Enhancing multi-class prediction of skin lesions with feature importance assessment

• Autorzy: Paulauskaite-Taraseviciene, Agne , Sutiene, Kristina , Dimsa, Nojus , Valiukeviciene, Skaidra
• Języki publikacji: EN

Abstrakty

EN

Numerous image processing techniques have been developed for the identification of various types of skin lesions. In real-world scenarios, the specific lesion type is often unknown in advance, leading to a multi-class prediction challenge. The available evidence underscores the importance of employing a comprehensive array of diverse features and subsequently identifying the most important ones as a crucial step in visual diagnostics. For this purpose, we addressed both binary and five-class classification tasks using a small dataset, with skin lesions prevalent in Lithuania. The model was trained using a rich set of 662 features, encompassing both conventional image features and graph-based ones, which were obtained from the superpixel graph generated using Delaunay triangulation. We explored the influence of feature importance determined by SHAP values, resulting in a weighted F1-score of 92.48% for the two-class classification and 71.21% for the five-class prediction.

Słowa kluczowe

PL

zmiany skórne; ekstrakcja cech; teoria grafów; wartość SHAP

EN

skin lesion; feature extraction; graph theory; multiclass prediction; SHAP value

• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2024
• Tom: Vol. 34, no. 4
• Strony: 617--629
• Opis fizyczny: Bibliogr. 45 poz., rys., tab.

Twórcy

autor

Paulauskaite-Taraseviciene, Agne

• Artificial Intelligence Centre, Kaunas University of Technology, K. Barsausko g. 59, 51423 Kaunas, Lithuania,

autor

Sutiene, Kristina

• Department of Mathematical Modeling, Kaunas University of Technology, Studentu g. 50, 51368 Kaunas, Lithuania,

autor

Dimsa, Nojus

• Faculty of Informatics, Kaunas University of Technology, Studentu g. 50, 51368 Kaunas, Lithuania,

autor

Valiukeviciene, Skaidra

• Department of Skin and Venereal Diseases, Lithuanian University of Health Sciences, A. Mickeviciaus g. 9, 44307 Kaunas, Lithuania,
• Department of Skin and Venereal Diseases, Hospital of Lithuanian University of Health Sciences ‘Kauno klinikos’ Eiveniu g. 2, 50161 Kaunas, Lithuania

