Skin Cancer Disease Detection Using Transfer Learning Technique
Source abstract
Abstract
Melanoma is a fatal type of skin cancer; the fury spread results in a high fatality rate when the malignancy is not treated at an initial stage. The patients’ lives can be saved by accurately detecting skin cancer at an initial stage. A quick and precise diagnosis might help increase the patient’s survival rate. It necessitates the development of a computer-assisted diagnostic support system. This research proposes a novel deep transfer learning model for melanoma classification using MobileNetV2. The MobileNetV2 is a deep convolutional neural network that classifies the sample skin lesions as malignant or benign. The performance of the proposed deep learning model is evaluated using the ISIC 2020 dataset. The dataset contains less than 2% malignant samples, raising the class imbalance. Various data augmentation techniques were applied to tackle the class imbalance issue and add diversity to the dataset. The experimental results demonstrate that the proposed deep learning technique outperforms state-of-the-art deep learning techniques in terms of accuracy and computational cost.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Cutaneous Melanoma Detection and Management · AI in cancer detection · Digital Imaging for Blood Diseases
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of CS&SE, Islamic International University, Islamabad 44000, Pakistan
Information Services, University of Okara, Renala Khurd 56130, Pakistan
Department of CS, University of Okara, Renala Khurd 56130, Pakistan
MLC Lab, University of Okara, Renala Khurd 56130, Pakistan
Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass 52571, Qassim, Saudi Arabia
References (75)
Show source-provided references
1. Factors, R. (2022, March 02). Basal and Squamous Cell Skin Cancer Causes, Risk Factors, and Prevention. Available online: https://www.cancer.org/content/dam/CRC/PDF/Public/8819.00.pdf.
2. Skin cancer epidemiology, detection, and management
3. Ultraviolet light and skin cancer in athletes10.1177/1941738109338923 ↗
4. (2022, May 22). Skin Cancer. Available online: https://www.aad.org/media/stats-skin-cancer.
5. (2015). Incidence estimate of nonmelanoma skin cancer (keratinocyte carcinomas) in the US population, 2012. JAMA Dermatol., 151, 1081–1086.10.1001/jamadermatol.2015.1187 ↗
6. The growing burden of invasive melanoma: Projections of incidence rates and numbers of new cases in six susceptible populations through 203110.1016/j.jid.2016.01.035 ↗
7. Melanoma classification on dermoscopy images using a neural network ensemble model10.1109/TMI.2016.2633551 ↗
8. Segmentation and classification of melanoma and benign skin lesions10.1016/j.ijleo.2017.04.084 ↗
9. (2022, May 22). Cancer Stat Facts: Melanoma of the Skin, Available online: https://seer.cancer.gov/statfacts/html/melan.html.
10. (2022, May 22). Melanoma: Statistics. Available online: https://www.cancer.net/cancer-types/melanoma/statistics.
11. Biopsy guided by dermoscopy in cutaneous pigmented lesion-case report10.1590/S0365-05962013000100020 ↗
12. Dermoscopy of melanoma and non-melanoma skin cancers10.3389/fmed.2019.00180 ↗
13. Melanoma staging: Evidence-based changes in the American Joint Committee on Cancer eighth edition cancer staging manual10.3322/caac.21409 ↗
14. Dermoscopy versus skin biopsy in diagnosis of suspicious skin lesions10.4103/AZMJ.AZMJ_67_17 ↗
15. Bajwa, M.N., Muta, K., Malik, M.I., Siddiqui, S.A., Braun, S.A., Homey, B., Dengel, A., and Ahmed, S. (2020). Computer-aided diagnosis of skin diseases using deep neural networks. Appl. Sci., 10.10.3390/app10072488 ↗
16. Pattern analysis, not simplified algorithms, is the most reliable method for teaching dermoscopy for melanoma diagnosis to residents in dermatology10.1046/j.1365-2133.2003.05023.x ↗
17. Validity and reliability of dermoscopic criteria used to differentiate nevi from melanoma: A web-based international dermoscopy society study10.1001/jamadermatol.2016.0624 ↗
18. Gutman, D., Codella, N.C., Celebi, E., Helba, B., Marchetti, M., Mishra, N., and Halpern, A. (2016). Skin lesion analysis toward melanoma detection: A challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv.
