Research Article
BibTex RIS Cite

Dengesiz Veri Kümelerinde Topluluk Yöntemlerine Dayalı Melanom Sınıflandırılması

Year 2022, Volume: 12 Issue: 2, 1122 - 1137, 15.12.2022
https://doi.org/10.31466/kfbd.1113417

Abstract

Dermoskopi görüntüleme, deri kanseri teşhisi için dermotolojistler tarafından yaygın bir biçimde kullanılan bir tanı metodudur. Dermotolojik değerlendirmenin uzman kişiye bağlı, zaman alıcı ve sübjektif olmasından dolayı otomatik sistemler dermotolojistler tarafından karar verme süreçlerine katkı sağlamaları için tercih edilmektedir. Deri lezyon görüntülerinden melanomların tespit edilmesi hastalığın erken teşhisi ile tedavi sürecini hızlandırarak hastalık ve ölüm oranlarını azaltmaktadır. Bu çalışmada cilt bölgesinden alınan görüntülerden oluşan erişime açık ISIC 2017 veri kümesindeki lezyon bölgelerinin öznitelikleri incelenerek görüntüler melanom ya da nevüs ve seboreik keratoz olarak sınıflandırılmıştır. Melanom verisine ait lezyon özniteliklerini temsil etmek için lezyon bölgesinin şekil, renk ve doku öznitelikleri elde edilmiştir. Çıkarılan öznitelikler k-en yakın komşuluk, destek vektör makineleri ve topluluk öğrenme yöntemlerinden kolay topluluk, RUSBoost, dengelenmiş torbalama ve dengelenmiş rastgele orman sınıflandırıcıları ile sınıflandırılmıştır. Elde edilen sonuçlara göre en iyi sınıflandırma sonuçları sırasıyla %100, %99.17, %99.33 ve %99.58 duyarlılık, özgüllük, doğruluk ve dengeli doğruluk değerleri ile RUSBoost sınıflandırıcısı ile elde edilmiştir. Ulaşılan sonuçlar önerilen öznitelik çıkarma ve sınıflandırma yönteminin lezyon bölgelerinden melanom sınıflandırması için büyük potansiyele sahip olduğunu göstermektedir.

