Multi-Class Diagnosis of Skin Lesions Using the Fourier Spectral Information of Images on Additive Color Model by Artificial Neural Network

This article presents a new methodology to diagnostics ten types of skin lesions based on the image’ s Fourier spectral information in an additive color model. All spectral information and correlation coefficients between the skin lesions classes conform the input signals to an Artificial Neural Network. In general, the results show the well-defined classification for all the skin lesions classes based on the high values for Accuracy, Precision, Sensitivity, and Specificity metrics performance and a reduced images misclassification percentage (≈5.9%) for the Testing sub-dataset, and less for Training (≈2.8%) and Validation (≈5.6%) sub-dataset even considering the strange objects, not-clarity, and black sections in some images analyzed. The general achieved classification Accuracy, Precision, Sensitivity, and Specificity percentages of the proposed method are 99.33 %, 94.16 %, 92.9 %, and 99.63 %, respectively. In particular, the skin lesions related to Basal Cell Carcinoma, Seborrhoeic Keratosis, and Melanocytic Nevus present the best performance regarding the Receiver Operating Characteristics, while the Pyogenic Granuloma was the worst classified.

[1]  Manan Shah,et al.  An anatomization on breast cancer detection and diagnosis employing multi-layer perceptron neural network (MLP) and Convolutional neural network (CNN) , 2020 .

[2]  H. Comber,et al.  Geographical, urban/rural and socioeconomic variations in nonmelanoma skin cancer incidence: a population‐based study in Ireland , 2011, The British journal of dermatology.

[3]  J. Álvarez-Borrego,et al.  Identification of melanoma cells: a method based in mean variance of signatures via spectral densities. , 2017, Biomedical optics express.

[4]  Rajiv Kumar Tripathi,et al.  Adaptive histogram equalization based on modified probability density function and expected value of image intensity , 2019, Signal, Image and Video Processing.

[5]  Theodoula N. Grapsa,et al.  Self-scaled conjugate gradient training algorithms , 2009, Neurocomputing.

[6]  Kohei Arai.  Image Classification Considering Probability Density Function based on Simplified Beta Distribution , 2020 .

[7]  Hongzhi Gao,et al.  Non-invasive prediction of hemoglobin levels by principal component and back propagation artificial neural network. , 2014, Biomedical optics express.

[8]  Josué Álvarez-Borrego,et al.  Methodology for diagnosing of skin cancer on images of dermatologic spots by spectral analysis. , 2015, Biomedical optics express.

[9]  K. Sellheyer.  Basal cell carcinoma: cell of origin, cancer stem cell hypothesis and stem cell markers , 2011, The British journal of dermatology.

[10]  Kyle J. Godfrey,et al.  Unique histopathologic features of the eyelid dermatofibroma , 2018, Orbit.

[11]  Khalid M. Hosny,et al.  Skin Lesions Classification Into Eight Classes for ISIC 2019 Using Deep Convolutional Neural Network and Transfer Learning , 2020, IEEE Access.

[12]  Yutaka Satoh,et al.  Using selective correlation coefficient for robust image registration , 2003, Pattern Recognit..

[13]  Trevor J. Bihl,et al.  Quantifying skin photodamage with spatial frequency domain imaging: statistical results. , 2019, Biomedical optics express.

[14]  Karim Baïna,et al.  Reduce False Positive Alerts for Elderly Person Fall Video-Detection Algorithm by convolutional neural network model , 2019, Procedia Computer Science.

[15]  Yufan He,et al.  Parallel deep neural networks for endoscopic OCT image segmentation. , 2019, Biomedical optics express.

[16]  L. Rudnicka,et al.  Non-invasive diagnostic techniques in the diagnosis of squamous cell carcinoma. , 2015, Journal of dermatological case reports.

[17]  Darío Baptista,et al.  A survey of artificial neural network training tools , 2013, Neural Computing and Applications.

[18]  Xiao Li,et al.  Learning Coupled Classifiers with RGB images for RGB-D object recognition , 2017, Pattern Recognit..

