RESEARCH ARTICLE
A novel hybrid artificial neural network technique for the early skin cancer diagnosis using color space conversions of original images
Salwan Tajjour,
Sonia Garg,
Shyam Singh Chandel,
Diksha Sharma,
Salwan Tajjour
Artificial Intelligence Research Group, Centre of Excellence in Energy Science and Technology, Shoolini University, Solan, India
Search for more papers by this authorSonia Garg
Yogananda School of Artificial Intelligence, Computer and Data Science, Shoolini University, Solan, India
Search for more papers by this authorCorresponding Author
Shyam Singh Chandel
Artificial Intelligence Research Group, Centre of Excellence in Energy Science and Technology, Shoolini University, Solan, India
Correspondence
Shyam Singh Chandel, Artificial Intelligence Research Group, Centre of Excellence in Energy Science and Technology, Shoolini University, Solan, 173212, India.
Email: [email protected]
Search for more papers by this authorDiksha Sharma
Yogananda School of Artificial Intelligence, Computer and Data Science, Shoolini University, Solan, India
Search for more papers by this authorSalwan Tajjour,
Sonia Garg,
Shyam Singh Chandel,
Diksha Sharma,
Salwan Tajjour
Artificial Intelligence Research Group, Centre of Excellence in Energy Science and Technology, Shoolini University, Solan, India
Search for more papers by this authorSonia Garg
Yogananda School of Artificial Intelligence, Computer and Data Science, Shoolini University, Solan, India
Search for more papers by this authorCorresponding Author
Shyam Singh Chandel
Artificial Intelligence Research Group, Centre of Excellence in Energy Science and Technology, Shoolini University, Solan, India
Correspondence
Shyam Singh Chandel, Artificial Intelligence Research Group, Centre of Excellence in Energy Science and Technology, Shoolini University, Solan, 173212, India.
Email: [email protected]
Search for more papers by this authorDiksha Sharma
Yogananda School of Artificial Intelligence, Computer and Data Science, Shoolini University, Solan, India
Search for more papers by this authorAbstract
In this study, an innovative hybrid machine learning-technique is used for the early skin cancer diagnosis fusing Convolutional Neural Network and Multilayer Perceptron to analyze images and information related to the skin cancer. This information is extracted manually after applying different color space conversions on the original images for better screening of the lesions. The proposed architecture is compared with standalone architecture in addition to some other techniques by commonly used evaluation metrics. HAM10000 dataset is used for training and testing as this data contain seven different skin lesions. The novelty of the proposed hybrid model is the structure of the network which handles structured data (patients' metadata and other useful features from different color spaces related to the illumination, energy, darkness, etc.) and unstructured data (images). The results show an overall 86%, 95% top-1 and top-2 accuracy respectively, and 96% area under the curve for the seven classes. The study demonstrates the superiority of the proposed hybrid model with a 2% improvement in the accuracy over the standalone model and a promising behavior as compared to the ensemble techniques. The follow-up research will include more patient data to develop a skin cancer detection device.
CONFLICT OF INTEREST
The authors declare no conflicts of interest.
Open Research
DATA AVAILABILITY STATEMENT
The data that support the findings of this study are available from the corresponding author upon reasonable request.
