Detection of Architectural Distortion with Deep Convolutional Neural Network and Data Augmentation of Limited Dataset

Nenhuma Miniatura disponível
Citações na Scopus
Tipo de produção
conferenceObject
Data de publicação
2019
DOI
Web of Science
Título da Revista
ISSN da Revista
Título do Volume
Editora
SPRINGER
Autores
COSTA, Arthur C.
OLIVEIRA, Helder C. R.
MELO, Carlos F. E.
VIEIRA, Marcelo A. C.
Citação
XXVI BRAZILIAN CONGRESS ON BIOMEDICAL ENGINEERING, CBEB 2018, VOL. 2, v.70, n.2, p.155-159, 2019
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
Early detection of breast cancer can increase treatment efficiency. One of the earliest signs of breast cancer is the Architectural Distortion (AD), which is a subtle contraction of the breast tissue, most of the time unnoticeable. A lot of techniques have been proposed over the years to aid the detection of AD in digital mammography but only a few using a deep learning approach. One of the most successful algorithms of deep neural architecture are the Convolutional Neural Networks (CNNs). However, to assure better CNN performance, the training step requires a large volume of data. This paper presents a deep CNN architecture designed for the automatic detection of AD in digital mammography images. For the training step, we considered the data augmentation approach, to overcome the limitation of clinical dataset. CNN performance was evaluated in terms of Receiver Operating Characteristic (ROC). The measured area under the ROC curve (AUC) was 0:87 for the proposed CNN in the task of AD detection in digital mammography.
Palavras-chave
Architectural distortion, Breast cancer, Digital mammography, Deep learning, Convolutional neural network
URI
https://observatorio.fm.usp.br/handle/OPI/34853
Referências
  1. Bahl M, 2015, AM J ROENTGENOL, V205, P1339, DOI 10.2214/AJR.15.14628
  2. Chatfield K, 2014, RETURN DEVIL DETAILS
  3. Elmore JG, 2003, JNCI-J NATL CANCER I, V95, P1384, DOI 10.1093/jnci/djg048
  4. Gaur S, 2013, AM J ROENTGENOL, V201, pW662, DOI 10.2214/AJR.12.10153
  5. Geron A, 2017, HANDS ON MACHINE LEA
  6. Glynn CG, 2011, RADIOLOGY, V260, P664, DOI 10.1148/radiol.11110159
  7. Greenspan H, 2016, IEEE T MED IMAGING, V35, P1153, DOI 10.1109/TMI.2016.2553401
  8. Heath M, 2001, IWDM 2000: 5TH INTERNATIONAL WORKSHOP ON DIGITAL MAMMOGRAPHY, P212
  9. Karellas A, 2008, MED PHYS, V35, P4878, DOI 10.1118/1.2986144
  10. LeCun Y, 2015, NATURE, V521, P436, DOI 10.1038/nature14539
  11. Maidment ADA, 2003, SEMIN ROENTGENOL, V38, P216, DOI 10.1016/S0037-198X(03)00048-8
  12. Nishikawa RA, 2007, COMPUT MED IMAG GRAP, V31, P224, DOI 10.1016/j.compmedimag.2007.02.009
  13. Rangayyan RM, 2010, J DIGIT IMAGING, V23, P611, DOI 10.1007/s10278-009-9257-x
  14. Veronesi U, 2005, LANCET, V365, P1727, DOI 10.1016/S0140-6736(05)66546-4

Coleções
Comunicações em Eventos - FM/MDR
Comunicações em Eventos - HC/InRad
Comunicações em Eventos - LIM/44