TIRNAK GÖRÜNTÜLERİNDEN HASTALIK TEŞHİSİ

Year 2022, , 464 - 470, 21.12.2022

Zuhal Can , Şahin Işık

https://doi.org/10.31796/ogummf.1111749

Abstract

Bu makale, insanların parmak ve tırnak görünümünün Darier hastalığı, Muehrcke çizgileri, alopesi areata, beau çizgileri, mavimsi tırnaklar ve çomaklaşma gibi çeşitli hastalıkların görüntü işleme ve derin öğrenme teknikleriyle teşhis edilmesine nasıl yardımcı olduğunu araştırıyor. 655 örnekle 17 farklı sınıftan oluşan genel bir veri seti kullandık. Eğitim, doğrulama ve test amaçları için yaygın olarak kullanılan bir kural olan 0.7:0.2:0.1'e dayanarak veri setini üç kata böldük. Yığın boyutu ve devirleri 32 ve 1000 olarak ayarlayarak Gürültülü-Öğrenci ağırlıklarını kullanarak EfficientNet-B2 modelini performans değerlendirme amacıyla test ettik. Model, tırnak hastalıklarını algılamak için test numunelerinden %72 doğruluk puanı ve %91 AUC puanı elde ediyor. Bu çalışmadaki deneysel bulgular, EfficientNet-B2 modelinin tırnak hastalığı tiplerini çok sayıda sınıf aracılığıyla kategorize edebileceğine dair yeni bir anlayışı doğrulamaktadır.

Keywords

EfficientNet, Derin öğrenme, Tahmin Uygulaması

DIAGNOSING DISEASES FROM FINGERNAIL IMAGES

Abstract

This paper investigates how people's finger and nail appearance helps diagnose various diseases, such as Darier's disease, Muehrcke's lines, alopecia areata, beau's lines, bluish nails, and clubbing, by image processing and deep learning techniques. We used a public dataset consisting of 17 different classes with 655 samples. We divided the dataset into three folds based on a widely used rule, the 0.7:0.2:0.1, for training, validation, and testing purposes. We tested the EfficientNet-B2 model for performance evaluation purposes by using Noisy-Student weights by setting the batch size and epochs as 32 and 1000. The model achieves a 72% accuracy score and 91% AUC score for test samples to detect fingernail diseases. The empirical findings in this study provide a new understanding that the EfficientNet-B2 model can categorize nail disease types through numerous classes.

Keywords

EfficientNet, Deep learning, Prediction application

References

• Albawi, Saad, Tareq Abed Mohammed, and Saad Al-Zawi. 2017. “Understanding of a Convolutional Neural Network.” Pp. 1–6 in 2017 international conference on engineering and technology (ICET).
• Chen, Hongming, Ola Engkvist, Yinhai Wang, Marcus Olivecrona, and Thomas Blaschke. 2018. “The Rise of Deep Learning in Drug Discovery.” Drug Discovery Today 23(6):1241–50.
• Deng, Yifan, Xinran Xu, Yang Qiu, Jingbo Xia, Wen Zhang, and Shichao Liu. 2020. “A Multimodal Deep Learning Framework for Predicting Drug--Drug Interaction Events.” Bioinformatics 36(15):4316–22.
• Esteva, Andre, Brett Kuprel, Roberto A. Novoa, Justin Ko, Susan M. Swetter, Helen M. Blau, and Sebastian Thrun. 2017. “Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks.” Nature 542(7639):115–18.
• Fangyu, L. I., and H. E. Hua. 2018. “Assessing the Accuracy of Diagnostic Tests.” Shanghai Archives of Psychiatry 30(3):207.
• Gayathri, S., D. C. Joy Winnie Wise, P. Baby Shamini, and N. Muthukumaran. 2020. “Image Analysis and Detection of Tea Leaf Disease Using Deep Learning.” Pp. 398–403 in 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC).
• Gustisyaf, Ahmad Ilham, and Ardiles Sinaga. 2021. “Implementation of Convolutional Neural Network to Classification Gender Based on Fingerprint.” International Journal of Modern Education & Computer Science 13(4).
• Kaggle. n.d. “Nail Dataset.” Retrieved (https://www.kaggle.com/datasets/reubenindustrustech/nail-dataset-new).
• Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. 2012. “Imagenet Classification with Deep Convolutional Neural Networks.” Advances in Neural Information Processing Systems 25.
• Lundervold, Alexander Selvikvåg, and Arvid Lundervold. 2019. “An Overview of Deep Learning in Medical Imaging Focusing on MRI.” Zeitschrift Für Medizinische Physik 29(2):102–27.
• Ravi, Daniele, Charence Wong, Fani Deligianni, Melissa Berthelot, Javier Andreu-Perez, Benny Lo, and Guang-Zhong Yang. 2016. “Deep Learning for Health Informatics.” IEEE Journal of Biomedical and Health Informatics 21(1):4–21.
• Tan, Mingxing, and Quoc Le. 2019. “Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks.” Pp. 6105–14 in International conference on machine learning.
• Watson, Cody, Nathan Cooper, David Nader Palacio, Kevin Moran, and Denys Poshyvanyk. 2022. “A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research.” ACM Transactions on Software Engineering and Methodology (TOSEM) 31(2):1–58.
• Yang, Xinfeng, Qiping Hu, and Shuaihao Li. 2020. “Recognition and Classification of Damaged Fingerprint Based on Deep Learning Fuzzy Theory.” Journal of Intelligent & Fuzzy Systems 38(4):3529–37.