Automatic Lesion Boundary Segmentation in Dermoscopic Images with Ensemble Deep Learning Methods

Early detection of skin cancer, particularly melanoma, is crucial to enable advanced treatment. Due to the rapid growth in the numbers of skin cancers, there is a growing need of computerized analysis for skin lesions. The state-of-the-art public available datasets for skin lesions are often accompanied with very limited amount of segmentation ground truth labeling as it is laborious and expensive. The lesion boundary segmentation is vital to locate the lesion accurately in dermoscopic images and lesion diagnosis of different skin lesion types. In this work, we propose the use of fully automated deep learning ensemble methods for accurate lesion boundary segmentation in dermoscopic images. We trained the Mask-RCNN and DeepLabv3+ methods on ISIC-2017 segmentation training set and evaluate the performance of the ensemble networks on ISIC-2017 testing set. Our results showed that the best proposed ensemble method segmented the skin lesions with Jaccard index of 79.58% for the ISIC-2017 testing set. The proposed ensemble method outperformed FrCN, FCN, U-Net, and SegNet in Jaccard Index by 2.48%, 7.42%, 17.95%, and 9.96% respectively. Furthermore, the proposed ensemble method achieved an accuracy of 95.6% for some representative clinically benign cases, 90.78% for the melanoma cases, and 91.29% for the seborrheic keratosis cases on ISIC-2017 testing set, exhibiting better performance than FrCN, FCN, U-Net, and SegNet.

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

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

[3]  Dagan Feng,et al.  Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks , 2017, IEEE Transactions on Biomedical Engineering.

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

[5]  Harald Kittler,et al.  Descriptor : The HAM 10000 dataset , a large collection of multi-source dermatoscopic images of common pigmented skin lesions , 2018 .

[6]  J. Mayer,et al.  Systematic review of the diagnostic accuracy of dermatoscopy in detecting malignant melanoma , 1997, The Medical journal of Australia.

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

[8]  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.

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

[10]  Mun-Taek Choi,et al.  Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks , 2018, Comput. Methods Programs Biomed..

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

[12]  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).

[13]  P. C. Siddalingaswamy,et al.  Techniques and algorithms for computer aided diagnosis of pigmented skin lesions - A review , 2018, Biomed. Signal Process. Control..

[14]  Antonio Criminisi,et al.  Segmentation of Brain Tumor Tissues with Convolutional Neural Networks , 2014 .

[15]  John R. Smith,et al.  Deep Learning, Sparse Coding, and SVM for Melanoma Recognition in Dermoscopy Images , 2015, MLMI.

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

[17]  David Polsky,et al.  Early diagnosis of cutaneous melanoma: revisiting the ABCD criteria. , 2004, JAMA.

[18]  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.

[19]  Giovanni Pellacani,et al.  Comparison between morphological parameters in pigmented skin lesion images acquired by means of epiluminescence surface microscopy and polarized-light videomicroscopy. , 2002, Clinics in dermatology.

[20]  Victor Alves,et al.  Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images , 2016, IEEE Transactions on Medical Imaging.

[21]  P. Lakhani,et al.  Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks. , 2017, Radiology.

[22]  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).

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

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

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

[26]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

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

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

[29]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

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

[31]  Shuiwang Ji,et al.  Deep convolutional neural networks for multi-modality isointense infant brain image segmentation , 2015, NeuroImage.

[32]  Paul Nghiem,et al.  Interactive Atlas of Dermoscopy , 2004 .

[33]  Manu Goyal,et al.  Facial Skin Classification Using Convolutional Neural Networks , 2017, ICIAR.

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

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