Performance Improvement of Melanoma Detection Using a Multi-Network System Based on Decision Fusion
Source abstract
Abstract
The incidence of melanoma cases continues to rise, underscoring the critical need for early detection and treatment. Recent studies highlight the significance of deep learning in melanoma detection, leading to improved accuracy. The field of computer-assisted detection is extensively explored along all lines, especially in the medical industry, as the benefit in this field is to save hu-man lives. In this domain, this direction must be maximally exploited and introduced into routine controls to improve patient prognosis, disease prevention, reduce treatment costs, improve population management, and improve patient empowerment. All these new aspects were taken into consideration to implement an EHR system with an automated melanoma detection system. The first step, as presented in this paper, is to build a system based on the fusion of decisions from multiple neural networks, such as DarkNet-53, DenseNet-201, GoogLeNet, Inception-V3, InceptionResNet-V2, ResNet-50, ResNet-101, and compare this classifier with four other applications: Google Teachable Machine, Microsoft Azure Machine Learning, Google Vertex AI, and SalesForce Einstein Vision based on the F1 score for further integration into an EHR platform. We trained all models on two databases, ISIC 2020 and DermIS, to also test their adaptability to a wide range of images. Comparisons with state-of-the-art research and existing applications confirm the promising performance of the proposed system.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Cutaneous Melanoma Detection and Management · AI in cancer detection · Cell Image Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Automatic Control and Computers, University Politehnica of Bucharest, 060042 Bucharest, Romania
Faculty of Electronics and Telecommunications, University Politehnica of Bucharest, 060042 Bucharest, Romania
References (88)
Show source-provided references
1. Intralesional Cancer Immunotherapies10.1016/j.hoc.2018.12.009 ↗
2. Melanoma: Molecular Pathogenesis and Therapeutic Management
3. Strashilov, S., and Yordanov, A. (2021). Aetiology and Pathogenesis of Cutaneous Melanoma: Current Concepts and Advances. Int. J. Mol. Sci., 22.10.3390/ijms22126395 ↗
4. National Cancer Institute (2020, February 02). Melanoma Treatment for Health Professionals (PDQ), Available online: www.cancer.gov/types/skin/hp/melanoma-treatment-pdq.
5. Stewart, B.W., and Wild, C.P. (2014). World Cancer Report 2014, World Health Organization, International Agency for Research on Cancer, IARC Publications.
6. El-Khatib, H., Popescu, D., and Ichim, L. (2020). Deep Learning–Based Methods for Automatic Diagnosis of Skin Lesions. Sensors, 20.10.3390/s20061753 ↗
7. Uveal melanoma incidence trends in Canada: A national comprehensive population-based study
8. Cancer statistics, 202310.3322/caac.21763 ↗
9. Ward, W.H., and Farma, J.M. (2018). Cutaneous Melanoma: Etiology and Therapy [Internet], Codon Publications.10.15586/codon.cutaneousmelanoma.2017 ↗
10. Machine learning approach in melanoma cancer stage detection
11. Koczkodaj, P., Sulkowska, U., Didkowska, J., Rutkowski, P., and Mańczuk, M. (2023). Melanoma Mortality Trends in 28 European Countries: A Retrospective Analysis for the Years 1960–2020. Cancers, 15.10.3390/cancers15051514 ↗
12. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries10.3322/caac.21660 ↗
13. Hospital-Based Study of Compliance with NCCN Guidelines and Predictive Factors of Sentinel Lymph Node Biopsy in the Setting of Thin Melanoma Using the National Cancer Database10.1177/000313481808400518 ↗
14. Analysis of prognostic factors for melanoma patients
15. Optimization of the Convolutional Neural Networks for Automatic Detection of Skin Cancer10.1515/med-2020-0006 ↗
16. Automatic diagnosis of skin diseases using convolution neural network10.1016/j.micpro.2020.103074 ↗
17. Automatic diagnosis of melanoma using hyperspectral data and GoogLeNet10.1111/srt.12891 ↗
18. Convolutional Neural Network (CNN) for Automatic Skin Cancer Classification System10.1088/1757-899X/982/1/012005 ↗
19. Augmented decision-making for acral lentiginous melanoma detection using deep convolutional neural networks10.1111/jdv.16185 ↗
20. Malignant Melanoma Classification Using Deep Learning: Datasets, Performance Measurements, Challenges and Opportunities10.1109/ACCESS.2020.3001507 ↗
21. Jain, V., and Chatterjee, J. (2020). Machine Learning with Health Care Perspective, Springer. Learning and Analytics in Intelligent Systems.10.1007/978-3-030-40850-3 ↗
22. Melanoma recognition by a deep learning convolutional neural network—Performance in different melanoma subtypes and localisations10.1016/j.ejca.2019.11.020 ↗