REFERENCES
- 1Jones OT, Ranmuthu CKI, Hall PN, Funston G, Walter FM. Recognising skin cancer in primary care. Adv Ther. 2020; 37(1): 603-616. doi:10.1007/s12325-019-01130-1
- 2Tschandl P, Codella N, Akay BN, et al. Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study. Lancet Oncol. 2019; 20(7): 938-947. doi:10.1016/S1470-2045(19)30333-X
- 3Dildar M, Akram S, Irfan M, et al. Skin cancer detection: a review using deep learning techniques. Int J Environ Res Public Health. 2021; 18(10):5479-5501. doi:10.3390/ijerph18105479
- 4Mehta P, Shah B. Review on techniques and steps of computer aided skin cancer diagnosis. Procedia Comput Sci. 2016; 85: 309-316. doi:10.1016/j.procs.2016.05.238
10.1016/j.procs.2016.05.238 Google Scholar
- 5Saba T. Recent advancement in cancer detection using machine learning: systematic survey of decades, comparisons and challenges. J Infect Public Health. 2020; 13(9): 1274-1289. doi:10.1016/j.jiph.2020.06.033
- 6Liu J, Chen C, Liu Z, Jermsittiparsert K, Ghadimi N. An IGDT-based risk-involved optimal bidding strategy for hydrogen storage-based intelligent parking lot of electric vehicles. J Energy Storage. 2020; 27:101057. doi:10.1016/j.est.2019.101057
- 7Mir M, Shafieezadeh M, Heidari MA, Ghadimi N. Application of hybrid forecast engine based intelligent algorithm and feature selection for wind signal prediction. Evol Syst. 2020; 11(4): 559-573. doi:10.1007/s12530-019-09271-y
- 8Akbary P, Ghiasi M, Pourkheranjani MRR, Alipour H, Ghadimi N. Extracting appropriate nodal marginal prices for all types of committed reserve. Comput Econ. 2019; 53(1): 1-26. doi:10.1007/s10614-017-9716-2
- 9Yang Z, Ghadamyari M, Khorramdel H, et al. Robust multi-objective optimal design of islanded hybrid system with renewable and diesel sources/stationary and mobile energy storage systems. Renew Sustain Energy Rev. 2021; 148:111295. doi:10.1016/j.rser.2021.111295
- 10Tahiri P, Sonia P, Jain G, Gupta WS, Tajjour S. An estimation of machine learning approaches for intrusion detection system. Int Conf Adv Comput Innov Technol Eng. 2021; 7:343-348. doi:10.1109/ICACITE51222.2021.9404643
10.1109/ICACITE51222.2021.9404643 Google Scholar
- 11Alyaseen A, Poddar A, Almohammed F, Tajjour S, Hammadeh K, Alahmad H. Predicting recycled aggregates compressive strength in high-performance concrete using artificial neural networks. In Applications of Computational Intelligence in Concrete Technology, CRC Press; 2022, pp. 269-283. doi:10.1201/9781003184331-16
10.1201/9781003184331?16 Google Scholar
- 12Alyaseen A, Poddar A, Almohammed F, Tajjour S, Hammadeh K, Alahmad H. Compressive strength prediction and analysis of concrete using hybrid artificial neural networks. In Applications of Computational Intelligence in Concrete Technology, CRC Press; 2022, pp. 285-303. doi:10.1201/9781003184331-17
10.1201/9781003184331?17 Google Scholar
- 13Tajjour S, Chandel S. Power generation forecasting of a solar photovoltaic power plant by a novel transfer learning technique with small solar radiation and power generation training data sets. SSRN Electron J. 2022. doi:10.2139/ssrn.4024225
10.2139/ssrn.4024225 Google Scholar
- 14Ben Farhat A, Chandel SS, Woo WL, Adnene C. A novel second order radial basis function neural network technique for enhanced load forecasting of photovoltaic Power systems. Int J Comput Sci Netw Secur. 2021;21:77-87. doi:10.22937/IJCSNS.2021.21.2.9
- 15Kumar A, Sharma V, Malik H, Chandel SS. Daily array yield prediction of grid-interactive photovoltaic plant using relief attribute evaluator based radial basis function neural network. Renew Sustain Energy Rev. 2017; 2016: 1-13. doi:10.1016/j.rser.2017.06.023
- 16Yadav AK, Chandel SS. Identification of relevant input variables for prediction of 1-minute time-step photovoltaic module power using artificial neural network and multiple linear regression models. Renew Sustain Energy Rev. 2017; 77: 955-969. doi:10.1016/j.rser.2016.12.029
- 17Xu Z, Sheykhahmad FR, Ghadimi N, Razmjooy N. Computer-aided diagnosis of skin cancer based on soft computing techniques. Open Med. 2020; 15(1): 860-871. doi:10.1515/med-2020-0131
10.1515/med?2020?0131 Google Scholar
- 18Razmjooy N, Rashid Sheykhahmad F, Ghadimi N. A hybrid neural network - world cup optimization algorithm for melanoma detection. Open Med. 2018; 13(1): 9-16. doi:10.1515/med-2018-0002
10.1515/med?2018?0002 Google Scholar
- 19Parsian A, Ramezani M, Ghadimi N. A hybrid neural network-gray wolf optimization algorithm for melanoma detection. Biomed Res. 2017; 28(8): 3408-3411.
