Breast Cancer Identification via Thermography Image Segmentation with a Gradient Vector Flow and a Convolutional Neural Network

Journal of Healthcare Engineering - Tập 2019 - Trang 1-13 - 2019
Santiago Tello-Mijares1,2, Fomuy Woo3, Franklin César Flores2
1Instituto Tecnológico Superior de Lerdo, Postgraduate Department, Lerdo 35150, Mexico
2Instituto Tecnológico de la Laguna, Postgraduate Department, Torreón 27000, Mexico
3Instituto de Seguridad y Servicios Sociales de los Trabajadores del Estado, Medical Familiar Unit, Torreón 27268, Mexico

Tóm tắt

Breast cancer is the most common cancer among women worldwide with about half a million cases reported each year. Mammary thermography can offer early diagnosis at low cost if adequate thermographic images of the breasts are taken. The identification of breast cancer in an automated way can accelerate many tasks and applications of pathology. This can help complement diagnosis. The aim of this work is to develop a system that automatically captures thermographic images of breast and classifies them as normal and abnormal (without cancer and with cancer). This paper focuses on a segmentation method based on a combination of the curvature function k and the gradient vector flow, and for classification, we proposed a convolutional neural network (CNN) using the segmented breast. The aim of this paper is to compare CNN results with other classification techniques. Thus, every breast is characterized by its shape, colour, and texture, as well as left or right breast. These data were used for training as well as to compare the performance of CNN with three classification techniques: tree random forest (TRF), multilayer perceptron (MLP), and Bayes network (BN). CNN presents better results than TRF, MLP, and BN.

Từ khóa


Tài liệu tham khảo

10.1109/tla.2018.8444159

10.1016/j.infrared.2018.08.007

10.1016/j.eswa.2014.04.027

10.1016/j.ijthermalsci.2013.03.001

10.1016/j.sigpro.2012.06.002

10.1155/2013/264246

10.1016/j.infrared.2015.06.012

2017, An overview of medical infrared imaging in breast abnormalities detection, 45

2017, Registration of contralateral breasts thermograms by shape context technique, 59

2017, An overview of medical infrared imaging in breast abnormalities detection, 69

10.1166/jmihi.2014.1226

10.18178/joig.3.1.47-51

10.1016/j.ijleo.2015.08.007

10.1016/j.infrared.2015.09.008

10.1007/s10916-008-9213-1

2014, EXCLI Journal, 13, 241

10.1007/s11517-018-1876-2

10.1016/j.ins.2007.03.027

10.1016/j.patcog.2008.08.007

10.1260/2040-2295.1.1.27

10.1016/j.infrared.2014.08.019

2014, EXCLI Journal, 13, 1204

10.1016/j.ijsu.2014.10.010

10.1016/j.patcog.2015.09.009

10.1016/j.bbe.2017.10.005

10.1155/2018/1214301

10.1155/2018/4168538

10.1155/2016/1841945

10.1155/2017/8314740

10.1155/2019/2912458

10.1155/2016/5689346

10.1007/bf00133570

10.1109/83.661186

10.1109/proc.1979.11328

10.1155/2015/586928

10.1155/2014/536308

10.1023/a:1010933404324

10.1109/5.726791

2019

10.1109/42.363096

Thông tin
Thông tin xuất bản

Journal of Healthcare Engineering

Tập 2019

1-13

Thông tin tác giả