin beraber kullanılmasıyla daha iyi sonuçlar verme potansiyeli de bulunmaktadır. ABSTRACTColon cancer, which is one of the most common cancer type, could be cured with its early diagnosis. In the current practice of medicine, there are many screening techniques such as colonoscopy, sigmoidoscopy, and stool test, however the most effective and most widely used method for cancer diagnosis is to take tissue sections with biopsy and examine them under a microscope. As this examination is based on visual interpretation, it may lead to subjective decisions and diagnostic differences among pathologists. The need of reducing inter-variability in cancer diagnosis has led to studies for extraction of features from biopsy images and development of algorithms that give objective results. In this paper, we propose a method for the automated classification of a colon tissue image with the features extracted from a histogram that models the existence of image regions determined in an unsupervised way. Experiments on colon tissue images show that the proposed method leads to more successful results compared to its counterparts. Moreover, the proposed method, which uses color intensities for feature extraction, has the potential of giving better results with the use of additional features.