- 20Djuric U, Zadeh G, Aldape K, Diamandis P. Precision histology: how deep learning is poised to revitalize histomorphology for personalized cancer care. NPJ Precis Oncol. 2017; 1(1): 22. doi:10.1038/s41698-017-0022-1
- 21Ramlakhan K, Shang Y, A mobile automated skin lesion classification system. Paper presented at: Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI, 2011, pp. 138–141, doi: 10.1109/ICTAI.2011.29
- 22Lee T, Ng V, Gallagher R, Coldman A, McLean D. Dullrazor®: a software approach to hair removal from images. Comput Biol Med. 1997; 27(6): 533-543. doi:10.1016/S0010-4825(97)00020-6
- 23Yang T, Chen Y, Lu J, Fan Z. Sampling with level set for pigmented skin lesion segmentation. Signal, Image Video Process. 2019; 13(4): 813-821. doi:10.1007/s11760-019-01417-4
- 24Elgamal M. Automatic skin cancer images classification. Int J Adv Comput Sci Appl. 2013; 4(3): 287-294. doi:10.14569/ijacsa.2013.040342
10.14569/ijacsa.2013.040342 Google Scholar
- 25Glaister J, Amelard R, Wong A, Clausi DA. MSIM: multistage illumination modeling of dermatological photographs for illumination-corrected skin lesion analysis. IEEE Trans Biomed Eng. 2013; 60(7): 1873-1883. doi:10.1109/TBME.2013.2244596
- 26Garcia-Arroyo JL, Garcia-Zapirain B. Segmentation of skin lesions in dermoscopy images using fuzzy classification of pixels and histogram thresholding. Comput Methods Programs Biomed. 2019; 168: 11-19. doi:10.1016/j.cmpb.2018.11.001
- 27Mahbod A, Schaefer G, Wang C, Ecker R, Ellinge I. Skin lesion classification using hybrid deep neural networks. IEEE Int Conf Acoust Speech Signal Process - Proc. 2019; 2019: 1229-1233. doi:10.1109/ICASSP.2019.8683352
10.1109/ICASSP.2019.8683352 Google Scholar
- 28Rajinikanth V, Madhavaraja N, Satapathy SC, Fernandes SL. Otsu's multi-thresholding and active contour snake model to segment dermoscopy images. J Med Imaging Heal Inform. 2017; 7(8): 1837-1840. doi:10.1166/jmihi.2017.2265
- 29Yuksel ME, Borlu M. Accurate segmentation of dermoscopic images by image thresholding based on type-2 fuzzy logic. IEEE Trans Fuzzy Syst. 2009; 17(4): 976-982. doi:10.1109/TFUZZ.2009.2018300
- 30Al-Masni MA, Al-antari MA, Choi MT, Han SM, Kim TS. Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks. Comput Methods Programs Biomed. 2018; 162: 221-231. doi:10.1016/j.cmpb.2018.05.027
- 31Xie F, Yang J, Liu J, Jiang Z, Wang Y. Skin lesion segmentation using high resolution convolutional neural network. Comput Methods Programs Biomed. 2020; 186:105241. doi:10.1016/j.cmpb.2019.105241
- 32Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In Lecture Notes In Computer Science, 2015, pp. 234-241. doi:10.1007/978-3-319-24574-4_28
10.1007/978-3-319-24574-4_28 Google Scholar
- 33Alom M, Yakopcic C, Hasan M, Taha T, Asari V. Recurrent residual U-net for medical image segmentation. J Med Imaging. 2019; 6: 1. doi:10.1117/1.jmi.6.1.014006
- 34Ünver HM, Ayan E. Skin lesion segmentation in dermoscopic images with combination of yolo and grabcut algorithm. Diagnostics. 2019; 9(3):72-93. doi:10.3390/diagnostics9030072
- 35Chen EZ, Dong X, Li X, et al. Lesion attributes segmentation for melanoma detection with multi-task u-net East China University of Science and Technology, Shanghai, China UT, Southwestern Medical Center, Dallas, TX, USA, Cleerly Inc, New York City, New York, USA, 2019 IEEE 16th Int. Symp. Biomed. Imaging (ISBI 2019), no. ISBI, pp. 485–488.
