Two-tier tissue decomposition for histopathological image representation and classification
IEEE Transactions on Medical Imaging
Institute of Electrical and Electronics Engineers
275 - 283
Item Usage Stats
In digital pathology, devising effective image representations is crucial to design robust automated diagnosis systems. To this end, many studies have proposed to develop object-based representations, instead of directly using image pixels, since a histopathological image may contain a considerable amount of noise typically at the pixel-level. These previous studies mostly employ color information to define their objects, which approximately represent histological tissue components in an image, and then use the spatial distribution of these objects for image representation and classification. Thus, object definition has a direct effect on the way of representing the image, which in turn affects classification accuracies. In this paper, our aim is to design a classification system for histopathological images. Towards this end, we present a new model for effective representation of these images that will be used by the classification system. The contributions of this model are twofold. First, it introduces a new two-tier tissue decomposition method for defining a set of multityped objects in an image. Different than the previous studies, these objects are defined combining texture, shape, and size information and they may correspond to individual histological tissue components as well as local tissue subregions of different characteristics. As its second contribution, it defines a new metric, which we call dominant blob scale, to characterize the shape and size of an object with a single scalar value. Our experiments on colon tissue images reveal that this new object definition and characterization provides distinguishing representation of normal and cancerous histopathological images, which is effective to obtain more accurate classification results compared to its counterparts.
Automated cancer diagnosis
Histopathological image representation
Tissue decomposition model
Classification (of information)
Automated cancer diagnosis
Diagnostic test accuracy study
Major clinical study
Published Version (Please cite this version)http://dx.doi.org/10.1109/TMI.2014.2354373
Showing items related by title, author, creator and subject.
TRIB2 confers resistance to anti-cancer therapy by activating the serine/threonine protein kinase AKT Hill, R.; Madureira, P. A.; Ferreira, B.; Baptista, I.; Machado, S.; Colaço, L.; Dos Santos, M.; Liu, N.; Dopazo, A.; Ugurel, S.; Adrienn, A.; Kiss-Toth, E.; Isbilen, M.; Gure, A. O.; Link, W. (Nature Publishing Group, 2017)Intrinsic and acquired resistance to chemotherapy is the fundamental reason for treatment failure for many cancer patients. The identification of molecular mechanisms involved in drug resistance or sensitization is imperative. ...
The miR-644a/CTBP1/p53 axis suppresses drug resistance by simultaneous inhibition of cell survival and epithelialmesenchymal transition in breast cancer Raza, U.; Saatci, O.; Uhlmann, S.; Ansari, S. A.; Eyüpoglu, E.; Yurdusev, E.; Mutlu, M.; Ersan, P. G.; Altundağ, M. K.; Zhang, J. D.; Dogan, H. T.; Güler, G.; Şahin, Ö. (Impact Journals LLC, 2016)Tumor cells develop drug resistance which leads to recurrence and distant metastasis. MicroRNAs are key regulators of tumor pathogenesis; however, little is known whether they can sensitize cells and block metastasis ...
Quantification of SLIT-ROBO transcripts in hepatocellular carcinoma reveals two groups of genes with coordinate expression Avci, M. E.; Konu, O.; Yagci, T. (BioMed Central, 2008)Background: SLIT-ROBO families of proteins mediate axon pathfinding and their expression is not solely confined to nervous system. Aberrant expression of SLIT-ROBO genes was repeatedly shown in a wide variety of cancers, ...