Archives

  • 2018-07
  • 2019-07
  • 2019-08
  • 2019-09
  • 2019-10
  • 2019-11
  • 2020-03
  • 2020-07
  • 2020-08
  • 2021-03
  • br A Karpathy A Khosla et

    2020-08-18


    A. Karpathy, A. Khosla, et al., Imagenet large scale visual recognition challenge, Int.
    [26] D.C. Brabham, Crowdsourcing as DAP5 model for problem solving: Leveraging the collective intelligence of online communities for public good, Doctoral dissertation The University of Utah, 2010. [27] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, Rethinking the inception architecture for computer vision, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 2818–2826. [28] S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Comput. 9 (1997) 1735–1780. [29] M. Macenko, M. Niethammer, J.S. Marron, D. Borland, J.T. Woosley, X. Guan, C. Schmitt, N.E. Thomas, A method for normalizing histology slides for quantitative analysis, in: IEEE International Symposium on Biomedical Imaging: From Nano To Macro, 2009, pp. 1107–1110.
    G. Irving, et al., Tensorflow: A system for large-scale machine learning, in: Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation, Savannah, GA, USA, 2016, pp. 265–283. [35] L.v.d. Maaten, G. Hinton, Visualizing data using t-SNE, J. Mach. Learn. Res. 9 (2008) 2579–2605. [36] M. Kohl, C. Walz, F. Ludwig, S. Braunewell, M. Baust, Assessment of breast cancer histology using densely connected convolutional networks, in: International Conference Image Analysis and Recognition, 2018, pp. 903–913. [37] Y. Wang, L. Sun, K. Ma, J. Fang, Breast cancer microscope image classification based on cnn with image deformation, in: International Conference Image Analysis and Recognition, 2018, pp. 845–852. [38] A. Golatkar, D. Anand, A. Sethi, Classification of breast cancer histology using deep learning, in: International Conference Image Analysis and Recognition, 2018, pp. 837–844. [39] H. Cao, S. Bernard, L. Heutte, R. Sabourin, Improve the performance of transfer learning without fine-tuning using dissimilarity-based multi-view learning for breast cancer histology images, in: International Conference Image Analysis and Recognition, 2018, pp. 779–787.
    [40] K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. [41] H. Ravishankar, P. Sudhakar, R. Venkataramani, S. Thiruvenkadam, P. Annangi, N. Babu, V. Vaidya, Understanding the mechanisms of deep transfer learning for medical images, in: International Workshop on Deep Learning in Medical Image Analysis, Cham, 2016, pp. 188–196.
    Contents lists available at ScienceDirect
    The Breast
    Original article
    Breast cancer imaging - A rapidly evolving discipline
    Fredrik Strand a, b, Sophia Zackrisson c, *
    a Breast Radiology, Karolinska University Hospital, 17176, Stockholm, Sweden
    b Department of Oncology-Pathology, Karolinska Institute, 17177, Stockholm, Sweden
    c Department of Translational Medicine, Diagnostic Radiology, Lund University, Skåne University Hospital Malmo,€ Malmo,€ 20502, Sweden
    Article history:
    Received in revised form
    Keywords:
    Breast cancer
    Screening
    Mammography
    Artificial intelligence
    Precise guidelines for MRI in preoperative mapping will be established
    Neoadjuvant therapy will be continuously guided by image-based functional biomarkers
    Along with improved treatment options, the importance of imaging in the metastatic setting will increase
    Medical disciplines will be more closely integrated for the full benefit of the patient
    Summary of predictions (Fig. 1)
    Image-based breast cancer screening will spread globally Awareness of mammography shortcomings will increase Tomosynthesis will become an established screening
    modality
    Mammographic breast compression will be optimized
    Contrast-enhancement will make mammography an alternative to MRI in limited settings
    The usefulness of automated ultrasound will be determined
    High-resolution diffusion and abbreviated protocols will enable MRI as a screening modality in certain subgroups
    Risk-stratification will be used to guide women to an adequate screening modality
    Artificial intelligence will potentially enhance many as-pects of breast imaging
    Radiomics - there will be a continued search for quanti-tative image features having observable biological correlates
    Minimally invasive image-guided procedures will replace open surgery for smaller lesions
    * Corresponding author.
    E-mail address: [email protected] (S. Zackrisson).
    The introduction of early detection of breast cancer through mammography screening was the most important preventive achievement to reduce breast cancer mortality. Today, breast im-aging is the patient's companion through the entire process of detection, diagnosis, prognosis, treatment choice and follow-up. Mammography is the core modality in breast imaging, com-plemented by ultrasound, magnetic resonance imaging (MRI) and, in certain settings, positron emission tomography (PET). In this preview article we share our personal perspective on possible future developments in the field.