CSG2341 Intelligent Systems
Repository of a CSG2341 Intelligent Systems group project by Mark Jamsek, Joshua Soto-Kitcher, and Jason Knox.
Group Set 2 Team 10 Proposal Report
Machine learning in dermoscopic diagnostics of malignant cutaneous neoplasms
Mark Jamsek, Joshua Soto-Kitcher, and Jason Knox
Abstract
Skin cancer is a fatal disease that impacts one million Australians every year.
Due to the inherent difficulty of accurately diagnosing skin lesions, and the critical
importance of early treatment, the purpose of this report is to review the literature
on machine learning enhanced diagnostics of cutaneous neoplasms. Initial research
found that convolutional neural networks produce the most accurate image classification
models, which led to further investigation into the binary classification models
developed with the AlexNet, ResNet, and VGGNet architectures that were employed in
various skin cancer detection projects. Further, with the problem of distinguishing
not only benign from malignant naevi but also melanocytic and non-melanocytic skin
cancers, additional research into the multiclass classification model implemented
with EfficientNet was also performed. Subsequent findings reveal that SoftMax and
Support Vector Machine (SVM) image classification functions were favoured, and
consistently produced models testing above 90% accuracy. Interestingly, these
results were irrespective of the dataset size. In addition, an on-device inference
application was reviewed, which highlighted both the challenges and prospects of
bringing this technology to mobile devices. As a final point, we propose a detailed
plan to design and develop a VGGNet convolutional neural network to classify images
of skin lesions from the PH2 and/or HAM10000 datasets using a SoftMax and/or
SVM classifier; with the secondary objective of researching the viability of adapting
this technology to mobile devices.
The full paper can be read here.
References
Journal Articles
Adegun, A. A., & Viriri, S. (2020). Deep Learning-Based System for Automatic Melanoma Detection. IEEE Access, 8, 7160–7172. https://doi.org/10.1109/ACCESS.2019.2962812
Dorj, U.-O., Lee, K.-K., Jae-Young, C., & Lee, M. (2018). The skin cancer classification using deep convolutional neural network. Multimedia Tools and Applications, 77(8), 9909–9924. https://doi.org/10.1007/s11042-018-5714-1
Gavrilov, D. A., Melerzanov, A. V., Shchelkunov, N. N., & Zakirov, E. I. (2019). Use of Neural Network-Based Deep Learning Techniques for the Diagnostics of Skin Diseases. Biomedical Engineering, 52(5), 348–352. https://doi.org/10.1007/s10527-019-09845-9
Goyal, M., Oakley, A., Bansal, P., Dancey, D., & Yap, M. H. (2020). Skin Lesion Segmentation in Dermoscopic Images With Ensemble Deep Learning Methods. In IEEE Access, 8, 4171–4181. https://doi.org/10.1109/ACCESS.2019.2960504
Naeem, A., Farooq, M. S., Khelifi, A. & Abid, A. (2020). Malignant Melanoma Classification Using Deep Learning: Datasets, Performance Measurements, Challenges and Opportunities. In IEEE Access, 8, 110575–110597. https://doi.org/10.1109/ACCESS.2020.3001507.
Putra, T. A., Rufaida, S. I., & Leu, J.-S. (2020). Enhanced Skin Condition Prediction Through Machine Learning Using Dynamic Training and Testing Augmentation. In IEEE Access, 8, 40536–40546. https://doi.org/10.1109/ACCESS.2020.2976045
Yap, J., Yolland, W., & Tschandl, P. (2018). Multimodal skin lesion classification using deep learning. Experimental Dermatology, 27(11), 1261–1267. https://doi.org/10.1111/exd.13777
Zhang, Q., Zhu, L., & Huang, D. (2019). High-Order Convolutional Neural Network Architecture for Predicting DNA-Protein Binding Sites. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 16(4), 1184–1192. https://doi.org/10.1109/TCBB.2018.2819660
Ozkan, I. A., & Koklu, M. (2017). Skin lesion classification using machine learning algorithms. International Journal of Intelligent Systems and Applications in Engineering, 5(4), 285–289. https://doi.org/10.18201/ijisae.2017534420
Alom, M. Z., Yakopcic, C., Hasan, M., Taha, T. M. & Asari, V. K. (2019). Recurrent residual U-Net for medical image segmentation. Journal of Medical Imaging, 6(1), 1–16. https://doi.org/10.1117/1.JMI.6.1.014006
Krizhevsky, A., Sutskever, I. & Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90. https://doi.org/10.1145/3065386
Premaladha, J. & Ravichandran, K. S. (2016). Novel approaches for diagnosing melanoma skin lesions through supervised and deep learning algorithms. Journal of Medical Systems, 40(4), 96. https://doi.org/10.1007/s10916-016-0460-2