19. Epiluminescence microscopy-based classification of pigmented skin lesions using computerized image analysis and an artificial neural network10.1097/00008390-199806000-00009 ↗
20. Melanoma computer-aided diagnosis: Reliability and feasibility study10.1158/1078-0432.CCR-03-0039 ↗
21. Artificial intelligence in power systems
22. Sivadasan, B. (2018, January 25). Application of artificial intelligence in electrical engineering. Proceedings of the National Conference on Emerging Research Trend in Electrical and Electronics Engineering (ERTEE 2018), Kalady, Kerala.
23. Xu, Y., Ahokangas, P., Louis, J.N., and Pongrácz, E. (2019). Electricity market empowered by artificial intelligence: A platform approach. Energies, 12.10.3390/en12214128 ↗
24. Machine learning applications in cancer prognosis and prediction10.1016/j.csbj.2014.11.005 ↗
25. Applications of machine learning in cancer prediction and prognosis10.1177/117693510600200030 ↗
26. Sohail, M., Ali, G., Rashid, J., Ahmad, I., Almotiri, S.H., AlGhamdi, M.A., Nagra, A.A., and Masood, K. (2021). Racial Identity-Aware Facial Expression Recognition Using Deep Convolutional Neural Networks. Appl. Sci., 12.10.3390/app12010088 ↗
27. Rashid, J., Khan, I., Ali, G., Almotiri, S.H., AlGhamdi, M.A., and Masood, K. (2021). Multi-Level Deep Learning Model for Potato Leaf Disease Recognition. Electronics, 10.10.3390/electronics10172064 ↗
28. A survey of deep learning and its applications: A new paradigm to machine learning10.1007/s11831-019-09344-w ↗
29. Hordri, N.F., Yuhaniz, S.S., and Shamsuddin, S.M. (2016, January 12). Deep learning and its applications: A review. Proceedings of the Conference on Postgraduate Annual Research on Informatics Seminar, Kuala Lumpur, Malaysia.
30. Deep learning applications and challenges in big data analytics10.1186/s40537-014-0007-7 ↗
31. Deep learning10.1038/nature14539 ↗
32. Skin cancer classification using convolutional neural networks: Systematic review10.2196/11936 ↗
33. The possibility of deep learning-based, computer-aided skin tumor classifiers10.3389/fmed.2019.00191 ↗
34. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
35. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
36. Kong, B., Sun, S., Wang, X., Song, Q., and Zhang, S. (2018, January 16–20). Invasive cancer detection utilizing compressed convolutional neural network and transfer learning. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Granada, Spain.10.1007/978-3-030-00934-2_18 ↗
37. Wu, S., Gao, Z., Liu, Z., Luo, J., Zhang, H., and Li, S. (2018, January 16–20). Direct reconstruction of ultrasound elastography using an end-to-end deep neural network. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Granada, Spain.10.1007/978-3-030-00928-1_43 ↗
38. Codella, N., Cai, J., Abedini, M., Garnavi, R., Halpern, A., and Smith, J.R. (2015, January 11). Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images. Proceedings of the International Workshop on Machine Learning in Medical Imaging, Lille, France.10.1007/978-3-319-24888-2_15 ↗
39. Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists10.1093/annonc/mdy166 ↗
40. Kawahara, J., and Hamarneh, G. (2016, January 17). Multi-resolution-tract CNN with hybrid pretrained and skin-lesion trained layers. Proceedings of the International Workshop on Machine Learning in Medical Imaging, Athens, Greece.10.1007/978-3-319-47157-0_20 ↗
41. Li, Y., and Shen, L. (2018). Skin lesion analysis towards melanoma detection using deep learning network. Sensors, 18.10.3390/s18020556 ↗
42. Menegola, A., Fornaciali, M., Pires, R., Bittencourt, F.V., Avila, S., and Valle, E. (2017, January 18–21). Knowledge transfer for melanoma screening with deep learning. Proceedings of the 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017), Melbourne, Australia.10.1109/ISBI.2017.7950523 ↗
43. MED-NODE: A computer-assisted melanoma diagnosis system using non-dermoscopic images10.1016/j.eswa.2015.04.034 ↗
44. Lynn, N.C., and War, N. (2019, January 6–7). Melanoma classification on dermoscopy skin images using bag tree ensemble classifier. Proceedings of the 2019 International Conference on Advanced Information Technologies (ICAIT), Yangon, Myanmar.10.1109/AITC.2019.8920908 ↗
45. Mukherjee, S., Adhikari, A., and Roy, M. (2019). Melanoma identification using MLP with parameter selected by metaheuristic algorithms. Intelligent Innovations in Multimedia Data Engineering and Management, IGI Global.10.4018/978-1-5225-7107-0.ch010 ↗
