A Skin Lesion Segmentation Method for Dermoscopic Images Based on Adaptive Thresholding with Normalization of Color Models

In medical image processing, the skin lesion segmentation problem plays a vital role, because it is necessary to improve quality of extracting skin lesion features to classify the skin lesion. Hence, imaging diagnosis systems can detect skin cancer early. It is necessary to treat the skin cancer, especially, melanoma – one of the most dangerous form of skin cancer. In this paper, we proposed two adaptive methods to estimate the global threshold used for skin lesion segmentation based on normalization of the color models: RGB and XYZ. The skin lesion segmentation based on our proposed methods gives better result than the Otsu segmentation method regarding the grayscale model. This comparison is assessed on popular metrics for image segmentation, such as Dice and Jaccard scores. Experiments are tested on the famous ISIC dataset.

[1]  Yading Yuan,et al.  Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance , 2017, IEEE Transactions on Medical Imaging.

[2]  K. Y. Kim,et al.  An Automatic Detection of the ROI Using Otsu Thresholding in Nonlinear Difference EIT Imaging , 2018, IEEE Sensors Journal.

[3]  Pascal Getreuer,et al.  Chan-Vese Segmentation , 2012, Image Process. Line.

[4]  Ming Chao,et al.  Improving Dermoscopic Image Segmentation With Enhanced Convolutional-Deconvolutional Networks , 2017, IEEE Journal of Biomedical and Health Informatics.

[5]  Derek Bradley,et al.  Adaptive Thresholding using the Integral Image , 2007, J. Graph. Tools.

[6]  Ovidiu Daescu,et al.  Deep learning for skin lesion segmentation , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[7]  Matt Berseth,et al.  ISIC 2017 - Skin Lesion Analysis Towards Melanoma Detection , 2017, ArXiv.

[8]  Dang N. H. Thanh,et al.  An adaptive image inpainting method based on the modified mumford-shah model and multiscale parameter estimation , 2019, Computer Optics.

[9]  Gabriela Csurka,et al.  What is a good evaluation measure for semantic segmentation? , 2013, BMVC.

[10]  David Dagan Feng,et al.  Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks , 2017, ArXiv.

[11]  Dang N. H. Thanh,et al.  BLOOD VESSELS SEGMENTATION METHOD FOR RETINAL FUNDUS IMAGES BASED ON ADAPTIVE PRINCIPAL CURVATURE AND IMAGE DERIVATIVE OPERATORS , 2019 .

[12]  The ABCD rule , 2004 .

[13]  Dang N. H. Thanh,et al.  A Variational Method to Remove the Combination of Poisson and Gaussian Noises , 2018, IMTA.

[14]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[15]  Allan Hanbury,et al.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool , 2015, BMC Medical Imaging.

[16]  Kimon P. Valavanis,et al.  Noise removal from color images , 1993, J. Intell. Robotic Syst..

[17]  Dang N. H. Thanh,et al.  Automatic Initial Boundary Generation Methods Based on Edge Detectors for the Level Set Function of the Chan-Vese Segmentation Model and Applications in Biomedical Image Processing , 2019, Frontiers in Intelligent Computing: Theory and Applications.

[18]  Robert W. G. Hunt,et al.  The reproduction of colour , 1957 .