LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 8 of total 8

Search options

  1. Book ; Online: An Adaptive Locally Connected Neuron Model

    Tek, F. Boray

    Focusing Neuron

    2018  

    Abstract: This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other ... ...

    Abstract This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other tool than the backpropagation algorithm to learn its parameters which control the receptive field locations and apertures. This research explores whether this ability makes the neuron focus on informative inputs and yields any advantage over fully connected neurons. The experiments include tests of focusing neuron networks of one or two hidden layers on synthetic and well-known image recognition data sets. The results demonstrated that the focusing neurons can move their receptive fields towards more informative inputs. In the simple two-hidden layer networks, the focusing layers outperformed the dense layers in the classification of the 2D spatial data sets. Moreover, the focusing networks performed better than the dense networks even when 70$\%$ of the weights were pruned. The tests on convolutional networks revealed that using focusing layers instead of dense layers for the classification of convolutional features may work better in some data sets.

    Comment: 45 pages, a national patent filed, submitted to Turkish Patent Office, No: -2017/17601, Date: 09.11.2017
    Keywords Computer Science - Neural and Evolutionary Computing ; Computer Science - Machine Learning ; Statistics - Machine Learning
    Subject code 006 ; 612
    Publishing date 2018-08-31
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article: Mitosis detection using generic features and an ensemble of cascade adaboosts.

    Tek, F Boray

    Journal of pathology informatics

    2013  Volume 4, Page(s) 12

    Abstract: ... receiver operating characteristics curves of true positive versus false positive rates; calculated recall, precision, F-measure, and ... scored 68, 28.1, and 39.7 for the recall, precision, and F-measure measures, respectively. Mostly used ...

    Abstract Context: Mitosis count is one of the factors that pathologists use to assess the risk of metastasis and survival of the patients, which are affected by the breast cancer.
    Aims: We investigate an application of a set of generic features and an ensemble of cascade adaboosts to the automated mitosis detection. Calculation of the features rely minimally on object-level descriptions and thus require minimal segmentation.
    Materials and methods: The proposed work was developed and tested on International Conference on Pattern Recognition (ICPR) 2012 mitosis detection contest data.
    Statistical analysis used: We plotted receiver operating characteristics curves of true positive versus false positive rates; calculated recall, precision, F-measure, and region overlap ratio measures.
    Results: WE TESTED OUR FEATURES WITH TWO DIFFERENT CLASSIFIER CONFIGURATIONS: 1) An ensemble of single adaboosts, 2) an ensemble of cascade adaboosts. On the ICPR 2012 mitosis detection contest evaluation, the cascade ensemble scored 54, 62.7, and 58, whereas the non-cascade version scored 68, 28.1, and 39.7 for the recall, precision, and F-measure measures, respectively. Mostly used features in the adaboost classifier rules were a shape-based feature, which counted granularity and a color-based feature, which relied on Red, Green, and Blue channel statistics.
    Conclusions: The features, which express the granular structure and color variations, are found useful for mitosis detection. The ensemble of adaboosts performs better than the individual adaboost classifiers. Moreover, the ensemble of cascaded adaboosts was better than the ensemble of single adaboosts for mitosis detection.
    Language English
    Publishing date 2013-05-30
    Publishing country United States
    Document type Journal Article
    ZDB-ID 2579241-6
    ISSN 2153-3539 ; 2229-5089
    ISSN (online) 2153-3539
    ISSN 2229-5089
    DOI 10.4103/2153-3539.112697
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  3. Book ; Online: Adaptive Convolution Kernel for Artificial Neural Networks

    Tek, F. Boray / Çam, İlker / Karlı, Deniz

    2020  

    Abstract: Many deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3$\times$3) kernels. This paper describes a method for training the size of convolutional kernels to provide varying size kernels in a single layer. ...

    Abstract Many deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3$\times$3) kernels. This paper describes a method for training the size of convolutional kernels to provide varying size kernels in a single layer. The method utilizes a differentiable, and therefore backpropagation-trainable Gaussian envelope which can grow or shrink in a base grid. Our experiments compared the proposed adaptive layers to ordinary convolution layers in a simple two-layer network, a deeper residual network, and a U-Net architecture. The results in the popular image classification datasets such as MNIST, MNIST-CLUTTERED, CIFAR-10, Fashion, and ``Faces in the Wild'' showed that the adaptive kernels can provide statistically significant improvements on ordinary convolution kernels. A segmentation experiment in the Oxford-Pets dataset demonstrated that replacing a single ordinary convolution layer in a U-shaped network with a single 7$\times$7 adaptive layer can improve its learning performance and ability to generalize.