References

  • Bangare, S. L., Dubal, A., Bangare, P. S. ve Patil, S. T. (2015). Reviewing Otsu’s Method for Image Thresholding. International Journal of Applied Engineering Research, 10(9), 21777-21783.
  • Binder, M., Schwarz, M., Winkler, A., Steiner, A., Kaider, A., Wolff, K. ve Pehamberger, H. (1995). Epiluminescence Microscopy: A Useful Tool for The Diagnosis of Pigmented Skin Lesions for Formally Trained Dermatologists. Archives of Dermatology, 131(3), 286-291.
  • Breiman, L. (1996). Bagging Predictors. Machine Learning, 24(2), 123-140.
  • Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32.
  • Celebi, M. E., Kingravi, H. A., Uddin, B., Iyatomi, H., Aslandogan, Y. A., Stoecker, W. V. ve Moss, R. H. (2007). A Methodological Approach to The Classification of Dermoscopy Images. Computerized Medical Imaging and Graphics, 31(6), 362-373.
  • Celebi, M. E., Iyatomi, H., Stoecker, W. V., Moss, R. H., Rabinovitz, H. S., Argenziano, G. ve Soyer, H. P. (2008). Automatic Detection of Blue-White Veil and Related Structures in Dermoscopy Images. Computerized Medical Imaging and Graphics, 32(8), 670-677.
  • Celebi, M. E., Codella, N. ve Halpern, A. (2019). Dermoscopy Image Analysis: Overview and Future Directions. IEEE Journal of Biomedical and Health Informatics, 23(2), 474-478.
  • Chang, W. Y., Huang, A., Yang, C. Y., Lee, C. H., Chen, Y. C., Wu, T. Y. ve Chen, G. S. (2013). Computer-Aided Diagnosis of Skin Lesions Using Conventional Digital Photography: A Reliability and Feasibility Study. PloS one, 8(11), e76212.
  • Chen, C., Liaw, A. ve Breiman, L. (2004). Using Random Forest to Learn Imbalanced Data. Technical Report, Berkeley.
  • Cortes, C. ve Vapnik, V. (1995). Support Vector Machines. Machine Learning. 20, 273–297.
  • Ganster, H., Pinz, P., Rohrer, R., Wildling, E., Binder, M. ve Kittler, H. (2001). Automated Melanoma Recognition. IEEE Transactions on Medical Imaging, 20(3), 233-239.
  • Goodson, A. G. ve Grossman, D. (2009). Strategies for Early Melanoma Detection: Approaches to The Patient with Nevi. Journal of the American Academy of Dermatology, 60(5), 719-735.
  • Khouloud, S., Ahlem, M., Fadel, T., & Amel, S. (2022). W-net and inception residual network for skin lesion segmentation and classification. Applied Intelligence, 52(4), 3976-3994.
  • Lee, T., Ng, V., Gallagher, R., Coldman, A. ve McLean, D. (1997). Dullrazor®: A Software Approach to Hair Removal from Images. Computers in Biology and Medicine, 27(6), 533-543.
  • Li, Y. ve Shen, L. (2018). Skin Lesion Analysis Towards Melanoma Detection using Deep Learning Network. Sensors, 18(2), 556.
  • Liu, X. Y., Wu, J. ve Zhou, Z. H. (2008). Exploratory Undersampling for Class-Imbalance Learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 39(2), 539-550.
  • Messadi, M., Bessaid, A. ve Taleb-Ahmed, A. (2009). Extraction of Specific Parameters for Skin Tumour Classification. Journal of Medical Engineering & Technology, 33(4), 288-295.
  • Okur, E. Ve Turkan, M. (2018). A Survey on Automated Melanoma Detection. Engineering Applications of Artificial Intelligence, 73, 50-67.
  • Schapire, R. E. (1999, Temmuz). A Brief Introduction to Boosting. International Joint Conference on Artificial Intelligence (s. 1401-1406). Stockholm, İsveç.
  • Seiffert, C., Khoshgoftaar, T. M., Van Hulse, J. ve Napolitano, A. (2009). RUSBoost: A Hybrid Approach to Alleviating Class Imbalance. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 40(1), 185-197.
  • Sheha, M. A., Mabrouk, M. S. ve Sharawy, A. (2012). Automatic Detection of Melanoma Skin Cancer Using Texture Analysis. International Journal of Computer Applications, 42(20), 22-26.
  • Silveira, M., Nascimento, J. C., Marques, J. S., Marçal, A. R., Mendonça, T., Yamauchi, S., Maeda, J. ve Rozeira, J. (2009). Comparison of Segmentation Methods for Melanoma Diagnosis in Dermoscopy Images. IEEE Journal of Selected Topics in Signal Processing, 3(1), 35-45.
  • Thao, L.T., ve Quang, N.H. (2017). Automatic Skin Lesion Analysis Towards Melanoma Detection. 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems (s.106-111). Hanoi,Vietnam.
  • Tsao, H., Olazagasti, J. M., Cordoro, K. M., Brewer, J. D., Taylor, S. C., Bordeaux, J. S., Chren, M. -M., Sober, A. J., Tegeler, C., Bhushan, R. ve Begolka, W. S. (2015). Early Detection of Melanoma: Reviewing The ABCDEs. Journal of the American Academy of Dermatology, 72(4), 717-723.
  • Yılmaz, A., Kalebaşı, M., Samoylenko, Y., Güvenilir, M. E. ve Uvet, H. (2021). Benchmarking of Lightweight Deep Learning Architectures for Skin Cancer Classification using ISIC 2017 Dataset. arXiv preprint , vol.1, no.1, 1-2.
  • ISIC: https://challenge.isicarchive.com/, (Erişim Tarihi: 28 Nisan 2022).
  • ISIC2017: https://challenge.isic-archive.com/landing/2017/44/, (Erişim Tarihi: 28 Nisan 2022).
  • WHO: https://www.who.int/news-room/fact-sheets/detail/cancer, (Erişim Tarihi: 28 Nisan 2022).
  • SCF: https://www.skincancer.org/, (Erişim Tarihi: 28 Nisan 2022).
  • CDC: https://www.cdc.gov/cancer/skin/, (Erişim Tarihi: 28 Nisan 2022).

