Automatic adjustment of the pulse-coupled neural network hyperparameters based on differential evolution and cluster validity index for image segmentation

Abstract The pulse-coupled neural network (PCNN) is a cortical model that can be used in image segmentation applications. The performance of the PCNN depends on adjusting its hyperparameters, where population-based metaheuristics, such as evolutionary algorithms, have been used to perform this task by optimizing a fitness function. In this regard, the entropy criterion is a common fitness function used to evaluate the quality of potential PCNN solutions. However, maximizing the entropy is related to maximize the inter-group separation, but the intra-group cohesion is unconsidered. In this regard, a cluster validity index (CVI) can be used as a fitness function, which defines a relationship between inter-group separation and intra-group cohesion. Therefore, we propose using a CVI to quantify the segmentation quality generated by the PCNN given a set of hyperparameters adjusted by the differential evolution algorithm. The proposed approach is tested on a dataset of natural images, where every image has three reference segmentations; thus, the Jaccard index is used to measure the segmentation performance. The experimental results reveal that a simplified PCNN, when used jointly with the Silhouette index, obtains the best performance with a mean Jaccard value of 0.77, whereas the entropy criterion attains 0.41. Additionally, the proposed approach is tested on two modalities of medical images to show its applicability in other kinds of images. The results suggest that using a CVI instead of the entropy criterion can improve the segmentation performance of the PCNN.

[1]  Yide Ma,et al.  Review of pulse-coupled neural networks , 2010, Image Vis. Comput..

[2]  T. Caliński,et al.  A dendrite method for cluster analysis , 1974 .

[3]  Swagatam Das,et al.  Automatic Clustering Using an Improved Differential Evolution Algorithm , 2007 .

[4]  Juan Humberto Sossa Azuela,et al.  Differential evolution training algorithm for dendrite morphological neural networks , 2018, Appl. Soft Comput..

[5]  Juanita Hernández,et al.  Automatic Tuning of the Pulse-Coupled Neural Network Using Differential Evolution for Image Segmentation , 2016, MCPR.

[6]  Yide Ma,et al.  Applications of Pulse-Coupled Neural Networks , 2011 .

[7]  M. Arndt,et al.  A neural network for feature linking via synchronous activity: Results from cat visual cortex and from simulations , 1989 .

[8]  Ding,et al.  Study of automated PCNN system based on fruit fly optimization algorithm , 2014 .

[9]  Minho Kim,et al.  New indices for cluster validity assessment , 2005, Pattern Recognit. Lett..

[10]  L Leija,et al.  Computerized lesion segmentation of breast ultrasound based on marker-controlled watershed transformation. , 2009, Medical physics.

[11]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[12]  Sarat Kumar Sahoo,et al.  Pulse coupled neural networks and its applications , 2014, Expert Syst. Appl..

[13]  M. Giger,et al.  Automatic segmentation of breast lesions on ultrasound. , 2001, Medical physics.

[14]  Juan Humberto Sossa Azuela,et al.  Retinal vessel extraction using Lattice Neural Networks with dendritic processing , 2015, Comput. Biol. Medicine.

[15]  Andries P. Engelbrecht,et al.  Computational Intelligence: An Introduction , 2002 .

[16]  Maryellen L. Giger,et al.  Computer-aided diagnosis of breast lesions in medical images , 2000, Comput. Sci. Eng..

[17]  Ujjwal Maulik,et al.  Performance Evaluation of Some Clustering Algorithms and Validity Indices , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Andrew K. C. Wong,et al.  A gray-level threshold selection method based on maximum entropy principle , 1989, IEEE Trans. Syst. Man Cybern..

[19]  Gerardo Beni,et al.  A Validity Measure for Fuzzy Clustering , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Jun Yu,et al.  Unsupervised image segmentation via Stacked Denoising Auto-encoder and hierarchical patch indexing , 2018, Signal Process..

[21]  Mengshu Hou,et al.  Automatic image segmentation based on PCNN with adaptive threshold time constant , 2011, Neurocomputing.

[22]  Jayaram K. Udupa,et al.  A framework for evaluating image segmentation algorithms , 2006, Comput. Medical Imaging Graph..

[23]  Václav Snásel,et al.  Metaheuristic design of feedforward neural networks: A review of two decades of research , 2017, Eng. Appl. Artif. Intell..

[24]  Ashraf K. Helmy,et al.  Image segmentation scheme based on SOM-PCNN in frequency domain , 2016, Appl. Soft Comput..

[25]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[26]  Dushyant Rao,et al.  Deep tracking in the wild: End-to-end tracking using recurrent neural networks , 2018, Int. J. Robotics Res..

[27]  Brian Kulis,et al.  W-Net: A Deep Model for Fully Unsupervised Image Segmentation , 2017, ArXiv.

[28]  Michele Ruggiero Banish,et al.  Using a genetic algorithm to find an optimized pulse coupled neural network solution , 2008, SPIE Defense + Commercial Sensing.

[29]  Maryellen L. Giger,et al.  Automated seeded lesion segmentation on digital mammograms , 1998, IEEE Transactions on Medical Imaging.

[30]  Hong Zhu,et al.  Particle Swarm Optimization for Automatic Parameters Determination of Pulse Coupled Neural Network , 2011, J. Comput..

[31]  Mohamed Medhat Gaber,et al.  A SOM-based Chan–Vese model for unsupervised image segmentation , 2017, Soft Comput..

[32]  Kevin L. Priddy,et al.  Artificial neural networks - an introduction , 2005, Tutorial text series.

[33]  Xiangying Jiang.  A Self-Adapting Pulse-Coupled Neural Network Based on Modified Differential Evolution Algorithm and Its Application on Image Segmentation , 2012 .

[34]  Masanori Suganuma,et al.  A genetic programming approach to designing convolutional neural network architectures , 2017, GECCO.

[35]  J. L. Johnson,et al.  Observation of periodic waves in a pulse-coupled neural network. , 1993, Optics letters.

[36]  Ronen Basri,et al.  Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Lei Ding,et al.  Image Segmentation with PCNN Model and Immune Algorithm , 2013, J. Comput..

[38]  Kenneth O. Stanley,et al.  Simple Evolutionary Optimization Can Rival Stochastic Gradient Descent in Neural Networks , 2016, GECCO.

[39]  Jason M. Kinser,et al.  The intersecting cortical model in image processing , 2004 .

[40]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Peng Zhang,et al.  PCNN document segmentation method based on bacterial foraging optimization algorithm , 2014, Digital Image Processing.

[42]  Iman Aganj,et al.  Unsupervised Medical Image Segmentation Based on the Local Center of Mass , 2018, Scientific Reports.

[43]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Guanying Wang,et al.  Self-Adaptive PCNN Based on the ACO Algorithm and its Application on Medical Image Segmentation , 2017, Intell. Autom. Soft Comput..