23. Tucker, A., Henriques Abreu, P., Cardoso, J., Pereira Rodrigues, P., and Riaño, D. (2021). Artificial Intelligence in Medicine, Springer. AIME 2021. Lecture Notes in Computer Science.10.1007/978-3-030-77211-6 ↗
24. A Deep Learning Model to Predict Knee Osteoarthritis Based on Nonimage Longitudinal Medical Record10.2147/JMDH.S325179 ↗
25. A cnn framework for classification of melanoma and benign lesions on dermatoscopic skin images
26. A new preprocessing approach to improve the performance of CNN-based skin lesion classification10.1007/s11517-021-02355-5 ↗
27. Zhang, R. (2021, January 15–17). Melanoma Detection Using Convolutional Neural Network. Proceedings of the 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE), Guangzhou, China.10.1109/ICCECE51280.2021.9342142 ↗
28. Alwakid, G., Gouda, W., Humayun, M., and Sama, N.U. (2022). Melanoma Detection Using Deep Learning-Based Classifications. Healthcare, 10.10.3390/healthcare10122481 ↗
29. Melanoma classification using light-Fields with morlet scattering transform and CNN: Surface depth as a valuable tool to increase detection rate10.1016/j.media.2021.102254 ↗
30. Bhimavarapu, U., and Battineni, G. (2022). Skin Lesion Analysis for Melanoma Detection Using the Novel Deep Learning Model Fuzzy GC-SCNN. Healthcare, 10.10.3390/healthcare10050962 ↗
31. Melanoma Detection Using a Deep Learning Approach10.33411/IJIST/2022040117 ↗
32. Melanoma Skin Cancer Classification based on CNN Deep Learning Algorithms10.11113/mjfas.v19n3.2900 ↗
33. Olayah, F., Senan, E.M., Ahmed, I.A., and Awaji, B. (2023). AI Techniques of Dermoscopy Image Analysis for the Early Detection of Skin Lesions Based on Combined CNN Features. Diagnostics, 13.10.3390/diagnostics13071314 ↗
34. Early and accurate detection of melanoma skin cancer using hybrid level set approach10.3389/fphys.2022.965630 ↗
35. Skin Cancer Image Detection and Classification by CNN based Ensemble Learning
36. Analysis of the ISIC image datasets: Usage, benchmarks and recommendations10.1016/j.media.2021.102305 ↗
37. Popescu, D., El-Khatib, M., El-Khatib, H., and Ichim, L. (2022). New Trends in Melanoma Detection Using Neural Networks: A Systematic Review. Sensors, 22.10.3390/s22020496 ↗
38. PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones10.1016/j.dib.2020.106221 ↗
39. A patient-centric dataset of images and metadata for identifying melanomas using clinical context10.1038/s41597-021-00815-z ↗
40. (2023, July 09). International Skin Imaging Collaboration: 2020. Available online: https://www.isic-archive.com.
41. Diepgen, T.L., and Yihune, G. (2023, July 09). Dermatology Information System—Dermis. Available online: https://www.dermis.net/dermisroot/en/home/index.htm.
42. ABCD rule and pre-trained CNNs for melanoma diagnosis10.1007/s11042-018-6404-8 ↗
43. Analysis of Various Image Preprocessing Techniques for Denoising of Flower Images
44. A Study on Various Image Processing Techniques
45. Optimizing the color-to-grayscale conversion for image classification10.1007/s11760-015-0828-7 ↗
46. Dullrazor®: A software approach to hair removal from images10.1016/S0010-4825(97)00020-6 ↗
47. Overview of Advanced Computer Vision Systems for Skin Lesions Characterization10.1109/TITB.2009.2017529 ↗
48. Rondón, C.V.N., Carvajal, D.A.C., Delgado, B.M., Casadiego, S.A.C., and Ibarra, D.G. (2021, January 13–15). Body hair noise suppression in skin lesions by differential operator and maximum variance threshold between classes. Proceedings of the 2021 IEEE 2nd International Congress of Biomedical Engineering and Bioengineering (CI-IB&BI), Bogota, Colombia.
49. Bibiloni, P., González-Hidalgo, M., and Massanet, S. (2017, January 21–24). Skin Hair Removal in Dermoscopic Images Using Soft Color Morphology. Proceedings of the Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria. Proceedings 16.10.1007/978-3-319-59758-4_37 ↗
50. Maglogiannis, I., and Delibasis, K. (2015, January 25–29). Hair removal on dermoscopy images. Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy.10.1109/EMBC.2015.7319013 ↗
51. E-shaver: An improved DullRazor® for digitally removing dark and light-colored hairs in dermoscopic images10.1016/j.compbiomed.2011.01.003 ↗
52. Koehoorn, J., Sobiecki, A.C., Boda, D., Diaconeasa, A., Doshi, S., Paisey, S., Jalba, A., and Telea, A. (2015, January 27–29). Automated Digital Hair Removal by Threshold Decomposition and Morphological Analysis. Proceedings of the Mathematical Morphology and Its Applications to Signal and Image Processing: 12th International Symposium, ISMM 2015, Reykjavik, Iceland. Proceedings 12.10.1007/978-3-319-18720-4_2 ↗
53. (2023, July 09). Transfer Learning Using Pretrained Network—MATLAB & Simulink. Available online: mathworks.com.
54. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). ImageNet Classification with Deep Convolutional Neural Net-works. Adv. Neural Inf. Process. Syst., 25.
55. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
56. Redmon, J. (2023, July 09). Darknet: Open Source Neural Networks in C. Available online: https://pjreddie.com/darknet.
57. A Novel Image Classification Approach via Dense-MobileNet Models
58. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
59. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A., and Liu, W. (2015, January 7–12). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
60. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
61. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2016, January 12–17). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.10.1609/aaai.v31i1.11231 ↗
62. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
63. Chollet, F. (2017, January 21–26). Xception: Deep learning with depthwise separable convolutions. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.195 ↗
64. A comparative study of multiple neural network for detection of COVID-19 on chest X-ray10.1186/s13634-021-00755-1 ↗
65. (2023, July 09). Teachable Machine. Available online: https://teachablemachine.withgoogle.com.
66. (2023, July 09). Algorithm & Component Reference for Azure Machine Learning Designer. Available online: https://learn.microsoft.com/en-us/azure/machine-learning/component-reference/component-reference?view=azureml-api-2.
67. Innovate Faster with Enterprise-Ready Generative AI (2023, July 09). Available online: https://cloud.google.com/vertex-ai.
68. (2023, July 09). What Is a REST API?. Available online: https://www.redhat.com/en/topics/api/what-is-a-rest-api.
69. (2023, July 09). No-Fuss AI for Your App: Meet Salesforce Einstein. Available online: https://www.toptal.com/salesforce/easy-ai-cloud-salesforce-einstein.
70. (2023, July 09). Giving Vertex AI, the New Unified ML Platform on Google Cloud, a Spin. Available online: https://towardsdatascience.com/giving-vertex-ai-the-new-unified-ml-platform-on-google-cloud-a-spin-35e0f3852f25.
71. (2023, July 09). What Is a Salesforce Sandbox?. Available online: https://www.salesforceben.com/salesforce-sandbox/.
72. Shrivastava, M. (2017). Learning Salesforce Einstein, Packt Publishing Ltd.
73. (2021). Lars Malmqvist Architecting AI Solutions on Salesforce: Design Powerful and Accurate AI-Driven State-of-the-Art Solutions Tailor-Made for Modern Business Demands, Packt Publishing Ltd.
74. (2023, July 09). Einstein Vision and Language Model Builder: User Guide. Available online: https://quip.com/z6a4AlCUw8n3.
75. (2023, July 09). Salesforce AI Research. Available online: https://blog.salesforceairesearch.com/.
76. Dermatologist-level classification of skin cancer with deep neural networks10.1038/nature21056 ↗
77. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions10.1038/sdata.2018.161 ↗
78. Towards Automated Melanoma Screening: An Overview of Emerging Image Processing and Machine Learning Techniques
79. Codella, N.C., Gutman, D., Celebi, M.E., Helba, B., Marchetti, M.A., Dusza, S.W., Kalloo, A., Liopyris, K., Mishra, N., and Kittler, H. (2018). 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). arXiv.10.1109/ISBI.2018.8363547 ↗
80. Comparison of Segmentation Methods for Melanoma Diagnosis in Dermoscopy Images
81. Han, S.S., Park, G.H., Lim, W., Kim, M.S., Na, J.I., Park, I., and Chang, S.E. (2017). Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis databases by region-based convolutional deep neural network. PLoS ONE, 12.10.1371/journal.pone.0191493 ↗
82. Comparing artificial intelligence algorithms to 157 German dermatologists: The melanoma classification benchmark10.1016/j.ejca.2018.12.016 ↗
83. A Review on Evaluation Metrics for Data Classification Evaluations10.5121/ijdkp.2015.5201 ↗
84. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20–25). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
85. Kaur, R., GholamHosseini, H., Sinha, R., and Lindén, M. (2022). Melanoma Classification Using a Novel Deep Convolutional Neural Network with Dermoscopic Images. Sensors, 22.10.1186/s12880-022-00829-y ↗
86. Uddin, M.S., and Bansal, J.C. (2020, January 20–21). Skin Lesion Classification Using Convolutional Neural Network for Mela-noma Recognition. Proceedings of the International Joint Conference on Advances in Computational Intelligence, Birulia, Bangladesh. Algorithms for Intelligent Systems.
87. Rezaoana, N., Hossain, M.S., and Andersson, K. (2020, January 26–27). Detection and Classification of Skin Cancer by Using a Parallel CNN Model. Proceedings of the 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), Bhubaneswar, India.10.1109/WIECON-ECE52138.2020.9397987 ↗
88. Tahir, M., Naeem, A., Malik, H., Tanveer, J., Naqvi, R.A., and Lee, S.-W. (2023). DSCC_Net: Multi-Classification Deep Learning Models for Diagnosing of Skin Cancer Using Dermoscopic Images. Cancers, 15.10.3390/cancers15072179 ↗