Abstract
The deadliest form of skin lesion is known as melanoma. Detection of melanoma at earlier stages significantly raises the rate of survival. Nevertheless, the precise detection of melanoma is very challenging for reasons like lower contrast among skin and lesion, visual similarity among non-melanoma and melanoma lesions, etc. This work presents a new melanoma detection approach, which is comprised of 3 foremost stages like: segmentation, feature extraction and detection. Beginning with segmentation, a new algorithm called the Self Adaptive Sea Lion Algorithm (SA-SLnO) is used to improve the K-means clustering model’s initial centroids in a way that maximizes performance. Here, the multi-objective considerations of intensity diverse centroid, geographical map, and frequency of occurrence, respectively, are used to carry out the best selection. Further, from the segmented images, the texture features were extracted, and they are subjected to “Deep Belief Network (DBN)” for melanoma detection. Eventually, the supremacy of the presented model is confirmed over existing models in terms of various measures.
Similar content being viewed by others
Data availability
No new data were generated or analysed in support of this research.
Abbreviations
- CNN:
-
Convolutional Neural Network
- DCNN:
-
Deep Convolutional Neural Network
- DBN:
-
Deep Belief Network
- FDR:
-
False Discovery Rate
- FNR:
-
False Negative Rate
- FPR:
-
False Positive Rate
- GLRM:
-
Gray Level Run-Length Matrix
- GLCM:
-
Gray-Level Co-Occurrence Matrix
- HoG:
-
Histogram of Gradients
- HoL:
-
Histogram of Lines
- LANM:
-
Lion Algorithm with New Mating Process
- LVP:
-
Local Vector Pattern
- LBP:
-
Local Binary Pattern
- MLP:
-
Multi-Layer Perceptron
- MCC:
-
Matthews Correlation Coefficient
- MI:
-
Mutual Information
- NN:
-
Neural Network
- NPV:
-
Negative Predictive Value
- NVLVP:
-
Neighborhood variant LVP
- PA-MSA:
-
Particle Assisted- Moth Search Algorithm
- PSO:
-
Particle Swarm Optimization
- SRM:
-
Statistical Region Merging
- SD:
-
Standard Deviation
- SVM:
-
Support Vector Machine
- SA-SLnO:
-
Self Adaptive Sea Lion Algorithm
- SMP:
-
Skin Magnifier with Polarized light
- WOA:
-
Whale Optimization Algorithm
References
Abuzaghleh O, Barkana BD, Faezipour M (2015) “Noninvasive Real-Time Automated Skin Lesion Analysis System for Melanoma Early Detection and Prevention", IEEE J Eng Health Med
Aima A, Sharma AK (2019) Predictive approach for melanoma skin cancer detection using CNN. In Proceedings of International Conference on Sustainable Computing in Science, Technology and Management (SUSCOM). Amity University Rajasthan, Jaipur-India
Alfed N, Khelifi F (2017) Bagged textural and color features for melanoma skin cancer detection in dermoscopic and standard images. Expert Syst Appl 9030:101–110
Bliznuks D, Bolocko K, Sisojevs A, Ayub K (2017) Towards the scalable cloud platform for non-invasive skin Cancer diagnostics. Procedia Comput Sci 104:468–476
Carrera C, Scope A, Dusza SW, Argenziano G, Marghoob AA (2017) “Clinical and dermoscopic characterization of pediatric and childhood melanomas. Multicenter study of 52 cases”, J Am Acad Dermatol, 9
Chen, K, Franko K, Sang R (2021) "Structured model pruning of convolutional networks on tensor processing units." arXiv preprint arXiv:2107.04191
Codella NCF et al (2017) Deep learning ensembles for melanoma recognition in dermoscopy images. IBM J Res Dev 61(4):5:1–5:15
Dascalu A, David EO (May 2019) Skin cancer detection by deep learning and sound analysis algorithms: a prospective clinical study of an elementary dermoscope. EBio Med 43:107–113
Do T et al (2018) Accessible melanoma detection using smartphones and Mobile image analysis. IEEE Trans Multimed 20(10):2849–2864
Ferris LK, Harkes JA, Gilbert B, Winger DG, Satyanarayanan M (2015) Computer-aided classification of melanocytic lesions using dermoscopic images. J Am Acad Dermatol 73(5):769–776