    Comment: 25 pages
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Neural and Evolutionary Computing
    Subject code 006
    Publishing date 2020-09-14
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Article ; Online: Mitosis detection using generic features and an ensemble of cascade adaboosts

    F Boray Tek

    Journal of Pathology Informatics, Vol 4, Iss 1, Pp 12-

    2013  Volume 12

    Abstract: ... receiver operating characteristics curves of true positive versus false positive rates; calculated recall, precision, F-measure, and ... scored 68, 28.1, and 39.7 for the recall, precision, and F-measure measures, respectively. Mostly used ...

    Abstract Context: Mitosis count is one of the factors that pathologists use to assess the risk of metastasis and survival of the patients, which are affected by the breast cancer. Aims: We investigate an application of a set of generic features and an ensemble of cascade adaboosts to the automated mitosis detection. Calculation of the features rely minimally on object-level descriptions and thus require minimal segmentation. Materials and Methods: The proposed work was developed and tested on International Conference on Pattern Recognition (ICPR) 2012 mitosis detection contest data. Statistical Analysis Used: We plotted receiver operating characteristics curves of true positive versus false positive rates; calculated recall, precision, F-measure, and region overlap ratio measures. Results: We tested our features with two different classifier configurations: 1) An ensemble of single adaboosts, 2) an ensemble of cascade adaboosts. On the ICPR 2012 mitosis detection contest evaluation, the cascade ensemble scored 54, 62.7, and 58, whereas the non-cascade version scored 68, 28.1, and 39.7 for the recall, precision, and F-measure measures, respectively. Mostly used features in the adaboost classifier rules were a shape-based feature, which counted granularity and a color-based feature, which relied on Red, Green, and Blue channel statistics. Conclusions: The features, which express the granular structure and color variations, are found useful for mitosis detection. The ensemble of adaboosts performs better than the individual adaboost classifiers. Moreover, the ensemble of cascaded adaboosts was better than the ensemble of single adaboosts for mitosis detection.
    Keywords Mitosis detection ; area granulometry ; cascade adaboost ; cost-sensitive learning ; ensemble classifier ; Computer applications to medicine. Medical informatics ; R858-859.7 ; Pathology ; RB1-214
    Language English
    Publishing date 2013-01-01T00:00:00Z
    Publisher Elsevier
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Article: Robust localization and identification of African clawed frogs in digital images

    Tek, F. Boray / Ä°zzet Kale / Flavio Cannavo / Giuseppe Nunnari

    Ecological informatics. 2014 Sept., v. 23

    2014  

    Abstract: We study the automatic localization and identification of African clawed frogs (Xenopus laevis sp.) in digital images taken in a laboratory environment. We propose a novel and stable frog body localization and skin pattern window extraction algorithm. We ...

    Abstract We study the automatic localization and identification of African clawed frogs (Xenopus laevis sp.) in digital images taken in a laboratory environment. We propose a novel and stable frog body localization and skin pattern window extraction algorithm. We show that it compensates scale and rotation changes very well. Moreover, it is able to localize and extract highly overlapping regions (pattern windows) even in the cases of intense affine transformations, blurring, Gaussian noise, and intensity transformations. The frog skin pattern (i.e. texture) provides a unique feature for the identification of individual frogs. We investigate the suitability of five different feature descriptors (Gabor filters, area granulometry, HoG,11Histogram of Oriented Gradients. dense SIFT,22Scale invariant feature transform. and raw pixel values) to represent frog skin patterns. We compare the robustness of the features based on their identification performance using a nearest neighbor classifier. Our experiments show that among five features that we tested, the best performing feature against rotation, scale, and blurring modifications was the raw pixel feature, whereas the SIFT feature was the best performing one against affine and intensity modifications.
    Keywords algorithms ; digital images ; frogs ; Xenopus laevis
    Language English
    Dates of publication 2014-09
    Size p. 3-12.
    Publishing place Elsevier B.V.
    Document type Article
    ZDB-ID 2212016-6
    ISSN 1878-0512 ; 1574-9541
    ISSN (online) 1878-0512
    ISSN 1574-9541
    DOI 10.1016/j.ecoinf.2013.09.005
    Database NAL-Catalogue (AGRICOLA)

    More links

    Kategorien

    In stock of ZB MED Bonn / Germany

    Z 7643: Show issues

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Article ; Online: Computer vision for microscopy diagnosis of malaria

    Dempster Andrew G / Tek F Boray / Kale Izzet

    Malaria Journal, Vol 8, Iss 1, p

    2009  Volume 153

    Abstract: Abstract This paper reviews computer vision and image analysis studies aiming at automated diagnosis or screening of malaria infection in microscope images of thin blood film smears. Existing works interpret the diagnosis problem differently or propose ... ...

