Skin lesion segmentation and classification using deep learning and handcrafted features

Accurate diagnostics of a skin lesion is a critical task in classification dermoscopic images. In this research, we form a new type of image features, called hybrid features, which has stronger discrimination ability than single method features. This study involves a new technique where we inject the handcrafted features or feature transfer into the fully connected layer of Convolutional Neural Network (CNN) model during the training process. Based on our literature review until now, no study has examined or investigated the impact on classification performance by injecting the handcrafted features into the CNN model during the training process. In addition, we also investigated the impact of segmentation mask and its effect on the overall classification performance. Our model achieves an 92.3% balanced multiclass accuracy, which is 6.8% better than the typical single method classifier architecture for deep learning.

[1]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[2]  Almabrok E. Essa,et al.  A Leaf Recognition Approach to Plant Classification Using Machine Learning , 2018, NAECON 2018 - IEEE National Aerospace and Electronics Conference.

[3]  Vijayan K. Asari,et al.  Histogram of Oriented Phase and Gradient (HOPG) Descriptor for Improved Pedestrian Detection , 2016 .

[4]  Russell C. Hardie,et al.  Skin Lesion Segmentation and Classification for ISIC 2018 by Combining Deep CNN and Handcrafted Features , 2019, ArXiv.

[5]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

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

[7]  Alain Pitiot,et al.  Fusing fine-tuned deep features for skin lesion classification , 2019, Comput. Medical Imaging Graph..

[8]  Redha Ali,et al.  Fused Deep Convolutional Neural Networks Based on Voting Approach for Efficient Object Classification , 2019, 2019 IEEE National Aerospace and Electronics Conference (NAECON).

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

[10]  Russell C. Hardie,et al.  Skin Lesion Segmentation and Classification for ISIC 2018 Using Traditional Classifiers with Hand-Crafted Features , 2018, ArXiv.

[11]  Youngjin Yoo,et al.  Modeling the Variability in Brain Morphology and Lesion Distribution in Multiple Sclerosis by Deep Learning , 2014, MICCAI.

[12]  J. Hornaday,et al.  Cancer Facts & Figures 2004 , 2004 .

[13]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[14]  Nguyen Hong Quang,et al.  Automatic skin lesion analysis towards melanoma detection , 2017, 2017 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES).

[15]  Hussin K. Ragb,et al.  Ensemble Lung Segmentation System Using Deep Neural Networks , 2020, 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

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

[17]  S. Menzies,et al.  Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta‐analysis of studies performed in a clinical setting , 2008, The British journal of dermatology.

[18]  Hussin K. Ragb,et al.  Deep Convolutional Neural Network Ensemble for Improved Malaria Parasite Detection , 2020, 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[19]  Temesguen Messay,et al.  A new computationally efficient CAD system for pulmonary nodule detection in CT imagery , 2010, Medical Image Anal..

[20]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[21]  H. Kittler,et al.  Diagnostic accuracy of dermoscopy. , 2002, The Lancet. Oncology.

[22]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Muhammad Imran Razzak,et al.  Deep Learning for Medical Image Processing: Overview, Challenges and Future , 2017, ArXiv.

[24]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

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

[26]  Redha Ali,et al.  Convolutional Neural Network for Classification of Histopathology Images for Breast Cancer Detection , 2019, 2019 IEEE National Aerospace and Electronics Conference (NAECON).

[27]  A. Kopf,et al.  Early detection of malignant melanoma: The role of physician examination and self‐examination of the skin , 1985, CA: a cancer journal for clinicians.

[28]  Russell C. Hardie,et al.  Deep Learning Ensemble Methods for Skin Lesion Analysis towards Melanoma Detection , 2019, 2019 IEEE National Aerospace and Electronics Conference (NAECON).

[29]  Vijayan K. Asari,et al.  Multi-feature fusion and PCA based approach for efficient human detection , 2016, 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[30]  Vijayan K. Asari,et al.  Histogram of oriented phase (HOP): a new descriptor based on phase congruency , 2016, Commercial + Scientific Sensing and Imaging.