Illumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images

The semantic segmentation of skin lesions is an important and common initial task in the computer aided diagnosis of dermoscopic images. Although deep learning-based approaches have considerably improved the segmentation accuracy, there is still room for improvement by addressing the major challenges, such as variations in lesion shape, size, color and varying levels of contrast. In this work, we propose the first deep semantic segmentation framework for dermoscopic images which incorporates, along with the original RGB images, information extracted using the physics of skin illumination and imaging. In particular, we incorporate information from specific color bands, illumination invariant grayscale images, and shading-attenuated images. We evaluate our method on three datasets: the ISBI ISIC 2017 Skin Lesion Segmentation Challenge dataset, the DermoFit Image Library, and the PH2 dataset and observe improvements of 12.02%, 4.30%, and 8.86% respectively in the mean Jaccard index over a baseline model trained only with RGB images.

[1]  Naimul Mefraz Khan,et al.  A Novel Focal Tversky Loss Function With Improved Attention U-Net for Lesion Segmentation , 2018, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[2]  N. Dubrawsky Cancer statistics , 1989, CA: a cancer journal for clinicians.

[3]  A. Jemal,et al.  Cancer statistics, 2020 , 2020, CA: a cancer journal for clinicians.

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

[5]  Lucia Maddalena,et al.  SDI+: A Novel Algorithm for Segmenting Dermoscopic Images , 2019, IEEE Journal of Biomedical and Health Informatics.

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

[7]  Hao Li,et al.  Visualizing the Loss Landscape of Neural Nets , 2017, NeurIPS.

[8]  A Lijiya,et al.  Skin Lesion Analysis Towards Melanoma Detection , 2019, 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT).

[9]  D. Fleming,et al.  Skin conditions are the commonest new reason people present to general practitioners in England and Wales , 2011, The British journal of dermatology.

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

[11]  Manu Goyal,et al.  The effect of color constancy algorithms on semantic segmentation of skin lesions , 2019, Medical Imaging.

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

[13]  Ghassan Hamarneh,et al.  Mask2Lesion: Mask-Constrained Adversarial Skin Lesion Image Synthesis , 2019, SASHIMI@MICCAI.

[14]  Gunther Wyszecki,et al.  Color Science: Concepts and Methods, Quantitative Data and Formulae, 2nd Edition , 2000 .

[15]  Pedro M. Ferreira,et al.  PH2 - A dermoscopic image database for research and benchmarking , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[16]  Tao Xu,et al.  Adversarial learning with multi-scale loss for skin lesion segmentation , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[17]  Cheng Lu,et al.  Intrinsic Images by Entropy Minimization , 2004, ECCV.

[18]  Guang Yang,et al.  Automatic skin lesion segmentation by coupling deep fully convolutional networks and shallow network with textons , 2019, Journal of medical imaging.

[19]  M. Copet,et al.  A Monte Carlo investigation of optical pathlength in inhomogeneous tissue and its application to near-infrared spectroscopy , 1993 .

[20]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[21]  Hao Chen,et al.  Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks , 2017, IEEE Transactions on Medical Imaging.

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

[23]  David W. Scott,et al.  Multivariate Density Estimation and Visualization , 2012 .

[24]  Noel C. F. Codella,et al.  Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[25]  Ghassan Hamarneh,et al.  Active contour models: application to oral lesion detection in color images , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[26]  Ghassan Hamarneh,et al.  Star Shape Prior in Fully Convolutional Networks for Skin Lesion Segmentation , 2018, MICCAI.

[27]  Ali Madooei,et al.  Incorporating Colour Information for Computer-Aided Diagnosis of Melanoma from Dermoscopy Images: A Retrospective Survey and Critical Analysis , 2016, Int. J. Biomed. Imaging.

[28]  Norimichi Tsumura,et al.  Independent Component Analysis of Skin Color Image , 1998, CIC.

[29]  Ghassan Hamarneh,et al.  Improved Inference via Deep Input Transfer , 2019, MICCAI.

[30]  J. Cohen,et al.  Color Science: Concepts and Methods, Quantitative Data and Formulas , 1968 .

[31]  Charles Poynton,et al.  Frequently Asked Questions about Color , 1997 .

[32]  Xudong Jiang,et al.  Dermoscopic Image Segmentation Through the Enhanced High-Level Parsing and Class Weighted Loss , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[33]  Costantino Grana,et al.  Augmenting data with GANs to segment melanoma skin lesions , 2019, Multimedia Tools and Applications.

[34]  Ghassan Hamarneh,et al.  CONVOLUTIONAL NEURAL NETWORK FOR SKIN LESION SEGMENTATION , 2018 .

[35]  Constantine Butakoff,et al.  Independent Histogram Pursuit for Segmentation of Skin Lesions , 2008, IEEE Transactions on Biomedical Engineering.

[36]  Gerald Schaefer,et al.  Contrast enhancement in dermoscopy images by maximizing a histogram bimodality measure , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[37]  Ali Madooei,et al.  Intrinsic Melanin and Hemoglobin Colour Components for Skin Lesion Malignancy Detection , 2012, MICCAI.

[38]  Robert B. Fisher,et al.  A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions , 2013 .

[39]  Julien Cohen-Adad,et al.  Deep semantic segmentation of natural and medical images: a review , 2019, Artificial Intelligence Review.

[40]  Ali Madooei,et al.  Automated Pre-processing Method for Dermoscopic Images and its Application to Pigmented Skin Lesion Segmentation , 2012, CIC.

[41]  Huiyu Zhou,et al.  A State-of-the-Art Survey on Lesion Border Detection in Dermoscopy Images , 2015 .

[42]  S. Feldman,et al.  Incidence Estimate of Nonmelanoma Skin Cancer (Keratinocyte Carcinomas) in the U.S. Population, 2012. , 2015, JAMA dermatology.