The effect of color constancy algorithms on semantic segmentation of skin lesions

With the ever growing occurrences of skin cancer and limited healthcare settings, a reliable computer assisted diagnostic system is needed to assist the dermatologists for lesion diagnosis. Skin lesion segmentation on dermo- scopic images can be an efficient tool to determine the differences between benign and malignant skin lesions. The dermoscopic images in the public skin lesion datasets are collected from various sources around the world. The color of lesions in dermoscopic images can be strongly dependent on the light source. In this work, we provide a new insight on the effect of color constancy algorithms on skin lesion segmentation with deep learning algorithm. We pre-process the ISIC Challenge Segmentation 2017 dataset using different color constancy algorithms and study the effect on a popular semantic segmentation algorithm, i.e. Fully Convolutional Networks. We evaluate the results with two evaluation metrics, i.e. Dice Similarity Coefficient and Jaccard Similarity Index. Overall, our experiments showed improvements in semantic segmentation of skin lesions when pre-processed with color constancy algorithms. Further, we investigate the effect of these algorithms on different types of lesions (Naevi, Melanoma and Seborrhoeic Keratosis). We found pre-processing with color constancy algorithms improved the segmentation results on Naevi and Seborrhoeic Keratosis, but not Melanoma. Future work will seek to investigate an adaptive color constancy algorithm that could improve the segmentation results.

[1]  Xipeng Qiu,et al.  A medical image color correction method base on supervised color constancy , 2008, 2008 IEEE International Symposium on IT in Medicine and Education.

[2]  Neil D. Reeves,et al.  Fully convolutional networks for diabetic foot ulcer segmentation , 2017, 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[3]  Pedro Costa,et al.  Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis , 2017, ArXiv.

[4]  Reyer Zwiggelaar,et al.  Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks , 2018, IEEE Journal of Biomedical and Health Informatics.

[5]  Manu Goyal,et al.  End-to-end breast ultrasound lesions recognition with a deep learning approach , 2018, Medical Imaging.

[6]  Manu Goyal,et al.  Robust Methods for Real-Time Diabetic Foot Ulcer Detection and Localization on Mobile Devices , 2019, IEEE Journal of Biomedical and Health Informatics.

[7]  Wei Zhang,et al.  Facial color management for mobile health in the wild , 2015, 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[8]  Gerald Schaefer,et al.  Colour and contrast enhancement for improved skin lesion segmentation , 2011, Comput. Medical Imaging Graph..

[9]  Manu Goyal,et al.  Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks , 2017, BIOINFORMATICS.

[10]  P. Jaccard.  Distribution de la flore alpine dans le bassin des Dranses et dans quelques régions voisines , 1901 .

[11]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[12]  Matti Pietikäinen,et al.  Detection of skin color under changing illumination: a comparative study , 2003, 12th International Conference on Image Analysis and Processing, 2003.Proceedings..

[13]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Neil D. Reeves,et al.  DFUNet: Convolutional Neural Networks for Diabetic Foot Ulcer Classification , 2017, IEEE Transactions on Emerging Topics in Computational Intelligence.

[15]  Xipeng Qiu,et al.  Color constancy model based on topology resolve-map in medical image processing , 2007, International Symposium on Multispectral Image Processing and Pattern Recognition.

[16]  Yongjie Li,et al.  Efficient Color Constancy with Local Surface Reflectance Statistics , 2014, ECCV.

[17]  Graham D. Finlayson,et al.  Shades of Gray and Colour Constancy , 2004, CIC.

[18]  Moi Hoon Yap,et al.  The effect of filtering algorithms for breast ultrasound lesions segmentation , 2018 .

[19]  Xiaolin Ma,et al.  Robust Estimation of Skin Pigmentation from Facial Color Images Based on Color Constancy , 2018, 2018 10th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA).

[20]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[21]  Nikola Banić,et al.  Smart light random memory sprays Retinex: a fast Retinex implementation for high-quality brightness adjustment and color correction. , 2015, Journal of the Optical Society of America. A, Optics, image science, and vision.

[22]  Manu Goyal,et al.  Breast ultrasound lesions recognition: end-to-end deep learning approaches , 2018, Journal of medical imaging.

[23]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[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]  Gerald Schaefer,et al.  Automated color calibration method for dermoscopy images , 2011, Comput. Medical Imaging Graph..

[26]  Manu Goyal,et al.  Multi-Class Lesion Diagnosis with Pixel-wise Classification Network , 2018, ArXiv.

[27]  Jorge S. Marques,et al.  Improving dermoscopy image analysis using color constancy , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[28]  Aichi Chien,et al.  An L1-based variational model for Retinex theory and its application to medical images , 2011, CVPR 2011.

[29]  Manu Goyal,et al.  Semantic Segmentation of Human Thigh Quadriceps Muscle in Magnetic Resonance Images , 2018, ArXiv.