Pixels to Classes: Intelligent Learning Framework for Multiclass Skin Lesion Localization and Classification

Abstract A novel deep learning framework is proposed for lesion segmentation and classification. The proposed technique incorporates two primary phases. For lesion segmentation, Mask recurrent convolutional neural network (MASK R-CNN) based architecture is implemented. In this architecture, Resnet50 along with feature pyramid network (FPN) is utilized as a backbone. Later, fully connected layer-based features are mapped for the final mask generation. In the classification phase, 24-layered convolutional neural network architecture is designed, which performs activation based on the visualization of higher features. Finally, best CNN features are provided to softmax classifiers for final classification. Three datasets (i.e. PH2, ISBI2016, and ISIC2017) are utilized for the validation of the segmentation process, whilst HAM10000 dataset is utilized for the classification. From the results, it is concluded that the proposed method outperforms several existing techniques, based on the selected set of parameters including sensitivity (85.57%), precision (87.01%), F1- Score (86.28%), and accuracy (86.5%).

[1]  Jeremiah W. Johnson,et al.  Adapting Mask-RCNN for Automatic Nucleus Segmentation , 2018, ArXiv.

[2]  Mohamed M. Foaud,et al.  Classification of skin lesions using transfer learning and augmentation with Alex-net , 2019, PloS one.

[3]  Nazia Hameed,et al.  Multi-class multi-level classification algorithm for skin lesions classification using machine learning techniques , 2020, Expert Syst. Appl..

[4]  Yong Xia,et al.  Attention Residual Learning for Skin Lesion Classification , 2019, IEEE Transactions on Medical Imaging.

[5]  Eric Z. Chen,et al.  From Deep Learning Towards Finding Skin Lesion Biomarkers , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[6]  Pedro A. Amado Assunção,et al.  Skin lesion classification enhancement using border-line features - The melanoma vs nevus problem , 2020, Biomed. Signal Process. Control..

[7]  Jorge S. Marques,et al.  A Survey of Feature Extraction in Dermoscopy Image Analysis of Skin Cancer , 2019, IEEE Journal of Biomedical and Health Informatics.

[8]  Ming-Chun Huang,et al.  Medical image learning from a few/few training samples: Melanoma segmentation study , 2019 .

[9]  A. Jemal,et al.  Cancer statistics, 2016 , 2016, CA: a cancer journal for clinicians.

[10]  Ghassan Hamarneh,et al.  Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features , 2017, IEEE Journal of Biomedical and Health Informatics.

[11]  Pierluigi Carcagnì,et al.  Classification of Skin Lesions by Combining Multilevel Learnings in a DenseNet Architecture , 2019, ICIAP.

[12]  Satya P. Singh,et al.  Deep Learning Solutions for Skin Cancer Detection and Diagnosis , 2020 .

[13]  Harald Kittler,et al.  The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions , 2018, Scientific Data.

[14]  Dong-Hyun Kim,et al.  Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification , 2020, Comput. Methods Programs Biomed..

[15]  LinLin Shen,et al.  Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network , 2017, Sensors.

[16]  Wiphada Wettayaprasit,et al.  Convolutional Neural Networks Using MobileNet for Skin Lesion Classification , 2019, 2019 16th International Joint Conference on Computer Science and Software Engineering (JCSSE).

[17]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[18]  P Barbini,et al.  Digital dermoscopy analysis for the differentiation of atypical nevi and early melanoma: a new quantitative semiology. , 1999, Archives of dermatology.

[19]  Soumen Mukherjee,et al.  Malignant Melanoma Classification Using Cross-Platform Dataset with Deep Learning CNN Architecture , 2019, Recent Trends in Signal and Image Processing.

[20]  Michael S. Bernstein,et al.  Scalable multi-label annotation , 2014, CHI.

[21]  Chunhua Shen,et al.  A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification , 2020, IEEE Transactions on Medical Imaging.

[22]  Amjad Rehman,et al.  A Sustainable Deep Learning Framework for Object Recognition Using Multi-Layers Deep Features Fusion and Selection , 2020, Sustainability.

[23]  Maria Trocan,et al.  Benign and Malignant Skin Lesion Classification Comparison for Three Deep-Learning Architectures , 2020, ACIIDS.

[24]  Stephan Dreiseitl,et al.  Do physicians value decision support? A look at the effect of decision support systems on physician opinion , 2005, Artif. Intell. Medicine.

[25]  V. del Marmol,et al.  Melanoma incidence and mortality in Europe: new estimates, persistent disparities , 2012, The British journal of dermatology.

[26]  Muhammad Sharif,et al.  Developed Newton-Raphson based deep features selection framework for skin lesion recognition , 2020, Pattern Recognit. Lett..

[27]  Muhammad Rashid,et al.  An integrated framework of skin lesion detection and recognition through saliency method and optimal deep neural network features selection , 2019, Neural Computing and Applications.

[28]  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).

[29]  Tim Holland-Letz,et al.  Superior skin cancer classification by the combination of human and artificial intelligence. , 2019, European journal of cancer.