Ensemble Methods-Based Melanoma Classification in Imbalanced Datasets

Year 2022, Volume: 12 Issue: 2, 1122 - 1137, 15.12.2022
https://doi.org/10.31466/kfbd.1113417

Abstract

Dermoscopy imaging is a diagnostic method widely used by dermatologists for the diagnosis of skin cancer. Since dermatological evaluation is dependent on the expert, timeconsuming and subjective, automated systems are preferred by dermatologists to contribute to the decision-making processes. Detection of melanomas from skin lesion images accelerates the treatment process together with the early diagnosis of the disease and reduces the morbidity and mortality rates. In this study, the features of the lesion areas in the public ISIC 2017 dataset consisting of images taken from the skin area were examined and the images were classified as melanoma and nevus or seborrheic keratosis. Shape, color and texture features of the lesion areas were obtained to represent the lesion features of the melanoma data. Extracted features were classified by k-nearest neighbor, support vector machines, and ensemble learning classifiers which are easy ensemble, RUSBoost, balanced bagging and balanced random forest classifier. According to the obtained results, the best classification results were obtained with the RUSBoost Classifier with 100%, 99.17%, 99.33% and 99.58% sensitivity, specificity, accuracy and balanced accuracy values, respectively. The achieved results show that the proposed feature extraction and classification method has great potential for melanoma classification from lesion areas.