46. Classification of melanoma and nevus in digital images for diagnosis of skin cancer10.1109/ACCESS.2019.2926837 ↗
47. Efficient fusion of handcrafted and pre-trained CNNs features to classify melanoma skin cancer10.1007/s11042-020-09637-4 ↗
48. Classification of melanoma based on feature similarity measurement for codebook learning in the bag-of-features model10.1016/j.bspc.2019.02.018 ↗
49. DermoDeep-A classification of melanoma-nevus skin lesions using multi-feature fusion of visual features and deep neural network10.1007/s11042-019-7652-y ↗
50. Classification of Dermoscopic skin cancer images using color and hybrid texture features
51. Pham, T.C., Luong, C.M., Visani, M., and Hoang, V.D. (2018). Deep CNN and data augmentation for skin lesion classification. Asian Conference on Intelligent Information and Database Systems, Springer.10.1007/978-3-319-75420-8_54 ↗
52. Automated melanoma recognition in dermoscopy images via very deep residual networks10.1109/TMI.2016.2642839 ↗
53. Melanoma recognition in dermoscopy images via aggregated deep convolutional features10.1109/TBME.2018.2866166 ↗
54. Rokhana, R., Herulambang, W., and Indraswari, R. (2020, January 24–26). Deep convolutional neural network for melanoma image classification. Proceedings of the 2020 International Electronics Symposium (IES), Marrakech, Morocco.10.1109/IES50839.2020.9231676 ↗
55. Liberman, G., Acevedo, D., and Mejail, M. (2018). Classification of melanoma images with fisher vectors and deep learning. Iberoamerican Congress on Pattern Recognition, Springer.10.1007/978-3-030-13469-3_85 ↗
56. Classifying melanoma skin lesions using convolutional spiking neural networks with unsupervised stdp learning rule10.1109/ACCESS.2020.2998098 ↗
57. Skin melanoma classification using ROI and data augmentation with deep convolutional neural networks10.1007/s11042-020-09067-2 ↗
58. Mukherjee, S., Adhikari, A., and Roy, M. (2019). Malignant melanoma classification using cross-platform dataset with deep learning CNN architecture. Recent Trends in Signal and Image Processing, Springer.10.1007/978-981-13-6783-0_4 ↗
59. Esteva, A., Kuprel, B., and Thrun, S. (2015). Deep Networks for Early Stage Skin Disease and Skin Cancer Classification, Stanford University.
60. Çakmak, M., and Tenekecı, M.E. (2021, January 9–11). Melanoma detection from dermoscopy images using Nasnet Mobile with Transfer Learning. Proceedings of the 2021 29th Signal Processing and Communications Applications Conference (SIU), Istanbul, Turkey.10.1109/SIU53274.2021.9477985 ↗
61. Deep neural networks are superior to dermatologists in melanoma image classification10.1016/j.ejca.2019.05.023 ↗
62. Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm10.1016/j.jid.2018.01.028 ↗
63. Hosny, K.M., Kassem, M.A., and Foaud, M.M. (2019). Classification of skin lesions using transfer learning and augmentation with Alex-net. PLoS ONE, 14.10.1371/journal.pone.0217293 ↗
64. Dermatologist-level classification of skin cancer with deep neural networks10.1038/nature21056 ↗
65. Machine learning for predictive modelling based on small data in biomedical engineering10.1016/j.ifacol.2015.10.185 ↗
66. Machine learning: The new’big thing’for competitive advantage10.1504/IJKEDM.2018.095523 ↗
67. Deep learning and process understanding for data-driven Earth system science10.1038/s41586-019-0912-1 ↗
68. Sarvepalli, S.K. (2015). Deep Learning in Neural Networks: The Science Behind an Artificial Brain, Liverpool Hope University.
69. (2022, March 05). The ISIC 2020 Challenge Dataset. Available online: https://challenge2020.isic-archive.com/.
70. (2022, March 05). The ISIC 2019 Challenge Dataset. Available online: https://challenge2019.isic-archive.com/.
71. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18–23). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
72. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18–23). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00716 ↗
73. Chollet, F. (2017, January 21–26). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.195 ↗
74. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.
75. Skin cancer disease images classification using deep learning solutions Multimedia Tools and Applications10.1007/s11042-021-10952-7 ↗