RESEARCH ARTICLE
SLICACO: An automated novel hybrid approach for dermatoscopic melanocytic skin lesion segmentation
Lokesh Singh,
Rekh Ram Janghel,
Satya Prakash Sahu,
Corresponding Author
Lokesh Singh
Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India
Correspondence
Lokesh Singh, Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India.
Email: [email protected]
Search for more papers by this authorRekh Ram Janghel
Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India
Search for more papers by this authorSatya Prakash Sahu
Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India
Search for more papers by this authorLokesh Singh,
Rekh Ram Janghel,
Satya Prakash Sahu,
Corresponding Author
Lokesh Singh
Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India
Correspondence
Lokesh Singh, Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India.
Email: [email protected]
Search for more papers by this authorRekh Ram Janghel
Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India
Search for more papers by this authorSatya Prakash Sahu
Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India
Search for more papers by this authorAbstract
Low contrast images and blurriness pose challenge in the over-segmentation of image, which increases model complexities. In this work, a novel hybrid dermoscopic skin-lesion segmentation method, namely SLICACO, is proposed incorporating the simple linear iterative clustering (SLIC) and ant colony optimization (ACO) algorithms. The working of proposed method is multifold. First, over-segmentation of preprocessed image is generated using SLIC super-pixel technique. Second, clusters of super-pixels generated by SLIC are used by ACO with the pixels of similar intensity for edge detection and seek for the optimum pathway in a strained zone. Third, lesion area is segmented using the Convex Hull and Thresholding. Fourth, Erosion Filtering is used to obtain the final segmented image. The performance of SLICACO is assessed on five benchmark dermatoscopic datasets and compared with deep learning models to test its generalizing behavior. Promising results are obtained on the PH2 archive data set with an accuracy of 95.9%.
CONFLICT OF INTEREST
The authors declare no conflicts of interest.
Open Research
DATA AVAILABILITY STATEMENT
The data sets used in the experiment are publicly available.
REFERENCES
- 1Pereira PMM, Fonseca-Pinto R, Paiva RP, et al. Dermoscopic skin lesion image segmentation based on local binary pattern clustering: comparative study. Biomed Signal Process Control. 2020; 59:101924. https://doi.org/10.1016/j.bspc.2020.101924.
- 2Ahn E, Kim J, Bi L, et al. Saliency - based lesion segmentation via background detection in dermoscopic images. IEEE J Biomed Health Inform. 2017; 21(6): 1685-1693.
- 3Ren X, Malik, J. Learning a classification model for segmentation. Proceedings of the IEEE International Conference on Computer Vision, 1(c); 2003:10-17. https://doi.org/10.1109/iccv.2003.1238308
10.1109/iccv.2003.1238308 Google Scholar
- 4Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Susstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Patttern Anal Mach Intell. 2012; 34(1): 1-8. https://doi.org/10.1109/tpami.2012.120.
10.1109/tpami.2012.120 Google Scholar
- 5Soltaninejad M, Yang G, Lambrou T, et al. Automated brain tumour detection and segmentation using superpixel-based extremely randomized trees in FLAIR MRI. Int J Comput Assist Radiol Surg. 2017; 12(2): 183-203. https://doi.org/10.1007/s11548-016-1483-3.
- 6Yang, G., Zhuang, X., Khan, H., et al. Multi-atlas propagation based left atrium segmentation coupled with super-voxel based pulmonary veins delineation in late gadolinium-enhanced cardiac MRI. Medical Imaging 2017: Image Processing; 2017:1013313. https://doi.org/10.1117/12.2250926
10.1117/12.2250926 Google Scholar
- 7Zhao J, Ren B, Hou Q, Cheng MM, Rosin PL. FLIC: fast linear iterative clustering with active search. Comput Vis Media. 2018; 4(4): 333-348.
10.1007/s41095-018-0123-y Google Scholar
- 8Govindaraj V, Murugan PR. A complete automated algorithm for segmentation of tissues and identification of tumor region in T1, T2, and flair brain images using optimization and clustering techniques. Int J Imaging Syst Technol. 2014; 24(4): 313-325. https://doi.org/10.1002/ima.22108.
- 9Yang J, Govindaraj VV, Ming Yang S-HW. Hearing loss detection by discrete wavelet transform and multi-layer perceptron trained by nature-inspired algorithms. Multimed Tools Appl. 2020; 79(21-22): 15717-15745. https://doi.org/10.1007/s11042-019-08344-z.
- 10Wang M, Liu X, Gao Y, Ma X, Soomro NQ. Superpixel segmentation: a benchmark. Signal Process Image Commun. 2017; 56: 28-39. https://doi.org/10.1016/j.image.2017.04.007.
