Archives

  • 2019-10
  • 2019-11
  • 2020-03
  • 2020-07
  • 2020-08
  • 2021-03
  • Rottlerin br J Kremer K Steenstrup Pedersen C Igel Active

    2020-08-18


    [18] J. Kremer, K. Steenstrup Pedersen, C. Igel, Active Learning With Support Vec-tor Machines, 4, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2014, pp. 313–326.
    [21] H. Samet, Foundations of Multidimensional and Metric Data Structures, Else-vier, Amsterdam, 2006.
    [22] R.O. Stehling, M.A. Nascimento, A.X. Falcão, A compact and e cient image re-trieval approach based on border/interior pixel classification, in: Intl. Conf. on Information and Knowledge Management, 2002, pp. 102–109.
    [24] M.S. Nixon, A.S. Aguado, Feature Extraction & Image Processing for Computer Vision, Academic Press, 2012.
    [30] S.C.H. Hoi, M.R. Lyu, A semi-supervised active learning framework for image retrieval, in: IEEE Computer Society Conference on Computer Vision and Pat-tern Recognition, 2, 2005, pp. 302–309.
    [31] L. Wang, K.L. Chan, Z. Zhang, Bootstrapping svm active learning by incorporat-ing unlabelled images for image retrieval, in: IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 1, 2003. I–I
    [32] R. Baeza-Yates, B. Ribeiro-Neto, Modern Information Retrieval: The Concepts and Technology Behind Search, 2nd, Addison-Wesley Publishing Company, USA, 2011.
    Rafael S. Bressan received his B.Sc. degree in Information Systems (2005) from the State University of the North of Parana (UENP), Brazil. In 2018, he Rottlerin received his M.Sc. in Computer Science from the Federal University of Technol-ogy - Parana, Brazil. Currently, he has been a Professor at the Department of Computing, University of Northern Parana (UNOPAR), Brazil. His research interests include image analysis, machine learning and pattern recognition.
    Pedro H. Bugatti received a B.Sc. degree in computer science (2005) from the Euripides Soares da Rocha Uni-versity of Marília, Brazil. In 2008, he received his M.Sc. in Computer Science from the University of São Paulo (ICMC-USP), Brazil. In 2012, he received his Ph.D. in Com-puter Science from the University of São Paulo (ICMC-USP), Brazil. Currently, he has been a Professor at the De-partment of Computing, Federal University of Technology
    - Parana (UTFPR), Brazil. His research interests include image analysis, machine learning, pattern recognition and content-based image retrieval.
    Priscila T.M. Saito received a B.Sc. degree in computer science (2007) from the Euripides Soares da Rocha Uni-versity of Marília, Brazil. In 2010, she received her M.Sc. in Computer Science from the University of São Paulo (ICMC-USP), Brazil. In 2014, she received her Ph.D. in Computer Science from the University of Campinas (IC-UNICAMP), Brazil. Currently, she has been a Professor at the Department of Computing, Federal University of Tech-nology - Parana (UTFPR), Brazil. She is also a member of the PLOS ONE Editorial Board, acting as an academic editor. Her research interests include image analysis, ma-chine learning and pattern recognition.
    Available online at www.sciencedirect.com
    ScienceDirect
    journal homepage: www.elsevier.com/locate/bbe
    1 2 3 Original Research Article
    4 Breast cancer diagnosis using abnormalities on
    5 ipsilateral views of digital mammograms
    6 Q1 Suhas Sapate a,*, Sanjay Talbar a, Abhishek Mahajan b, Nilesh Sable b, 7 Subhash Desai b, Meenakshi Thakur b
    8 a SGGS Institute of Engineering & Technology, Nanded, Maharashtra 431606, India 9 b Department of Radiodiagnosis, Tata Memorial Centre, Parel, Mumbai, Maharashtra, India
    Article history:
    Received in revised form
    Available online xxx
    Keywords:
    Breast cancer
    Digital mammograms
    Ipsilateral views
    Radiomic features
    Image-based sensitivity
    Case-based sensitivity
    Ipsilateral views of digital mammograms help radiologists to localize and confirm abnormal lesions during diagnosis of breast cancers. This study aims at developing algorithms which improve accuracy of computer-aided diagnosis (CADx) for analyzing breast abnormalities on ipsilateral views. The proposed system is community simplification a fusion of single and two view systems. Single view approach detects and characterizes suspicious lesions on craniocaudal (CC) and medio-lateral oblique (MLO) view separately using geometric and textural features. Lesions detected on each view are paired with potential lesions on another view. The proposed algorithm computes the correspondence score of each lesion pair. Single view information is fused with two views correspondence score to discriminate malignant tumours from benign masses using the SVM classifier. Performance of SVM classifier is assessed using five-fold cross validation (CV), Kappa metric and ROC analysis. Algorithms are applied to 110 pairs of mammograms from local dataset and 74 pairs from open dataset. Single view scheme yielded image-based sensitivity of 91.63% and 88.17% at 1.35 and 1.51 false positives per image (FPs/I) on local and open dataset respectively. Single view classification yielded FPs/I of 1.03 and 1.20 with sensitivity of 70%. Fusion based two views scheme using SVM classifier produced average case-based sensitivity of 75.91% at 0.69 FPs/I and 73.65% at 0.72 FPs/I on local and open dataset respectively. Fusion of single view features with two view corre-spondence score leads to improved case-based detection sensitivity. Proposed fusion based approach results into accurate and reliable diagnosis of breast abnormalities than single view approach.