Kumar, S. M., Kumar, J. R. & Gopalakrishnan, K. (2019). Skin cancer diagnostic using machine learning techniques-stationary wavelet transform and random forest classifier. International Journal of Innovative Technology and Exploring Engineering, 9(2), 4705–4708. https://doi.org/10.35940/ijitee.B9016.129219
Conference Papers
Chakraborty, S., Mali, K., Chatterjee, S., Anand, S., Basu, A., Banerjee, S., Das, M., & Bhattacharya, A. (2017). Image based Skin Disease Detection using Hybrid Neural Network coupled Bag-of-Features. In 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (pp. 242–246). IEEE. https://doi.org/10.1109/UEMCON.2017.8249038
Ge, Z., Demyanov, S., Chakravorty, R., Bowling, A., & Garnavi, R. (2017). Skin disease recognition using deep saliency features and multimodal learning of dermoscopy and clinical images. In M. Descoteaux, L. Maier-Hein, A. Franz, P. Jannin, D. Collins, & S. Duchesne (Eds.), Medical Image Computing and Computer Assisted Intervention — MICCAI 2017. Proceedings of the 20th International Conference (pp. 250-258). Springer. https://doi.org/10.1007/978-3-319-66179-7_29
He, X., Wang, S., Shi, S., Tang, Z., Wang, Y., Zhao, Z., Dai, J., Ni, R., Zhang X., Liu, X., Wu, Z., Yu, W., & Chu, X. (2019). Computer-Aided Clinical Skin Disease Diagnosis Using CNN and Object Detection Models. In 2019 IEEE International Conference on Big Data (pp. 4839–4844). IEEE. https://doi.org/10.1109/BigData47090.2019.9006528
Kaymak, S., Esmaili, P., & Serener, A. (2018). Deep Learning for Two-Step Classification of Malignant Pigmented Skin Lesions. In 2018 14th Symposium on Neural Networks and Applications (NEUREL), (pp. 1–6). https://doi.org/10.1109/NEUREL.2018.8587019.
Shahin, A. H., Kamal, A., & Elattar, M. A. (2018). Deep Ensemble Learning for Skin Lesion Classification from Dermoscopic Images. In 2018 9th Cairo International Biomedical Engineering Conference (CIBEC) (pp. 150-153). IEEE. https://doi.org/10.1109/CIBEC.2018.8641815 ECU library link of conference paper.
Yan, Y., Kawahara, J., & Hamarneh, G. (2019). Melanoma Recognition via Visual Attention. In A. C. S. Chung, J. C. Gee, P. A. Yushkevich, & S. Bao (Eds.), Information Processing in Medical Imaging: 26th International Conference, IPMI 2019 (pp. 793-804). Springer. https://doi.org/10.1007/978-3-030-20351-1
Yu, Z., Jiang, X., Wang, T., & Lei, B. (2017). Aggregating deep convolutional features for melanoma recognition in dermoscopy images. In Machine learning in medical imaging: 8th international workshop (pp. 238–246). https://doi.org/10.1007/978-3-319-67389-9_28
Fisher, R. B., Rees, J., & Bertrand, A. (2020). Classification of ten skin lesion classes: Hierarchical knn versus deep net. In Y. Zheng, B. M. Williams, & K. Chen (Eds.), Medical image understanding and analysis (pp. 86–98). Springer International Publishing.
Dai, X., Spasic ́, I., Meyer, B., Chapman, S. & Andres, F. (2019). Machine learning on mobile: An on-device inference app for skin cancer detection. Fourth International Conference on Fog and Mobile Edge Computing, 301–305. https://doi.org/10.1109/FMEC.2019.8795362
Harangi, B., Baran, A. & Hajdu, A. (2018). Classification of skin lesions using an ensemble of deep neural networks. 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2575–2578. https://doi.org/10.1109/EMBC.2018.8512800
Swain, D., Bijawe, S., Akolkar, P., Mahajani, M., Shinde, A. & Maladhari, P. (2020). Virtual dermoscopy using deep learning approach. In P. K. Mallick, P. K. Pattnaik, A. R. Panda & V. E. Balas (Eds.), Cognitive computing in human cognition: Perspectives and applications (pp. 61–71). Springer International Publishing. https://doi.org/10.1007/978-3-030-48118-6_6
Books
Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.
Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep Learning. The MIT Press.
Murphy, K. P. (2012). Machine Learning A Probabilistic Perspective. The MIT Press.
Negnevitsky, M. (2011). Artificial Intelligence A Guide to Intelligent Systems (3rd. ed.). Pearson Education Limited.
Patterson, J. & Gibson, A. (2017). Deep Learning A Practitioner’s Approach. O’Reilly Media, Inc.
Khan, S., Rahmani, H., Shah, S. & Bennamoun, M. (2018). A guide to convolutional neural networks for computer vision (G. Medioni & S. Dickinson, Eds.). Morgan & Claypool Publishers. https://doi.org/10.2200/S00822ED1V01Y201712COV015