Refining Skin Lesions Classification Performance Using Geometric Features of Superpixels

Overview

Journal Sci Rep

Specialty Science

Date 2023 Jul 15

PMID 37454166

Authors

Simona Moldovanu

Mihaela Miron

Cristinel-Gabriel Rusu

Keka C Biswas

Luminita Moraru

Affiliations

Soon will be listed here.

Abstract

This paper introduces superpixels to enhance the detection of skin lesions and to discriminate between melanoma and nevi without false negatives, in dermoscopy images. An improved Simple Linear Iterative Clustering (iSLIC) superpixels algorithm for image segmentation in digital image processing is proposed. The local graph cut method to identify the region of interest (i.e., either the nevi or melanoma lesions) has been adopted. The iSLIC algorithm is then exploited to segment sSPs. iSLIC discards all the SPs belonging to image background based on assigned labels and preserves the segmented skin lesions. A shape and geometric feature extraction task is performed for each segmented SP. The extracted features are fed into six machine learning algorithms such as: random forest, support vector machines, AdaBoost, k-nearest neighbor, decision trees (DT), Gaussian Naïve Bayes and three neural networks. These include Pattern recognition neural network, Feed forward neural network, and 1D Convolutional Neural Network for classification. The method is evaluated on the 7-Point MED-NODE and PAD-UFES-20 datasets and the results have been compared to the state-of-art findings. Extensive experiments show that the proposed method outperforms the compared existing methods in terms of accuracy.

Citing Articles

Convolutional Neural Network-Machine Learning Model: Hybrid Model for Meningioma Tumour and Healthy Brain Classification.

Moldovanu S, Tabacaru G, Barbu M J Imaging. 2024; 10(9).

PMID: 39330455 PMC: 11433632. DOI: 10.3390/jimaging10090235.

References

Cheadle C, Vawter M, Freed W, Becker K . Analysis of microarray data using Z score transformation. J Mol Diagn. 2003; 5(2):73-81. PMC: 1907322. DOI: 10.1016/S1525-1578(10)60455-2. View

Rehman A, Khan M, Mehmood Z, Saba T, Sardaraz M, Rashid M . Microscopic melanoma detection and classification: A framework of pixel-based fusion and multilevel features reduction. Microsc Res Tech. 2020; 83(4):410-423. DOI: 10.1002/jemt.23429. View

Pacheco A, Lima G, Salomao A, Krohling B, Biral I, de Angelo G . PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones. Data Brief. 2020; 32:106221. PMC: 7479321. DOI: 10.1016/j.dib.2020.106221. View

Annaby M, Elwer A, Rushdi M, Rasmy M . Melanoma Detection Using Spatial and Spectral Analysis on Superpixel Graphs. J Digit Imaging. 2021; 34(1):162-181. PMC: 7886936. DOI: 10.1007/s10278-020-00401-6. View

Khan M, Sharif M, Akram T, Damasevicius R, Maskeliunas R . Skin Lesion Segmentation and Multiclass Classification Using Deep Learning Features and Improved Moth Flame Optimization. Diagnostics (Basel). 2021; 11(5). PMC: 8145295. DOI: 10.3390/diagnostics11050811. View

Kawahara J, Daneshvar S, Argenziano G, Hamarneh G . 7-Point Checklist and Skin Lesion Classification using Multi-Task Multi-Modal Neural Nets. IEEE J Biomed Health Inform. 2018; . DOI: 10.1109/JBHI.2018.2824327. View

Szyc L, Hillen U, Scharlach C, Kauer F, Garbe C . Diagnostic Performance of a Support Vector Machine for Dermatofluoroscopic Melanoma Recognition: The Results of the Retrospective Clinical Study on 214 Pigmented Skin Lesions. Diagnostics (Basel). 2019; 9(3). PMC: 6787620. DOI: 10.3390/diagnostics9030103. View

Sornapudi S, Stanley R, V Stoecker W, Almubarak H, Long R, Antani S . Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels. J Pathol Inform. 2018; 9:5. PMC: 5869967. DOI: 10.4103/jpi.jpi_74_17. View

Rastgoo M, Garcia R, Morel O, Marzani F . Automatic differentiation of melanoma from dysplastic nevi. Comput Med Imaging Graph. 2015; 43:44-52. DOI: 10.1016/j.compmedimag.2015.02.011. View

10.

Thapar P, Rakhra M, Cazzato G, Hossain M . A Novel Hybrid Deep Learning Approach for Skin Lesion Segmentation and Classification. J Healthc Eng. 2022; 2022:1709842. PMC: 9038388. DOI: 10.1155/2022/1709842. View

11.

Moldovanu S, Damian Michis F, Biswas K, Culea-Florescu A, Moraru L . Skin Lesion Classification Based on Surface Fractal Dimensions and Statistical Color Cluster Features Using an Ensemble of Machine Learning Techniques. Cancers (Basel). 2021; 13(21). PMC: 8582408. DOI: 10.3390/cancers13215256. View

12.

Popescu D, El-Khatib M, El-Khatib H, Ichim L . New Trends in Melanoma Detection Using Neural Networks: A Systematic Review. Sensors (Basel). 2022; 22(2). PMC: 8778535. DOI: 10.3390/s22020496. View

13.

Masud M, Rashed A, Hossain M . Convolutional neural network-based models for diagnosis of breast cancer. Neural Comput Appl. 2020; 34(14):11383-11394. PMC: 7545025. DOI: 10.1007/s00521-020-05394-5. View

14.

Chicco D, Jurman G . The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics. 2020; 21(1):6. PMC: 6941312. DOI: 10.1186/s12864-019-6413-7. View

15.

van Zeijl M, Ismail R, de Wreede L, van den Eertwegh A, de Boer A, van Dartel M . Real-world outcomes of advanced melanoma patients not represented in phase III trials. Int J Cancer. 2020; 147(12):3461-3470. PMC: 7689762. DOI: 10.1002/ijc.33162. View

16.

Tanaka T, Voigt M . Decision tree analysis to stratify risk of de novo non-melanoma skin cancer following liver transplantation. J Cancer Res Clin Oncol. 2018; 144(3):607-615. DOI: 10.1007/s00432-018-2589-5. View

17.

Shetty B, Fernandes R, Rodrigues A, Chengoden R, Bhattacharya S, Lakshmanna K . Skin lesion classification of dermoscopic images using machine learning and convolutional neural network. Sci Rep. 2022; 12(1):18134. PMC: 9616944. DOI: 10.1038/s41598-022-22644-9. View

18.

Kim H, Inoue J, Kasuya T . Unsupervised microstructure segmentation by mimicking metallurgists' approach to pattern recognition. Sci Rep. 2020; 10(1):17835. PMC: 7575545. DOI: 10.1038/s41598-020-74935-8. View

19.

Celebi M, Kingravi H, Uddin B, Iyatomi H, Aslandogan Y, V Stoecker W . A methodological approach to the classification of dermoscopy images. Comput Med Imaging Graph. 2007; 31(6):362-73. PMC: 3192405. DOI: 10.1016/j.compmedimag.2007.01.003. View

20.

Afza F, Sharif M, Mittal M, Khan M, Hemanth D . A hierarchical three-step superpixels and deep learning framework for skin lesion classification. Methods. 2021; 202:88-102. DOI: 10.1016/j.ymeth.2021.02.013. View