- 36Messadi M, Bessaid A, Taleb-Ahmed A. Extraction of specific parameters for skin tumour classification. J Med Eng Technol. 2009; 33(4): 288-295. doi:10.1080/03091900802451315
- 37Shimizu K, Iyatomi H, Celebi ME, Norton KA, Tanaka M. Four-class classification of skin lesions with task decomposition strategy. IEEE Trans Biomed Eng. 2015; 62(1): 274-283. doi:10.1109/TBME.2014.2348323
- 38Harangi B. Skin lesion classification with ensembles of deep convolutional neural networks. J Biomed Inform. 2018; 86: 25-32. doi:10.1016/j.jbi.2018.08.006
- 39Milton MAA. Automated skin lesion classification using ensemble of deep neural networks in ISIC 2018: skin lesion analysis towards melanoma detection challenge, 2019, Available: http://arxiv.org/abs/1901.10802.
- 40Patwardhan SV, Dai S, Dhawan AP. Multi-spectral image analysis and classification of melanoma using fuzzy membership-based partitions. Comput Med Imaging Graph. 2005; 29(4): 287-296. doi:10.1016/j.compmedimag.2004.11.001
- 41Shahin AH, Kamal A, Elattar MA. Deep ensemble learning for skin lesion classification from dermoscopic images. 2018 9th Cairo Int Biomed Eng Conf CIBEC 2018 - Proc. 2018; 150-153. doi:10.1109/CIBEC.2018.8641815
10.1109/CIBEC.2018.8641815 Google Scholar
- 42Sultana NN, Puhan NB, Mandal B. DeepPCA Based Objective Function for Melanoma Detection. Paper presented at: International Conference on Information Technology (ICIT), 2018, pp. 68–72, doi: 10.1109/ICIT.2018.00025
- 43Lee YC, Jung SH, Won HH. WonDerM: skin lesion classification with fine-tuned neural networks. arXiv. 2018.
- 44Qin Z, Liu Z, Zhu P, Xue Y. A GAN-based image synthesis method for skin lesion classification. Comput Methods Programs Biomed. 2020; 195:105568. doi:10.1016/j.cmpb.2020.105568
- 45Tajjour S, Patel SK, Parmar C, Dhasarathan V. Implementation of automatic skin lesions diagnosis-a deep learning ensembling approach. J Adv Eng Comput. 2020; 4(4): 261. doi:10.25073/jaec.202044.306
10.25073/jaec.202044.306 Google Scholar
- 46Tschandl P. The HAM10000 Dataset, a Large Collection of Multi-Source Dermatoscopic Images of Common Pigmented Skin Lesions - ViDIR Dataverse. Harvard Dataverse; 2018. doi:10.7910/DVN/DBW86T (accessed Apr. 30, 2022).
10.7910/DVN/DBW86T Google Scholar
- 47Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. 2019, pp. 6105–6114.
- 48Gessert N, Sentker T, Madesta F, et al. Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting, pp. 1–5, 2018, Available: http://arxiv.org/abs/1808.01694.
- 49Sae-Lim W, Wettayaprasit W, Aiyarak P. Convolutional neural networks using mobilenet for skin lesion classification. Paper presented at: 16th international joint conference on computer science and software engineering (JCSSE). 2019 pp. 242–247.
- 50Chaturvedi SS, Gupta K, Prasad PS. Skin lesion analyser: an efficient seven-way multi-class skin cancer classification using mobilenet. Adv Intell Syst Comput. 2021; 1141: 165-176. doi:10.1007/978-981-15-3383-9_15
10.1007/978?981?15?3383?9_15 Google Scholar
- 51Mahbod A, Schaefer G, Wang C, Dorffner G, Ecker R, Ellinger I. Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification. Comput Methods Programs Biomed. 2020; 193: 1-27. doi:10.1016/j.cmpb.2020.105475