George A, Rajakumar BR (2013) APOGA: An Adaptive Population Pool Size based Genetic Algorithm. AASRI Procedia - 2013 AASRI Conf Intell Syst Control (ISC 2013) 4:288–296. https://doi.org/10.1016/j.aasri.2013.10.043
Harangi B (2018) Skin lesion classification with ensembles of deep convolutional neural networks. J Biomed Inform 86:25–32
Hussain AA, Themstrup L, Nürnberg BM (2016) GBE Jemec, “adjunct use of optical coherence tomography increases the detection of recurrent basal cell carcinoma over clinical and dermoscopic examination alone”. Photodiagn Photodyn Ther 14:178–184
Jadhav AR, Ghontale AG, Shrivastava VK (2018) Segmentation and Border Detection of Melanoma Lesions Using Convolutional Neural Network and SVM. Comput Intell Theor Appl Future Dir 1:97–108
Jaimes N, Marghoob AA, Rabinovitz H, Braun RP, Keir J (2015) Clinical and dermoscopic characteristics of melanomas on nonfacial chronically sun-damaged skin. J Am Acad Dermatol 72(6):1027–1035
Kasmi R, Mokrani K (2016) Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule. IET Image Processing 10(6):448–455
Loescher LJ, Monika J, Peter Soyer H, Shea K, Curiel-Lewandrowski C (2013) Advances in skin Cancer early detection and diagnosis. Semin Oncol Nurs 29(3):170–181
Mahbod A, Schaefer G, Ellinger I, Ecker R, Wang C (2019) Fusing fine-tuned deep features for skin lesion classification. Comput Med Imaging Graph 71:19–29
Marchetti MA, Codella NCF, Dusza SW, Gutman DA (2017) Results of the 2016 international skin imaging collaboration international symposium on biomedical imaging challenge: comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images. J Am Acad Dermatol 78(2):270–277
Masadeh R, Mahafzah B, Sharieh A (2019) Sea Lion Optimization Algorithm. Int J Adv Comput Sci Appl 10:388–395
Mehta P, Shah B (2016) Review on techniques and steps of computer aided skin Cancer diagnosis. Procedia Comput Sci 85:309–316
Meshram, A, Gade A, Dutonde A (2022) An AutomaticSkin Melanoma Detection Based on Convolution Neural Network. No. 8350. EasyChair
Mukherjee S. Adhikari A, Roy M (2018) "Malignant melanoma detection using multi layer perceptron with optimized network parameter selection by PSO",Contemporary Adv Innov Appl Inf Technol, pp. 101–109
Niukkanen A, Arponen O, Nykänen A, Masarwah A, Sutela A, Liimatainen T (2018) Ritva Vanninen & Mazen Sudah, Quantitative Volumetric K-Means Cluster Segmentation of Fibroglandular Tissue and Skin in Breast MRI. J Digit Imaging 31:425–434
Oliveira RB, Pereira AS, Tavares JMRS (2017) Skin lesion computational diagnosis of dermoscopic images: ensemble models based on input feature manipulation. Comput Methods Prog Biomed 149:43–53
Pennisi A, Bloisi DD, Nardi D (2016) Anna Rita Giampetruzzi, Antonio Facchiano, “skin lesion image segmentation using Delaunay triangulation for melanoma detection”. Comput Med Imaging Graph 52:89–103
Poluru RK, Lokesh Kumar R (2019) Enhancement of ATC by optimizing TCSC configuration using adaptive moth flame optimization algorithm. J Comput Mech Power Syst Control 2(3):1–9
Properties of variance, from (2020) https://en.wikipedia.org/wiki/Qualitative_variation, Access Date:2020-05-13
Punal M (2016) Arabi, Gayatri Joshi, N. Vamsha Deepa,"performance evaluation of GLCM and pixel intensity matrix for skin texture analysis". Perspect Sci 8:203–206
Rajakumar BR (2013) Impact of Static and Adaptive Mutation Techniques on Genetic Algorithm. Int J Hybrid Intell Syst 10(1):11–22. https://doi.org/10.3233/HIS-120161
Rajakumar BR (2013) Static and Adaptive Mutation Techniques for Genetic algorithm: A Systematic Comparative Analysis. Int J Comput Sci Eng 8(2):180–193. https://doi.org/10.1504/IJCSE.2013.053087
Rajakumar BR, George A (2012) "A New Adaptive Mutation Technique for Genetic Algorithm", In proceedings of IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pages: 1–7, December 18–20, Coimbatore, India, https://doi.org/10.1109/ICCIC.2012.6510293.
