MRFE-CNN: multi-route feature extraction model for breast tumor segmentation in Mammograms using a convolutional neural network

被引:43
作者
Ranjbarzadeh, Ramin [1 ]
Sarshar, Nazanin Tataei [2 ]
Ghoushchi, Saeid Jafarzadeh [3 ]
Esfahani, Mohammad Saleh [4 ]
Parhizkar, Mahboub [5 ]
Pourasad, Yaghoub [6 ]
Anari, Shokofeh [7 ]
Bendechache, Malika [8 ]
机构
[1] Univ Guilan, Fac Engn, Dept Telecommun Engn, Rasht, Iran
[2] Islamic Azad Univ, Dept Engn, Tehran North Branch, Tehran, Iran
[3] Urmia Univ Technol, Fac Ind Engn, Orumiyeh, Iran
[4] Islamic Azad Univ, Dept Comp Engn, Isfahan Khorasgan Branch, Esfahan, Iran
[5] Islamic Azad Univ, Fac Basic Sci, Dept Basic Sci, Cent Tehran Branch, Tehran, Iran
[6] Urmia Univ Technol UUT, Dept Elect Engn, POB 57166-419, Orumiyeh, Iran
[7] Islamic Azad Univ, Dept Accounting Econ & Financial Sci, South Tehran Branch, Tehran, Iran
[8] Dublin City Univ, Fac Engn & Comp, Sch Comp, Dublin, Ireland
基金
爱尔兰科学基金会;
关键词
Medical image analysis; Breast cancer; Breast tumor segmentation; Deep learning; Pectoral muscle segmentation; IMAGE SEGMENTATION; CONTOURS; ORGANS;
D O I
10.1007/s10479-022-04755-8
中图分类号
C93 [管理学]; O22 [运筹学];
学科分类号
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要
Breast cancer is cancer that develops from the breast tissue and has been recognized as one of the most dangerous and deadly diseases that is the second leading cause of cancer deaths in women. To help doctors and radiologists to diagnose these tumors as well as decrease the time and increase the accuracy, many machine learning methods have been implemented by now. Most of these methods suffer from extracting some significant features that represent the boundary of tumors. This is due to the fact that benign and malignant tumors can be considered the same if some borders cannot segment properly. So, in this study, we propose an automatic breast tumor segmentation and recognition based on a shallow convolutional neural network that uses multi-feature extraction routes. Also, an image enhancement approach is used before applying the image into the model which leads to avoiding a very deep structure. Our strategy leads to improvement in detecting the border of tumors and boosts the classification accuracy of tumors. We evaluated our pipeline on Mammographic Image Analysis Society (Mini-MIAS) and Digital Database for Screening Mammography (DDSM) datasets. The developed model can localize and classify tumors with the accuracy of 0.936, 0.890, 0.871 on the DDSM, and 0.944, 0.915, 0.892 on the Mini-MIAS, for normal, benign, and malignant regions, respectively.
引用
收藏
页码:1021 / 1042
页数:22
相关论文
共 77 条
  • [31] Jafarian Amir Hossein, 2019, Iran J Pathol, V14, P232, DOI 10.30699/ijp.2019.94997.1939
  • [32] Image contrast enhancement using unsharp masking and histogram equalization
    Kansal, Shubhi
    Purwar, Shikha
    Tripathi, Rajiv Kumar
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (20) : 26919 - 26938
  • [33] Breast tumor segmentation and shape classification in mammograms using generative adversarial and convolutional neural network
    Kumar Singh, Vivek
    Rashwan, Hatem A.
    Romani, Santiago
    Akram, Farhan
    Pandey, Nidhi
    Kamal Sarker, Md Mostafa
    Saleh, Adel
    Arenas, Meritxell
    Arquez, Miguel
    Puig, Domenec
    Torrents-Barrena, Jordina
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2020, 139
  • [34] Binary-Classifiers-Enabled Filters for Semi-Supervised Learning
    Kumar, Teerath
    Park, Jinbae
    Ali, Muhammad Salman
    Uddin, A. F. M. Shahab
    Ko, Jong Hwan
    Bae, Sung-Ho
    [J]. IEEE ACCESS, 2021, 9 : 167663 - 167673
  • [35] Efficient backprop
    LeCun, Y
    Bottou, L
    Orr, GB
    Müller, KR
    [J]. NEURAL NETWORKS: TRICKS OF THE TRADE, 1998, 1524 : 9 - 50
  • [36] Breast tumor segmentation in 3D automatic breast ultrasound using Mask scoring R-CNN
    Lei, Yang
    He, Xiuxiu
    Yao, Jincao
    Wang, Tonghe
    Wang, Lijing
    Li, Wei
    Curran, Walter J.
    Liu, Tian
    Xu, Dong
    Yang, Xiaofeng
    [J]. MEDICAL PHYSICS, 2021, 48 (01) : 204 - 214
  • [37] An improved contrast enhancement algorithm for infrared images based on adaptive double plateaus histogram equalization
    Li, Shuo
    Jin, Weiqi
    Li, Li
    Li, Yiyang
    [J]. INFRARED PHYSICS & TECHNOLOGY, 2018, 90 : 164 - 174
  • [38] Online Human Action Detection Using Joint Classification-Regression Recurrent Neural Networks
    Li, Yanghao
    Lan, Cuiling
    Xing, Junliang
    Zeng, Wenjun
    Yuan, Chunfeng
    Liu, Jiaying
    [J]. COMPUTER VISION - ECCV 2016, PT VII, 2016, 9911 : 203 - 220
  • [39] Liu JH, 2011, COMM COM INF SC, V224, P172
  • [40] Computer-aided breast cancer diagnosis based on image segmentation and interval analysis
    Liu, Qing
    Liu, Zhigang
    Yong, Shenghui
    Jia, Kun
    Razmjooy, Navid
    [J]. AUTOMATIKA, 2020, 61 (03) : 496 - 506