High-Level Hessian-Based Image Processing with the Frangi Neuron

被引:0
|
作者
Hachaj, Tomasz [1 ]
Piekarczyk, Marcin [1 ]
机构
[1] AGH Univ Sci & Technol, Fac Elect Engn Automat Comp Sci & Biomed Engn, Dept Appl Comp Sci, Al A Mickiewicza 30, PL-30059 Krakow, Poland
关键词
neural network; machine learning; deep learning; Frangi filter; Hessian; semantic segmentation; VESSEL SEGMENTATION; EXTRACTION; FEATURES; NETWORK;
D O I
10.3390/electronics12194159
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The Frangi neuron proposed in this work is a complex element that allows high-level Hessian-based image processing. Its adaptive parameters (weights) can be trained using a minimum number of training data. In our experiment, we showed that just one image is enough to optimize the values of the weights. An intuitive application of the Frangi neuron is to use it in image segmentation process. In order to test the performance of the Frangi neuron, we used diverse medical datasets on which second-order structures are visualized. The Frangi network presented in this paper trained on a single image proved to be significantly more effective than the U-net trained on the same dataset. For the datasets tested, the network performed better as measured by area under the curve receiver operating characteristic (ROC AUC) than U-net and the Frangi algorithm. However, the Frangi network performed several times faster than the non-GPU implementation of Frangi. There is nothing to prevent the Frangi neuron from being used as part of any other network as a component to process two-dimensional images, for example, to detect certain second-order features in them.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Assessment of hessian-based Frangi vesselness filter in optoacoustic imaging
    Longo, Antonia
    Morscher, Stefan
    Najafababdi, Jaber Malekzadeh
    Jüstel, Dominik
    Zakian, Christian
    Ntziachristos, Vasilis
    [J]. Photoacoustics, 2020, 20
  • [2] Assessment of hessian-based Frangi vesselness filter in optoacoustic imaging
    Longo, Antonia
    Morscher, Stefan
    Najafababdi, Jaber Malekzadeh
    Juestel, Dominik
    Zakian, Christian
    Ntziachristos, Vasilis
    [J]. PHOTOACOUSTICS, 2020, 20
  • [3] Hessian-Based Affine Adaptation of Salient Local Image Features
    Ruan Lakemond
    Sridha Sridharan
    Clinton Fookes
    [J]. Journal of Mathematical Imaging and Vision, 2012, 44 : 150 - 167
  • [4] Hessian-Based Norm Regularization for Image Restoration With Biomedical Applications
    Lefkimmiatis, Stamatios
    Bourquard, Aurelien
    Unser, Michael
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2012, 21 (03) : 983 - 995
  • [5] Hessian-Based Similarity Metric for Multimodal Medical Image Registration
    Eskandari, Mohammadreza
    Gueziri, Houssem-Eddine
    Collins, D. Louis
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2023 WORKSHOPS, 2023, 14394 : 253 - 264
  • [6] Hessian-Based Affine Adaptation of Salient Local Image Features
    Lakemond, Ruan
    Sridharan, Sridha
    Fookes, Clinton
    [J]. JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2012, 44 (02) : 150 - 167
  • [7] High-Level Expectations for Low-Level Image Processing
    Hotz, Lothar
    Neumann, Bernd
    Terzic, Kasim
    [J]. KI 2008: ADVANCES IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2008, 5243 : 87 - +
  • [8] HESSIAN-BASED REGULARIZATION FOR 3-D MICROSCOPY IMAGE RESTORATION
    Lefkimmiatis, Stamatios
    Bourquard, Aurelien
    Unser, Michael
    [J]. 2012 9TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2012, : 1731 - 1734
  • [9] HESSIAN-BASED SAMPLING FOR HIGH-DIMENSIONAL MODEL REDUCTION
    Chen, Peng
    Ghattas, Omar
    [J]. INTERNATIONAL JOURNAL FOR UNCERTAINTY QUANTIFICATION, 2019, 9 (02) : 103 - 121
  • [10] A HIGH-LEVEL LANGUAGE FOR PARALLEL IMAGE-PROCESSING
    BROWN, J
    CROOKES, D
    [J]. IMAGE AND VISION COMPUTING, 1994, 12 (02) : 67 - 79