Bibliografia

• [1] Abbes, W., Sellami, D., Marc-Zwecker, S. and Zanni-Merk, C. (2021). Fuzzy decision ontology for melanoma diagnosis using KNN classifier, Multimedia Tools and Applications 80: 25517-25538.
• [2] Abdelhalim, I.S.A., Mohamed, M.F. and Mahdy, Y.B. (2021). Data augmentation for skin lesion using self-attention based progressive generative adversarial network, Expert Systems with Applications 165: 113922.
• [3] Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P. and Süsstrunk, S. (2010). Slic superpixels, Technical Report 149300, Ecole Polytechnique F´ed´erale de Lausanne, Lausanne.
• [4] Aladhadh, S., Alsanea, M., Aloraini, M., Khan, T., Habib, S. and Islam, M. (2022). An effective skin cancer classification mechanism via medical vision transformer, Sensors 22(11): 4008.
• [5] Aldhyani, T.H.H., Verma, A., Al-Adhaileh, M.H. and Koundal, D. (2022). Multi-class skin lesion classification using a lightweight dynamic kernel deep-learning-based convolutional neural network, Diagnostics 12(9), Article no. 2048.
• [6] Ali, K., Shaikh, Z.A., Khan, A.A. and Laghari, A.A. (2022). Multiclass skin cancer classification using EfficientNets - A first step towards preventing skin cancer, Neuroscience Informatics 2(4): 100034.
• [7] Aloupogianni, E., Ishikawa, M., Kobayashi, N. and Obi, T. (2022). Hyperspectral and multispectral image processing for gross-level tumor detection in skin lesions: A systematic review, Journal of Biomedical Optics 27(06): 060901.
• [8] Alwakid, G., Gouda, W., Humayun, M. and Sama, N.U. (2022). Melanoma detection using deep learning-based classifications, Healthcare 10(12): 2481.
• [9] Annaby, M.H., Elwer, A.M., Rushdi, M.A. and Rasmy, M.E.M. (2021). Melanoma detection using spatial and spectral analysis on superpixel graphs, Journal of Digital Imaging 34(1): 162-181.
• [10] Araújo, R.L., Araújo, F.H.D.d. and Silva, R.R.V.e. (2021). Automatic segmentation of melanoma skin cancer using transfer learning and fine-tuning, Multimedia Systems 28(4): 1239-1250.
• [11] Ashraf, H., Waris, A., Ghafoor, M.F., Gilani, S.O. and Niazi, I.K. (2022). Melanoma segmentation using deep learning with test-time augmentations and conditional random fields, Scientific Reports 12(1): 3948.
• [12] Bibi, S., Khan, M.A., Shah, J.H., Damaševičius, R., Alasiry, A., Marzougui, M., Alhaisoni, M. and Masood, A. (2023). MSRNet: Multiclass skin lesion recognition using additional residual block based fine-tuned deep models information fusion and best feature selection, Diagnostics 13(19), Article no. 3063.
• [13] Codella, N.C.F., Gutman, D., Celebi,M.E., Helba, B. Marchetti, M.A., Dusza, S.W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H. and Halpern, A. (2017). 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), 2018 IEEE 15th International Symposium on Biomedical Imaging, Washington, USA, pp. 168-172.
• [14] Combalia, M., Codella, N.C.F., Rotemberg, V., Helba, B., Vilaplana, V., Reiter, O., Carrera, C., Barreiro, A., Halpern, A.C., Puig, S. and Malvehy, J. (2019). BCN20000: Dermoscopic lesions in the wild, arXiv: 1908.02288.
• [15] Damian, F.-A., Moldovanu, S. and Moraru, L. (2022). Melanoma detection using a random forest algorithm, 2022 E-Health and Bioengineering Conference (EHB), Iasi, Romania.
• [16] Dildar, M., Akram, S., Irfan, M., Khan, H.U., Ramzan, M., Mahmood, A.R., Alsaiari, S.A., Saeed, A.H.M., Alraddadi, M.O. and Mahnashi, M.H. (2021). Skin cancer detection: A review using deep learning techniques, International Journal of Environmental Research and Public Health 18(10): 5479.
• [17] Emery, J.D., Hunter, J., Hall, P.N., Watson, A.J., Moncrieff, M. and Walter, F.M. (2010). Accuracy of siascopy for pigmented skin lesions encountered in primary care: Development and validation of a new diagnostic algorithm, BMC Dermatology 10(1): 9.
• [18] Gutman, D., Codella, N.C.F., Celebi, E., Helba, B., Marchetti, M., Mishra, N. and Halpern, A. (2016). Skin lesion analysis toward melanoma detection: A challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC), arXiv: 1605.01397.
• [19] Hurtado, J. and Reales, F. (2021). A machine learning approach for the recognition of melanoma skin cancer on macroscopic images, TELKOMNIKA (Telecommunication Computing Electronics and Control) 19(4): 1357.
• [20] Ilis, anu, M.-A., Moldoveanu, F. and Moldoveanu, A. (2023). Multispectral imaging for skin diseases assessment - State of the art and perspectives, Sensors 23(8): 3888.
• [21] Jocher, G., Chaurasia, A. and Qiu, J. (2023). Ultralytics YOLOv8, https://github.com/ultralytics/ultralytics.
• [22] Kassem, M.A., Hosny, K.M., Damaševičius, R. and Eltoukhy, M.M. (2021). Machine learning and deep learning methods for skin lesion classification and diagnosis: A systematic review, Diagnostics 11(8), Article no. 1390.
• [23] Khan, M.A., Sharif, M.I., Raza, M., Anjum, A., Saba, T. and Shad, S.A. (2022). Skin lesion segmentation and classification: A unified framework of deep neural network features fusion and selection, Expert Systems 39(7): e12497.
