Skin melanoma segmentation using recurrent and convolutional neural networks

Skin melanoma is one of the highly addressed health problems in many countries. Dermatologists diagnose melanoma by visual inspections of mole using clinical assessment tools such as ABCD. However, computer vision tools have been introduced to assist in quantitative analysis of skin lesions. Deep learning is one of the trending machine learning techniques that have been successfully utilized to solve many difficult computer vision tasks. We proposed using a hybrid method that utilizes two popular deep learning methods: convolutional and recurrent neural networks. The proposed method was trained using 900 images and tested on 375 images. Images were obtained from “Skin Lesion Analysis Toward Melanoma Detection” challenge which was hosted by ISBI 2016 conference. We achieved segmentation average accuracy of 0.98 and Jaccard index of 0.93. Results were compared with other state-of-the-art methods, including winner of ISBI 2016 challenge for skin melanoma segmentation, along with the same evaluation criteria.

[1]  H P Soyer,et al.  A pilot trial of mobile, patient‐performed teledermoscopy , 2015, The British journal of dermatology.

[2]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

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

[4]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling , 2015, CVPR 2015.

[5]  Francesco Visin,et al.  A guide to convolution arithmetic for deep learning , 2016, ArXiv.

[6]  Rob Fergus,et al.  Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Junji Maeda,et al.  Comparison of Segmentation Methods for Melanoma Diagnosis in Dermoscopy Images , 2009, IEEE Journal of Selected Topics in Signal Processing.

[8]  R. Wolfe,et al.  Comparative performance of 4 dermoscopic algorithms by nonexperts for the diagnosis of melanocytic lesions. , 2005, Archives of dermatology.

[9]  한보형,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015 .

[10]  Vibhav Vineet,et al.  Conditional Random Fields as Recurrent Neural Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Yoshua Bengio,et al.  ReSeg: A Recurrent Neural Network for Object Segmentation , 2015, ArXiv.

[12]  Ilias Maglogiannis,et al.  Skin lesions image analysis utilizing smartphones and cloud platforms. , 2015, Methods in molecular biology.

[13]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Rafael García,et al.  Computerized analysis of pigmented skin lesions: A review , 2012, Artif. Intell. Medicine.

[15]  Gerald Schaefer,et al.  Lesion border detection in dermoscopy images , 2009, Comput. Medical Imaging Graph..

[16]  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).

[17]  Hassan Mohamed,et al.  Skin lesion segmentation using Gray Level Co-occurance Matrix , 2016 .

[18]  Yoshua Bengio,et al.  Gated Feedback Recurrent Neural Networks , 2015, ICML.