Intelligent skin cancer detection applying autoencoder, MobileNetV2 and spiking neural networks

Abstract Melanocytes are skin cells that give color to the skin and form melanin color pigments. The unbalanced division and proliferation of these cells result in skin cancer. The early diagnosis and proper treatment of skin cancer are so important. In this scope, a novel model that relies upon the autoencoder, spiking, and convolutional neural networks is proposed to ensure a useful decision support tool in this study. The experiments were carried out on an open-access dataset called the ISIC skin cancer consisting of 1800 being and 1497 malignant tumor images. In the proposed approach, the dataset is reconstructed using the autoencoder model. The original dataset and structured dataset were trained and classified by the MobileNetV2 model that consists of residual blocks, and the spiking networks. The classification success rate of the study was 95.27%. As a result, it was seen that the autoencoder model and spiking networks contributed to enhancing the performance of the MobileNetV2 model. Thanks to the proposed model, a novel fully automated decision support tool with high sensitivity was ensured for skin cancer detection.

[1]  Saiful Islam,et al.  Cancer diagnosis in histopathological image: CNN based approach , 2019, Informatics in Medicine Unlocked.

[2]  Yalin Zheng,et al.  UV imaging reveals facial areas that are prone to skin cancer are disproportionately missed during sunscreen application , 2017, PloS one.

[3]  Cömert Zafer,et al.  Fusing fine-tuned deep features for recognizing different tympanic membranes , 2020 .

[4]  Mesut Toğaçar,et al.  COVID-19 detection using deep learning models to exploit Social Mimic Optimization and structured chest X-ray images using fuzzy color and stacking approaches , 2020, Computers in Biology and Medicine.

[5]  Dewei Li,et al.  LINEX Support Vector Machine for Large-Scale Classification , 2019, IEEE Access.

[6]  Zafer Cömert,et al.  Detection of lung cancer on chest CT images using minimum redundancy maximum relevance feature selection method with convolutional neural networks , 2020 .

[7]  Yongjun Jia,et al.  Using a stacked-autoencoder neural network model to estimate sea state bias for a radar altimeter , 2018, PloS one.

[8]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  J. Kato,et al.  Dermoscopy of Melanoma and Non-melanoma Skin Cancers , 2019, Front. Med..

[10]  Mubashir Ahmad,et al.  Vertebrae segmentation via stacked sparse autoencoder from computed tomography images , 2019, International Conference on Digital Image Processing.

[11]  Khalid M. Hosny,et al.  Classification of skin lesions using transfer learning and augmentation with Alex-net , 2019, PloS one.

[12]  Pengfei Chen,et al.  Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks , 2019, ArXiv.

[13]  Narasimhan Sundararajan,et al.  SEFRON: A New Spiking Neuron Model With Time-Varying Synaptic Efficacy Function for Pattern Classification , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[14]  Malu Zhang,et al.  An Efficient Supervised Training Algorithm for Multilayer Spiking Neural Networks , 2016, PloS one.

[15]  Tim Holland-Letz,et al.  Deep neural networks are superior to dermatologists in melanoma image classification. , 2019, European journal of cancer.

[16]  Chenquan Gan,et al.  The optimally designed autoencoder network for compressed sensing , 2019, EURASIP J. Image Video Process..

[17]  Zafer Cömert,et al.  Computer-aided diagnosis system combining FCN and Bi-LSTM model for efficient breast cancer detection from histopathological images , 2019, Appl. Soft Comput..

[18]  Ali Mohammad Alqudah,et al.  Segmented and Non-Segmented Skin Lesions Classification Using Transfer Learning and Adaptive Moment Learning Rate Technique Using Pretrained Convolutional Neural Network , 2019, Journal of Biomimetics, Biomaterials and Biomedical Engineering.

[19]  MATLAB Software , 2020, Introduction to Engineering Heat Transfer.

[20]  Jerzy Stefanowski,et al.  Visual-based analysis of classification measures and their properties for class imbalanced problems , 2018, Inf. Sci..

[21]  Jih-Jeng Huang,et al.  Double Deep Autoencoder for Heterogeneous Distributed Clustering , 2019, Inf..

[22]  Mesut Toğaçar,et al.  BrainMRNet: Brain tumor detection using magnetic resonance images with a novel convolutional neural network model. , 2019, Medical hypotheses.

[23]  Albert Bifet,et al.  Spiking Neural Networks and Online Learning: An Overview and Perspectives , 2019, Neural Networks.

[24]  Sugiyanto,et al.  Skins cancer identification system of HAMl0000 skin cancer dataset using convolutional neural network , 2019, INTERNATIONAL CONFERENCE ON SCIENCE AND APPLIED SCIENCE (ICSAS) 2019.

[25]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[26]  Xiaochao Dang,et al.  A Delay Learning Algorithm Based on Spike Train Kernels for Spiking Neurons , 2019, Front. Neurosci..

[27]  A S Spinelli,et al.  Computing of temporal information in spiking neural networks with ReRAM synapses , 2018, Faraday discussions.

[28]  F. Liu-Smith,et al.  Race-, Age-, and Anatomic Site-Specific Gender Differences in Cutaneous Melanoma Suggest Differential Mechanisms of Early- and Late-Onset Melanoma , 2019, International journal of environmental research and public health.

[29]  Peter Corcoran,et al.  Advanced Deep Learning Methodologies for Skin Cancer Classification in Prodromal Stages , 2020, AICS.

[30]  Zafer Cömert,et al.  BreastNet: A novel convolutional neural network model through histopathological images for the diagnosis of breast cancer , 2020 .

[31]  Mesut Toğaçar,et al.  Application of breast cancer diagnosis based on a combination of convolutional neural networks, ridge regression and linear discriminant analysis using invasive breast cancer images processed with autoencoders. , 2019, Medical hypotheses.

[32]  Romain Brette,et al.  Brian 2, an intuitive and efficient neural simulator , 2019, eLife.