- 11Achanta R, Susstrunk S. Superpixels and polygons using simple non-iterative clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2017:4651-4660. https://doi.org/10.1109/ICETCE.2011.5776422.
10.1109/ICETCE.2011.5776422 Google Scholar
- 12Shen J, Hao X, Liang Z, Liu Y, Wang W, Shao L. Real-time superpixel segmentation by DBSCAN clustering algorithm. IEEE Trans Image Process. 2016; 25(12): 5933-5942. https://doi.org/10.1109/TIP.2016.2616302.
- 13Van den Bergh M, Boix X, Roig G, Van Gool L. SEEDS: superpixels extracted via energy-driven sampling. Int J Comput Vis. 2015; 111(3): 298-314. https://doi.org/10.1007/s11263-014-0744-2.
- 14Stutz D, Hermans A, Leibe B. Superpixels: an evaluation of the state-of-the-art. Comput Vis Image Underst. 2018; 166: 1-27. https://doi.org/10.1016/j.cviu.2017.03.007.
- 15Zhou B. Image segmentation using SLIC superpixels and affinity propagation clustering. Int J Sci Res. 2015; 4(4): 1525-1529.
- 16Patino D, Avendaño J, Branch JW. Automatic skin lesion segmentation on dermoscopic images by the means of superpixel merging. International Conference on Medical Image Computing and Computer-Assisted Intervention; 2018:728-736. https://doi.org/10.1007/978-3-030-00937-3
10.1007/978-3-030-00937-3 Google Scholar
- 17Strassburg J, Grzeszick R, Rothacker L, Fink GA. On the influence of superpixel methods for image parsing. VISAPP 2015 - 10th International Conference on Computer Vision Theory and Applications; VISIGRAPP, Proceedings, 2; 2015:518-527. https://doi.org/10.5220/0005355705180527
10.5220/0005355705180527 Google Scholar
- 18Nayyar A, Singh R. Ant colony optimization-computational swarm intelligence technique. 3rd International Conference on Computing for Sustainable Global Development (INDIACom); IEEE; 2016:1493-1499.
- 19Sengupta S, Mittal N, Modi M. Improved skin lesion edge detection method using Ant colony optimization. Skin Res Technol. 2019; 25(6): 846-856. https://doi.org/10.1111/srt.12744.
- 20Sudhriti S, Neetu M, Megha M. Improved skin lesions detection using color space and artificial intelligence techniques. J Dermatolog Treat. 2020; 31(5): 511-518. https://doi.org/10.1080/09546634.2019.1708239.
- 21Zhang L, Yang G, Ye X. Automatic skin lesion segmentation by coupling deep fully convolutional networks and shallow network with textons. J Med Imaging. 2019; 6(2): 1. https://doi.org/10.1117/1.jmi.6.2.024001.
- 22Ali AR, Li J, Kanwal S, Yang G, Hussain A, O'Shea SJ. A novel fuzzy multilayer perceptron (F-MLP) for the detection of irregularity in skin lesion border using dermoscopic images. Front Med. 2020c; 7: 1-14. https://doi.org/10.3389/fmed.2020.00297.
- 23Ali A-R, Li J, Yang G, O'Shea SJ. A machine learning approach to automatic detection of irregularity in skin lesion border using dermoscopic images. PeerJ Comput Sci. 2020a; 6:e268. https://doi.org/10.7717/peerj-cs.268.
- 24Qiu Y, Cai J, Qin X, Zhang J. Inferring skin lesion segmentation with fully connected CRFs based on multiple deep convolutional neural networks. IEEE Access. 2020; 8: 144246-144258. https://doi.org/10.1109/ACCESS.2020.3014787.
- 25Ali AR, Li J, O'Shea SJ, Yang G, Trappenberg T, Ye X. A deep learning based approach to skin lesion border extraction with a novel edge detector in dermoscopy images. Proceedings of the International Joint Conference on Neural Networks (IJCNN). IEEE; 2019:1-7.
- 26Baig R, Bibi M, Hamid A, Kausar S, Khalid S. Deep learning approaches towards skin lesion segmentation and classification from dermoscopic images—a review. Curr Med Imaging. 2020; 16(5): 513-533.
- 27Ali ARH, Li J, Yang G. Automating the ABCD rule for melanoma detection: a survey. IEEE Access. 2020b; 8: 83333-83346. https://doi.org/10.1109/ACCESS.2020.2991034.
- 28 ISIC Challenge. https://challenge.isic-archive.com/landing/2016. Accessed September 13, 2020.
- 29 ISIC Challenge. https://challenge.isic-archive.com/landing/2017. Accessed September 13, 2020.