Srinivasan, Kathiravan, Vishal Sharma, Nalin D Jayakody K, Vincent DR (2018) "D-ConvNet: deep learning model for enhancement of brain MR images." in basic & Clinical Pharmacology & Toxicology, vol. 124, pp. 3–4. 111 RIVER ST, HOBOKEN 07030–5774, NJ USA: WILEY
Sukanya (2019) “Deep Learning based Melanoma Detection with Optimized Features via Hybrid Algorithm”, in communication
Sukanya (n.d.) "A Novel Melanoma Detection Model: Adapted K-Means Clustering based Segmentation Process", In comunication
Swamy SM, Rajakumar BR, Valarmathi IR (2013) Design of hybrid wind and photovoltaic power system using opposition-based genetic algorithm with cauchy mutation. Cauchy Mutation 2013:504–510
Tan TY, Zhang L, Neoh SC, Lim CP (2018) Intelligent skin cancer detection using enhanced particle swarm optimization. Knowl-Based Syst 158:1–135
Tan TY, Zhang L, Lim CP (2019) Intelligent skin cancer diagnosis using improved particle swarm optimization and deep learning models. Appl Soft Comput 84:105725
Thomas R, Rangachar MJS (2018) Hybrid optimization based DBN for face recognition using low-resolution images. Multimed Res 1(1):33–43
Wagh MB, Gomathi N (2019) Improved GWO-CS algorithm-based optimal routing strategy in VANET. J Network Commun Syst 2(1):34–42
Wang HZ, Wang GB, Li GQ, Peng JC, Liu YT (2016) Deep belief network based deterministic and probabilistic wind speed forecasting approach. Appl Energy 182:80–93
Xie F, Yang J, Liu J, Jiang Z, Wang Y (2020) Skin lesion segmentation using high-resolution convolutional neural network. Comput Methods Programs Biomed 186:Article 105241
Yang S, Byungho O, Hahm S, Chung K-Y, Lee B-U (2017) Ridge and furrow pattern classification for acral lentiginous melanoma using dermoscopic images. Biomed Signal Process Control 32:90–96
Yuan Y, Chao M, Lo YC (2017) Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance. IEEE Trans Med Imaging 36(9):1876–1886
Zanddizari H, Nguyen N, Zeinali B, Chang JM (2021) A new preprocessing approach to improve the performance of CNN-based skin lesion classification. Med Biol Eng Comput 59(5):1123–1131
Zhang N, Cai Y-X, Wang Y-Y, Tian Y-T, Badami B (2020) Skin cancer diagnosis based on optimized convolutional neural network. Artif Intell Med 102:101756
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sukanya, S.T., Jerine, S. Skin lesion analysis towards melanoma detection using optimized deep learning network. Multimed Tools Appl 82, 27795–27817 (2023). https://doi.org/10.1007/s11042-023-14454-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14454-6