    Abstract Abstract This paper reviews computer vision and image analysis studies aiming at automated diagnosis or screening of malaria infection in microscope images of thin blood film smears. Existing works interpret the diagnosis problem differently or propose partial solutions to the problem. A critique of these works is furnished. In addition, a general pattern recognition framework to perform diagnosis, which includes image acquisition, pre-processing, segmentation, and pattern classification components, is described. The open problems are addressed and a perspective of the future work for realization of automated microscopy diagnosis of malaria is provided.
    Keywords Arctic medicine. Tropical medicine ; RC955-962 ; Infectious and parasitic diseases ; RC109-216
    Language English
    Publishing date 2009-07-01T00:00:00Z
    Publisher BMC
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  7. Article ; Online: Computer vision for microscopy diagnosis of malaria.

    Tek, F Boray / Dempster, Andrew G / Kale, Izzet

    Malaria journal

    2009  Volume 8, Page(s) 153

    Abstract: This paper reviews computer vision and image analysis studies aiming at automated diagnosis or screening of malaria infection in microscope images of thin blood film smears. Existing works interpret the diagnosis problem differently or propose partial ... ...

    Abstract This paper reviews computer vision and image analysis studies aiming at automated diagnosis or screening of malaria infection in microscope images of thin blood film smears. Existing works interpret the diagnosis problem differently or propose partial solutions to the problem. A critique of these works is furnished. In addition, a general pattern recognition framework to perform diagnosis, which includes image acquisition, pre-processing, segmentation, and pattern classification components, is described. The open problems are addressed and a perspective of the future work for realization of automated microscopy diagnosis of malaria is provided.
    MeSH term(s) Algorithms ; Animals ; Diagnosis, Computer-Assisted/instrumentation ; Diagnosis, Computer-Assisted/methods ; Humans ; Image Processing, Computer-Assisted/methods ; Malaria/classification ; Malaria/diagnosis ; Microscopy ; Pattern Recognition, Automated/methods ; Vision, Ocular
    Language English
    Publishing date 2009-07-13
    Publishing country England
    Document type Journal Article ; Review
    ISSN 1475-2875
    ISSN (online) 1475-2875
    DOI 10.1186/1475-2875-8-153
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  8. Article ; Online: Assessment of algorithms for mitosis detection in breast cancer histopathology images.

    Veta, Mitko / van Diest, Paul J / Willems, Stefan M / Wang, Haibo / Madabhushi, Anant / Cruz-Roa, Angel / Gonzalez, Fabio / Larsen, Anders B L / Vestergaard, Jacob S / Dahl, Anders B / Cireşan, Dan C / Schmidhuber, Jürgen / Giusti, Alessandro / Gambardella, Luca M / Tek, F Boray / Walter, Thomas / Wang, Ching-Wei / Kondo, Satoshi / Matuszewski, Bogdan J /
    Precioso, Frederic / Snell, Violet / Kittler, Josef / de Campos, Teofilo E / Khan, Adnan M / Rajpoot, Nasir M / Arkoumani, Evdokia / Lacle, Miangela M / Viergever, Max A / Pluim, Josien P W

    Medical image analysis

    2015  Volume 20, Issue 1, Page(s) 237–248

    Abstract: The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. However, mitosis counting is ... ...

    Abstract The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. However, mitosis counting is laborious, subjective and may suffer from low inter-observer agreement. With the wider acceptance of whole slide images in pathology labs, automatic image analysis has been proposed as a potential solution for these issues. In this paper, the results from the Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described. The challenge was based on a data set consisting of 12 training and 11 testing subjects, with more than one thousand annotated mitotic figures by multiple observers. Short descriptions and results from the evaluation of eleven methods are presented. The top performing method has an error rate that is comparable to the inter-observer agreement among pathologists.
    MeSH term(s) Algorithms ; Breast Neoplasms/pathology ; Female ; Humans ; Mitosis ; Observer Variation
    Language English
    Publishing date 2015-02
    Publishing country Netherlands
    Document type Comparative Study ; Journal Article ; Research Support, Non-U.S. Gov't
    ZDB-ID 1356436-5
    ISSN 1361-8423 ; 1361-8431 ; 1361-8415
    ISSN (online) 1361-8423 ; 1361-8431
    ISSN 1361-8415
    DOI 10.1016/j.media.2014.11.010
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 5206: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (2.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

To top