- 30Tschandl P, Rosendahl C, Kittler H. Data descriptor: the HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data. 2018; 5: 1-9. https://doi.org/10.1038/sdata.2018.161.
- 31 ADDI - Automatic Computer-Based Diagnosis System for Dermoscopy Images. https://www.fc.up.pt/addi/ph2database.html. Accessed September 13, 2020.
- 32Giotis I, Molders N, Land S, Biehl M, Jonkman MF, Petkov N. MED-NODE: a computer-assisted melanoma diagnosis system using non-dermoscopic images. Expert Syst Appl. 2015; 42(19): 6578-6585. https://doi.org/10.1016/j.eswa.2015.04.034.
- 33Ramírez-Gallego S, Krawczyk B, García S, Woźniak M, Herrera F. A survey on data preprocessing for data stream mining: current status and future directions. Neurocomputing. 2017; 239: 39-57. https://doi.org/10.1016/j.neucom.2017.01.078.
- 34Sabouri P, Gholamhosseini H, Larsson T, Collins J. A cascade classifier for diagnosis of melanoma in clinical images. International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC; 2014:6748-6751. https://doi.org/10.1109/EMBC.2014.6945177
10.1109/EMBC.2014.6945177 Google Scholar
- 35Gessert N, Nielsen M, Shaikh M, Werner R, Schlaefer A. Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data. MethodsX. 2020; 7: 1-10. https://doi.org/10.1016/j.mex.2020.100864.
- 36Tharwat A. Classification assessment methods. Appl Comput Inform. 2018; 1-14. https://doi.org/10.1016/j.aci.2018.08.003.
10.1016/j.aci.2018.08.003 Google Scholar
- 37 Matplotlib 3.1.2 Documentation. https://matplotlib.org/3.1.1/tutorials/index.html. Accessed March 23, 2020.
- 38 Pandas - Python Data Analysis Library. https://pandas.pydata.org/. Accessed March 23, 2020.
- 39 scikit-learn: Machine Learning in Python — scikit-learn 0.22.2 Documentation. https://scikit-learn.org/stable/. Accessed March 23, 2020.
- 40 NumPy — NumPy. https://numpy.org/. Accessed March 23, 2020.
- 41 An Introduction to Seaborn — Seaborn 0.10.0 Documentation. https://seaborn.pydata.org/introduction.html. Accessed March 23, 2020.
- 42Sawyer SF. Analysis of variance: the fundamental concepts. J Man Manip Ther. 2009; 17(2): 27-38. https://doi.org/10.1179/jmt.2009.17.2.27e.
10.1179/jmt.2009.17.2.27E Google Scholar
- 43Fujikoshi Y. Two-way ANOVA models with unbalanced data. Discrete Math. 1993; 116(1-3): 315-334. https://doi.org/10.1016/0012-365X(93)90410-U.
- 44Yuan, Y. Automatic skin lesion segmentation with fully convolutional-deconvolutional networks. ArXiv Preprint ArXiv:1703.05165; 2017:1-5. https://doi.org/10.1109/JBHI.2017.2787487
10.1109/JBHI.2017.2787487 Google Scholar
- 45Li Y, Shen L. Skin lesion analysis towards melanoma detection using deep learning network. Sensors. 2018; 18(2): 1-16. https://doi.org/10.3390/s18020556.
- 46Bi L, Kim J, Ahn E, Feng D. Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks. ArXiv Preprint ArXiv:1703.04197; 2017: 6-9. http://arxiv.org/abs/1703.04197.
- 47Lin BS, Michael K, Kalra S, Tizhoosh, HR. . Skin lesion segmentation: U-nets versus clustering. 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 – Proceedings; January 2018:1-7. https://doi.org/10.1109/SSCI.2017.8280804
10.1109/SSCI.2017.8280804 Google Scholar
- 48Al-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. https://doi.org/10.1016/j.cmpb.2018.05.027.
- 49Ünver HM, Ayan E. Skin lesion segmentation in dermoscopic images with combination of yolo and grabcut algorithm. Diagnostics. 2019; 9(3): 1–21. https://doi.org/10.3390/diagnostics9030072.
- 50Xie Y, Zhang J, Xia Y, Shen C. A mutual bootstrapping model for automated skin lesion segmentation and classification. IEEE Trans Med Imaging. 2020; 39(7): 2482-2493. https://doi.org/10.1109/TMI.2020.2972964.
- 51Shan P, Wang Y, Fu C, Song W, Chen J. Automatic skin lesion segmentation based on FC-DPN. Comput Biol Med. 2020; 123:103762. https://doi.org/10.1016/j.compbiomed.2020.103762.
