DermoNet: densely linked convolutional neural network for efficient skin lesion segmentation

被引:29
作者
Baghersalimi, Saleh [1 ]
Bozorgtabar, Behzad [1 ]
Schmid-Saugeon, Philippe [2 ]
Ekenel, Hazim Kemal [3 ]
Thiran, Jean-Philippe [1 ]
机构
[1] Ecole Polytech Fed Lausanne, Elect Engn Dept, Signal Proc Lab LTS5, Stn 11, CH-1015 Lausanne, Switzerland
[2] DermoSafe SA, EPFL Innovat Pk,Batiment D, CH-1015 Lausanne, Switzerland
[3] Dept Comp Engn, TR-34469 Istanbul, Turkey
关键词
Fully convolutional neural networks; Lesion segmentation;
D O I
10.1186/s13640-019-0467-y
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Recent state-of-the-art methods for skin lesion segmentation are based on convolutional neural networks (CNNs). Even though these CNN-based segmentation approaches are accurate, they are computationally expensive. In this paper, we address this problem and propose an efficient fully convolutional neural network, named DermoNet. In DermoNet, due to our densely connected convolutional blocks and skip connections, network layers can reuse information from their preceding layers and ensure high accuracy in later network layers. By doing so, we take advantage of the capability of high-level feature representations learned at intermediate layers with varying scales and resolutions for lesion segmentation. Quantitative evaluation is conducted on three well-established public benchmark datasets: the ISBI 2016, ISBI 2017, and the PH2 datasets. The experimental results show that our proposed approach outperforms the state-of-the-art algorithms on these three datasets. We also compared the runtime performance of DermoNet with two other related architectures, which are fully convolutional networks and U-Net. The proposed approach is found to be faster and suitable for practical applications.
引用
收藏
页数:10
相关论文
共 32 条
  • [1] Abadi M., 2015, P 12 USENIX S OPERAT
  • [2] [Anonymous], P 3 INT C LEARNING R
  • [3] [Anonymous], 2016, ARXIV PREPRINT ARXIV
  • [4] SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
    Badrinarayanan, Vijay
    Kendall, Alex
    Cipolla, Roberto
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) : 2481 - 2495
  • [5] Berseth M., 2017, ISIC 2017 SKIN LESIO
  • [6] Bozorgtabar B, 2017, I S BIOMED IMAGING, P256, DOI 10.1109/ISBI.2017.7950514
  • [7] Sparse Coding Based Skin Lesion Segmentation Using Dynamic Rule-Based Refinement
    Bozorgtabar, Behzad
    Abedini, Mani
    Garnavi, Rahil
    [J]. MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2016, 2016, 10019 : 254 - 261
  • [8] Semantic object classes in video: A high-definition ground truth database
    Brostow, Gabriel J.
    Fauqueur, Julien
    Cipolla, Roberto
    [J]. PATTERN RECOGNITION LETTERS, 2009, 30 (02) : 88 - 97
  • [9] Border detection in dermoscopy images using statistical region merging
    Celebi, M. Emre
    Kingravi, Hassan A.
    Iyatomi, Hitoshi
    Aslandogan, Y. Alp
    Stoecker, William V.
    Moss, Randy H.
    Malters, Joseph M.
    Grichnik, James M.
    Marghoob, Ashfaq A.
    Rabinovitz, Harold S.
    Menzies, Scott W.
    [J]. SKIN RESEARCH AND TECHNOLOGY, 2008, 14 (03) : 347 - 353
  • [10] DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    Chen, Liang-Chieh
    Papandreou, George
    Kokkinos, Iasonas
    Murphy, Kevin
    Yuille, Alan L.
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) : 834 - 848