[19]  Dimitris N. Metaxas,et al.  A computationally efficient 3D/2D registration method based on image gradient direction probability density function , 2017, Neurocomputing.

[20]  M L Meistrell,et al.  Evaluation of neural network performance by receiver operating characteristic (ROC) analysis: examples from the biotechnology domain. , 1989, Computer methods and programs in biomedicine.

[21]  U. Alabalık,et al.  Multiple disseminated pyogenic granuloma after second degree scald burn: a rare two case. , 2013, International journal of burns and trauma.

[22]  Kung-Bin Sung,et al.  Modelling spatially-resolved diffuse reflectance spectra of a multi-layered skin model by artificial neural networks trained with Monte Carlo simulations. , 2018, Biomedical optics express.

[23]  Peter A. Flach,et al.  ROC curves in cost space , 2013, Machine Learning.

[24]  Aman Jantan,et al.  State-of-the-art in artificial neural network applications: A survey , 2018, Heliyon.

[25]  J. Álvarez-Borrego,et al.  Spectral indexes obtained by implementation of the fractional Fourier and Hermite transform for the diagnosis of malignant melanoma. , 2019, Biomedical optics express.

[26]  A. Jayachandran,et al.  Multi-Class Skin Lesions Classification System Using Probability Map Based Region Growing and DCNN , 2020, Int. J. Comput. Intell. Syst..

[27]  Aidong Adam Ding,et al.  Neural-network prediction with noisy predictors , 1999, IEEE Trans. Neural Networks.

[28]  Yue Liu.  Artificial Intelligence–Based Neural Network for the Diagnosis of Diabetes: Model Development , 2020, JMIR medical informatics.

[29]  Khalid M. Hosny,et al.  Classification of Skin Lesions into Seven Classes Using Transfer Learning with AlexNet , 2020, Journal of Digital Imaging.

[30]  Joanna Jaworek-Korjakowska,et al.  eSkin: Study on the Smartphone Application for Early Detection of Malignant Melanoma , 2018, Wirel. Commun. Mob. Comput..

[31]  D. Donoho,et al.  Fast and accurate Polar Fourier transform , 2006 .

[32]  U. G. Dailey.  Cancer,Facts and Figures about. , 2022, Journal of the National Medical Association.

[33]  Wei Wu,et al.  Multi-instance multi-label learning of natural scene images: via sparse coding and multi-layer neural network , 2017, IET Comput. Vis..

[34]  D. Sasikala,et al.  Correlation Coefficient Measure of Mono and Multimodal Brain Image Registration using Fast Walsh Hadamard Transform , 2011 .

[35]  Ulas Sunar,et al.  Noninvasive mesoscopic imaging of actinic skin damage using spatial frequency domain imaging. , 2017, Biomedical optics express.

[36]  A. Karadağ,et al.  The status of the seborrheic keratosis. , 2017, Clinics in dermatology.

[37]  K. Sardana,et al.  Optimal management of common acquired melanocytic nevi (moles): current perspectives , 2014, Clinical, cosmetic and investigational dermatology.

[38]  J. Dheeba,et al.  Computer-aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach , 2014, J. Biomed. Informatics.

[39]  Supriya Sharma,et al.  Heterogeneous conceptualization of etiopathogenesis: Oral pyogenic granuloma , 2019, National journal of maxillofacial surgery.

[40]  Natan T. Shaked,et al.  PhUn-Net: ready-to-use neural network for unwrapping quantitative phase images of biological cells. , 2020, Biomedical optics express.

[41]  Lopamudra Mukherjee,et al.  Convolutional neural networks for whole slide image superresolution. , 2018, Biomedical optics express.

[42]  Igor Meglinski,et al.  Hyperspectral imaging of human skin aided by artificial neural networks. , 2019, Biomedical optics express.

[43]  Walter L. Smith.  Probability and Statistics , 1959, Nature.

[44]  Mitsuo Kawato,et al.  Feedback error learning of movement by multi-layer neural network , 1988, Neural Networks.