References

  • Bangare, S. L., Dubal, A., Bangare, P. S. ve Patil, S. T. (2015). Reviewing Otsu’s Method for Image Thresholding. International Journal of Applied Engineering Research, 10(9), 21777-21783.
  • Binder, M., Schwarz, M., Winkler, A., Steiner, A., Kaider, A., Wolff, K. ve Pehamberger, H. (1995). Epiluminescence Microscopy: A Useful Tool for The Diagnosis of Pigmented Skin Lesions for Formally Trained Dermatologists. Archives of Dermatology, 131(3), 286-291.
  • Breiman, L. (1996). Bagging Predictors. Machine Learning, 24(2), 123-140.
  • Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32.
  • Celebi, M. E., Kingravi, H. A., Uddin, B., Iyatomi, H., Aslandogan, Y. A., Stoecker, W. V. ve Moss, R. H. (2007). A Methodological Approach to The Classification of Dermoscopy Images. Computerized Medical Imaging and Graphics, 31(6), 362-373.
  • Celebi, M. E., Iyatomi, H., Stoecker, W. V., Moss, R. H., Rabinovitz, H. S., Argenziano, G. ve Soyer, H. P. (2008). Automatic Detection of Blue-White Veil and Related Structures in Dermoscopy Images. Computerized Medical Imaging and Graphics, 32(8), 670-677.
  • Celebi, M. E., Codella, N. ve Halpern, A. (2019). Dermoscopy Image Analysis: Overview and Future Directions. IEEE Journal of Biomedical and Health Informatics, 23(2), 474-478.
  • Chang, W. Y., Huang, A., Yang, C. Y., Lee, C. H., Chen, Y. C., Wu, T. Y. ve Chen, G. S. (2013). Computer-Aided Diagnosis of Skin Lesions Using Conventional Digital Photography: A Reliability and Feasibility Study. PloS one, 8(11), e76212.
  • Chen, C., Liaw, A. ve Breiman, L. (2004). Using Random Forest to Learn Imbalanced Data. Technical Report, Berkeley.
  • Cortes, C. ve Vapnik, V. (1995). Support Vector Machines. Machine Learning. 20, 273–297.
  • Ganster, H., Pinz, P., Rohrer, R., Wildling, E., Binder, M. ve Kittler, H. (2001). Automated Melanoma Recognition. IEEE Transactions on Medical Imaging, 20(3), 233-239.
  • Goodson, A. G. ve Grossman, D. (2009). Strategies for Early Melanoma Detection: Approaches to The Patient with Nevi. Journal of the American Academy of Dermatology, 60(5), 719-735.
  • Khouloud, S., Ahlem, M., Fadel, T., & Amel, S. (2022). W-net and inception residual network for skin lesion segmentation and classification. Applied Intelligence, 52(4), 3976-3994.
  • Lee, T., Ng, V., Gallagher, R., Coldman, A. ve McLean, D. (1997). Dullrazor®: A Software Approach to Hair Removal from Images. Computers in Biology and Medicine, 27(6), 533-543.
  • Li, Y. ve Shen, L. (2018). Skin Lesion Analysis Towards Melanoma Detection using Deep Learning Network. Sensors, 18(2), 556.
  • Liu, X. Y., Wu, J. ve Zhou, Z. H. (2008). Exploratory Undersampling for Class-Imbalance Learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 39(2), 539-550.
  • Messadi, M., Bessaid, A. ve Taleb-Ahmed, A. (2009). Extraction of Specific Parameters for Skin Tumour Classification. Journal of Medical Engineering & Technology, 33(4), 288-295.
  • Okur, E. Ve Turkan, M. (2018). A Survey on Automated Melanoma Detection. Engineering Applications of Artificial Intelligence, 73, 50-67.
  • Schapire, R. E. (1999, Temmuz). A Brief Introduction to Boosting. International Joint Conference on Artificial Intelligence (s. 1401-1406). Stockholm, İsveç.
  • Seiffert, C., Khoshgoftaar, T. M., Van Hulse, J. ve Napolitano, A. (2009). RUSBoost: A Hybrid Approach to Alleviating Class Imbalance. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 40(1), 185-197.
  • Sheha, M. A., Mabrouk, M. S. ve Sharawy, A. (2012). Automatic Detection of Melanoma Skin Cancer Using Texture Analysis. International Journal of Computer Applications, 42(20), 22-26.
  • Silveira, M., Nascimento, J. C., Marques, J. S., Marçal, A. R., Mendonça, T., Yamauchi, S., Maeda, J. ve Rozeira, J. (2009). Comparison of Segmentation Methods for Melanoma Diagnosis in Dermoscopy Images. IEEE Journal of Selected Topics in Signal Processing, 3(1), 35-45.
  • Thao, L.T., ve Quang, N.H. (2017). Automatic Skin Lesion Analysis Towards Melanoma Detection. 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems (s.106-111). Hanoi,Vietnam.
  • Tsao, H., Olazagasti, J. M., Cordoro, K. M., Brewer, J. D., Taylor, S. C., Bordeaux, J. S., Chren, M. -M., Sober, A. J., Tegeler, C., Bhushan, R. ve Begolka, W. S. (2015). Early Detection of Melanoma: Reviewing The ABCDEs. Journal of the American Academy of Dermatology, 72(4), 717-723.
  • Yılmaz, A., Kalebaşı, M., Samoylenko, Y., Güvenilir, M. E. ve Uvet, H. (2021). Benchmarking of Lightweight Deep Learning Architectures for Skin Cancer Classification using ISIC 2017 Dataset. arXiv preprint , vol.1, no.1, 1-2.
  • ISIC: https://challenge.isicarchive.com/, (Erişim Tarihi: 28 Nisan 2022).
  • ISIC2017: https://challenge.isic-archive.com/landing/2017/44/, (Erişim Tarihi: 28 Nisan 2022).
  • WHO: https://www.who.int/news-room/fact-sheets/detail/cancer, (Erişim Tarihi: 28 Nisan 2022).
  • SCF: https://www.skincancer.org/, (Erişim Tarihi: 28 Nisan 2022).
  • CDC: https://www.cdc.gov/cancer/skin/, (Erişim Tarihi: 28 Nisan 2022).
There are 30 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Elif Kanca 0000-0003-4273-9295

Selen Ayas 0000-0002-8226-2359

Publication Date December 15, 2022
Published in Issue Year 2022 Volume: 12 Issue: 2

Cite

APA Kanca, E., & Ayas, S. (2022). Dengesiz Veri Kümelerinde Topluluk Yöntemlerine Dayalı Melanom Sınıflandırılması. Karadeniz Fen Bilimleri Dergisi, 12(2), 1122-1137. https://doi.org/10.31466/kfbd.1113417