Wound Detection by Simple Feedforward Neural Network

被引:7
|
作者
Marijanovic, Domagoj [1 ]
Nyarko, Emmanuel Karlo [1 ]
Filko, Damir [1 ]
机构
[1] Comp Sci & Informat Technol Osijek, Fac Elect Engn, Osijek 31000, Croatia
关键词
chronic wounds; wound detection; wound segmentation; feedforward neural network; robot; SEGMENTATION;
D O I
10.3390/electronics11030329
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Chronic wounds are a heavy burden on medical facilities, so any help in treating them is most welcome. Current research focuses on wound analysis, especially wound tissue classification, wound measurement, and wound healing prediction to assist medical personnel in wound treatment, with the main goal of reducing wound healing time. The first phase of wound analysis is wound segmentation, where the task is to extract wounds from the healthy tissue and image background. In this work, a standard feedforward neural network was developed for the purpose of wound segmentation using data from the MICCAI 2021 Foot Ulcer Segmentation (FUSeg) Challenge. It proved to be a simple yet efficient method for extracting wounds from images. The proposed algorithm is part of a compact system that analyzes chronic wounds using a robotic manipulator, RGB-D camera and 3D scanner. The feedforward neural network consists of only five fully connected layers, the first four with Rectified Linear Unit (ReLU) activation functions and the last with sigmoid activation functions. Three separate models were trained and tested using images provided as part of the challenge. The predicted images were post-processed and merged to improve the final segmentation performance.The accuracy metrics observed during model training and selection were Precision, Recall and F1 score. The experimental results of the proposed network provided a recall value of 0.77, precision value of 0.72, and an F1 score (Dice score) of 0.74.
引用
收藏
页数:18
相关论文
共 50 条
  • [31] Relations Between Wavelet Network and Feedforward Neural Network
    刘志刚
    何正友
    钱清泉
    Journal of Southwest Jiaotong University, 2002, (02) : 179 - 184
  • [32] Domain Flux-based DGA Botnet Detection Using Feedforward Neural Network
    Ashiq, Md Ishtiaq
    Bhowmick, Protick
    Hossain, Md Shohrab
    Narman, Husnu S.
    MILCOM 2019 - 2019 IEEE MILITARY COMMUNICATIONS CONFERENCE (MILCOM), 2019,
  • [33] A simple method to estimate the size of feedforward neural networks
    Li, YJ
    2003 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5, CONFERENCE PROCEEDINGS, 2003, : 1322 - 1326
  • [34] Visualizing the function computed by a feedforward neural network
    Plate, T
    Band, P
    Bert, J
    Grace, J
    PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 306 - 309
  • [35] Efficient learning algorithm for feedforward neural network
    Du, Zhengchun
    Liu, Yutian
    Xia, Daozhi
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 1995, 23 (08): : 57 - 61
  • [36] Modeling of Feedforward Neural Network in PAHRA Architecture
    Vokorokos, Liberios
    Adam, Norbert
    PROCEEDINGS OF THE 9TH WSEAS INTERNATIONAL CONFERENCE ON SIMULATION, MODELLING AND OPTIMIZATION, 2009, : 446 - +
  • [37] Establishing impacts of the inputs in a feedforward neural network
    T. Tchaban
    M. J. Taylor
    J. P. Griffin
    Neural Computing & Applications, 1998, 7 : 309 - 317
  • [38] Optimizing feedforward artificial neural network architecture
    Benardos, P. G.
    Vosniakos, G. -C.
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2007, 20 (03) : 365 - 382
  • [39] Particle swarms for feedforward neural network training
    Mendes, R
    Cortez, P
    Rocha, M
    Neves, J
    PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 1895 - 1899
  • [40] Establishing impacts of the inputs in a feedforward neural network
    Tchaban, T
    Taylor, MJ
    Griffin, JP
    NEURAL COMPUTING & APPLICATIONS, 1998, 7 (04): : 309 - 317