• [24] Li, X., Wang, Y., Basu, S., Kumbier, K. and Yu, B. (2019). A debiased MDI feature importance measure for random forests, Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada, pp. 8049-8080.
• [25] Liutkus, J., Kriukas, A., Stragyte, D., Mazeika, E., Raudonis, V., Galetzka, W., Stang, A. and Valiukeviciene, S. (2023). Accuracy of a smartphone-based artificial intelligence application for classification of melanomas, melanocytic nevi, and seborrheic keratoses, Diagnostics 13(13): 2139.
• [26] Mendonca, T., Ferreira, P.M., Marques, J.S., Marcal, A.R.S. and Rozeira, J. (2013). Ph2 - A dermoscopic image database for research and benchmarking, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan, pp. 5437-5440.
• [27] Murugan, A., Nair, S.H. and Kumar, K.P.S. (2019). Detection of skin cancer using SVM, random forest and KNN classifiers, Journal of Medical Systems 43(8): 1-9, DOI: 10.1007/s10916-019-1400-8.
• [28] Navarrete-Dechent, C., Dusza, S.W., Liopyris, K., Marghoob, A.A., Halpern, A.C. and Marchetti, M.A. (2018). Automated dermatological diagnosis: Hype or reality?, Journal of Investigative Dermatology 138(10): 2277-2279, DOI: 10.1016/j.jid.2018.04.040.
• [29] Oliveira, R.B., Pereira, A.S. and Tavares, J.M.R. (2017). Skin lesion computational diagnosis of dermoscopic images: Ensemble models based on input feature manipulation, Computer Methods and Programs in Biomedicine 149: 43-53, DOI: 10.1016/j.cmpb.2017.07.009.
• [30] Oliveira, R.B., Pereira, A.S. and Tavares, J.M.R.S. (2018). Computational diagnosis of skin lesions from dermoscopic images using combined features, Neural Computing and Applications 31(10): 6091-6111.
• [31] Oukil, S., Kasmi, R., Mokrani, K. and García-Zapirain, B. (2021). Automatic segmentation and melanoma detection based on color and texture features in dermoscopic images, Skin Research and Technology 28(2): 203-211.
• [32] Rashid, H., Tanveer, M.A. and Aqeel Khan, H. (2019). Skin lesion classification using GAN based data augmentation, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, pp. 916-919.
• [33] Rey-Barroso, L., Burgos-Fernández, F., Delpueyo, X., Ares, M., Royo, S., Malvehy, J., Puig, S. and Vilaseca, M. (2018). Visible and extended near-infrared multispectral imaging for skin cancer diagnosis, Sensors 18(5): 1441.
• [34] SIIM-ISIC (2020). International Skin Imaging Collaboration 2020 Challenge Dataset, https://challenge2020.isic-archive.com/.
• [35] Sharma, G., Wu, W. and Dalal, E.N. (2004). The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations, Color Research & Application 30(1): 21-30.
• [36] Shetty, B., Fernandes, R., Rodrigues, A.P., Chengoden, R., Bhattacharya, S. and Lakshmanna, K. (2022). Skin lesion classification of dermoscopic images using machine learning and convolutional neural network, Scientific Reports 12(1): 18134.
• [37] Sunarya, C.A., Siswanto, J.V., Cam, G.S. and Kurniadi, F.I. (2023). Skin cancer classification using Delaunay triangulation and graph convolutional network, International Journal of Advanced Computer Science and Applications 14(6), DOI: 10.14569/IJACSA.2023.0140685.
• [38] Surówka, G. and Ogorzałek, M. (2022). Segmentation of the melanoma lesion and its border, International Journal of Applied Mathematics and Computer Science 32(4): 683-699, DOI: 10.34768/amcs-2022-0047.
• [39] Tembhurne, J.V., Hebbar, N., Patil, H.Y. and Diwan, T. (2023). Skin cancer detection using ensemble of machine learning and deep learning techniques, Multimedia Tools and Applications 82(18): 27501-27524.
• [40] Tschandl, P., Rosendahl, C. and Kittler, H. (2018). The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions, Scientific Data 5(1): 180161.
• [41] Vikas Reddy, K. and Rama Parvathy, L. (2022). Accurate detection and classification of melanoma skin cancer using decision tree algorithm over CNN, in D.J. Hemanth et al. (Eds), Advances in Parallel Computing Algorithms, Tools and Paradigms, IOS Press, Amsterdam, pp. 321-326.
• [42] Wang, C.-Y., Bochkovskiy, A. and Liao, H.-Y.M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, arXiv: 2207.02696.
• [43] Wen, D., Khan, S.M., Ji Xu, A., Ibrahim, H., Smith, L., Caballero, J., Zepeda, L., de Blas Perez, C., Denniston, A.K., Liu, X. and Matin, R.N. (2022). Characteristics of publicly available skin cancer image datasets: A systematic review, The Lancet Digital Health 4(1): e64-e74.
• [44] Winkler, J.K., Fink, C., Toberer, F., Enk, A., Deinlein, T., Hofmann-Wellenhof, R., Thomas, L., Lallas, A., Blum, A., Stolz, W. and Haenssle, H.A. (2019). Association between surgical skin markings in dermoscopic images and diagnostic performance of a deep learning convolutional neural network for melanoma recognition, JAMA Dermatology 155(10): 1135-1141.
• [45] Zafar, M., Sharif, M.I., Sharif, M.I., Kadry, S., Bukhari, S.A.C. and Rauf, H.T. (2023). Skin lesion analysis and cancer detection based on machine/deep learning techniques: A comprehensive survey, Life 13(1): 146.

Identyfikatory

DOI

10.61822/amcs-2024-0041