Cilt Lezyonlarının Sınıflandırılmasında Derin Öğrenme Tabanlı Bir Yöntem

Yıl 2021, Cilt: 10 Sayı: 1, 30 - 36, 25.06.2021

Volkan Göreke

https://doi.org/10.46810/tdfd.797683

Cited By: 2

Öz

Cilt kanseri kötü huylu tümörlerin kontrolsüz çoğalması ile başlar. Dünya çapında sık karşılaşılan bir kanser türüdür. Uzman hekimler tarafından çıplak gözle incelemesi ve teşhis konulması güçtür. Bu yüzden bilgisayar destekli teşhis sistemleri hekimlere tanı koymada yardımcı olabilir. Bu sistemler günümüzde yapay zekanın bir türü olan derin sinir ağlarını yaygın olarak kullanır. Pek çok derin sinir ağı içeren çalışmada veri girişi olarak medikal görüntüler kullanılır. Ağ mimarisine bağlı olarak bu sistemler öznitelikleri kendi katmanlarında çıkarırlar. Bu çalışmada VGG16 ön eğitimli derin sinir ağı kullanılarak ilk önce ağ katmanlarından görüntülere ilişkin öznitelikler elde edilmiştir. Daha sonra yüksek miktarda veri içeren bu özniteliklerin boyutu azaltılmıştır. Böylece sınıflandırmada en iyi başarımı sağlayacak öznitelikler elde edilmiştir. Veri artırma algoritması kullanılarak elde edilen nümerik veri artırılmış ve CNN tür derin sinir ağında %96 sınıflandırma doğruluğu ve %100 AUC başarımı elde edilmiştir.

Anahtar Kelimeler

Cilt kanseri, derin sinir ağları, veri artırma

Kaynakça

• [1] Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019. CA Cancer Journal for Clinicians. 2019;69(1):7–34.
• [2] Jones OT, Jurascheck LC, Van Melle MA, Hickman S, Burrows NP, Hall PN, et al. Dermoscopy for melanoma detection and triage in primary care: A systematic review. BMJ Open. 2019;9.
• [3] Codella NCF, Gutman D, Celebi ME, Helba B, Marchetti MA, Dusza SW, et al. 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]. In: Internation Symposium Biomedecal Imaging. Washington, D.C 2018-April:p.168–172.
• [4] Matsunaga K, Hamada A, Minagawa A, Koga H. Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble. 2017;2–5. http://arxiv.org/abs/1703.03108
• [5] Guo S, Yang Z. Multi-Channel-ResNet: An integration framework towards skin lesion analysis. Informatics in Medicine Unlocked. 2018;12:67–74.
• [6] Chen S, Wang Z, Shi J, Liu B, Yu N. A multi-task framework with feature passing module for skin lesion classification and segmentation. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI). Washington, D.C. April 4-7, 2018.p.1126-1129.
• [7] Menegola A, Tavares J, Fornaciali M, Li LT, Avila S, Valle E. RECOD Titans at ISIC Challenge 2017. 2017;1–5. Available from: http://arxiv.org/abs/1703.04819.
• [8] Yang X, Li H, Wang L, Yeo SY, Su Y, Zeng Z. Skin Lesion Analysis by Multi-Target Deep Neural Networks. In: 2018 40 th Annual International Conference IEEE Eng Med Biol Soc EMBS. Honolulu, HI, USA 2018 July:p.1263–1266.
• [9] DeVries T, Ramachandram D. Skin Lesion Classification Using Deep Multi-scale Convolutional Neural Networks. 2017; http://arxiv.org/abs/1703.01402.
• [10] González-Díaz I. DermaKNet: Incorporating the Knowledge of Dermatologists to Convolutional Neural Networks for Skin Lesion Diagnosis. IEEE J Biomed Heal Informatics. 2019;23[2]:547–59.
• [11] Tang P, Liang Q, Yan X, Xiang S, Zhang D. GP-CNN-DTEL: Global-Part CNN Model with Data-Transformed Ensemble Learning for Skin Lesion Classification. IEEE J Biomed Heal Informatics. 2020:1–1.
• [12] Yang X, Zeng Z, Yeo SY, Tan C, Tey HL, Su Y. A Novel Multi-task Deep Learning Model for Skin Lesion Segmentation and Classification. https://arxiv.org/abs/1703.01025 2017;1–4.
• 13] Yadav SS, Jadhav SM. Deep convolutional neural network based medical image classification for disease diagnosis. Journal of Big Data. 2019;6(113).
• [14] Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Medical Image Analysis journal. 2017;42 :60–88.
• [15] Abraham B, Nair MS. ScienceDirect Computer-aided detection of COVID-19 from X-ray images using multi-CNN and Bayesnet classifier. Biocybernetics and Biomedical Engineering. 2020;1–10.
• [16] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 3rd Internation Conference Learn Represent ICLR 2015 - San Diego, CA, 2015;1–14.
• [17] Chollet F. Deep Learning with Phyton. Manning. 2018.
• [18] Janecek A, Gansterer WNW, Demel M, Ecker G. On the Relationship Between Feature Selection and Classification Accuracy. Fsdm. 2008:90–105.
• [19] Guda V, Golla M, Datta A. Performance Analysis of Learning Models on Medical Documents. IJIRT 2018;4(12):822–828.
• [20] Subho RH, Chowdhhury R,Chaki D,Islam S,Rahman D.A Univariate Feature Selection Approach for Finding Key Factors of Restaurant Business. In: 2019 IEEE Region 10 Symposium(TENSYMP). India, Kolkata: 2019;p.605-610.
• [21] Rashid KM, Louis J. Times-series data augmentation and deep learning for construction equipment activity recognition. Advanced Engineering Informatics. 2019;42:100944.
• [22] Lashgari E, Liang D, Maoz U. Data augmentation for deep-learning-based electroencephalography. Journal of Neuroscience Methods journal. 2020;346:108885.
• [23] Basic Data Augmentation & Feature Reduction [Internet]. Available from: https://www.kaggle.com/bigironsphere/basic-data-augmentation-feature-reduction.
• [24] Wong SC, Gatt A, Stamatescu V, McDonnell MD. Understanding Data Augmentation for Classification: When to Warp? 2016 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA). Gold Coast, QLD, Australia;2016.
• [25] Alakus TB, Turkoglu I. Comparison of deep learning approaches to predict COVID-19 infection. Chaos, Solitons and Fractals. 2020;140:110120.
• [26] Jauro F, Chiroma H, Gital AY, Almutairi M, Abdulhamid SM, Abawajy JH. Deep learning architectures in emerging cloud computing architectures: Recent development, challenges and next research trend. Applied Soft Computing Journal. 2020;96:106582.
• [27] Mumtaz W, Qayyum A. A deep learning framework for automatic diagnosis of unipolar depression. International Journal of Medical Informatics. 2019;132(103983).
• [28] Hajian-Tilaki K. Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Caspian Journal of Internal Medicine 2013;4(2):627–35.
• [29] Safari S, Baratloo A, Elfil M, Negida A. Evidence Based Emergency Medicine; Part 5 Receiver Operating Curve and Area under the Curve. Emergency 2016;4(2):111–3.
• [30] Roger P. Evaluating Information: Validity, Reliability, Accuracy, Triangulation. In: Research Methods in Politics;SAGE Press;2011;p.79-99
• [31] Dougherty E, Hua J, Sima C. Performance of Feature Selection Methods. Curr Genomics. 2009;10(6):365–74.
• [32] Dan Lo CT, Ordóñez P, Cepeda C. Feature selection and improving classification performance for malware detection. In: 2016 IEEE International Conference Big Data. Atlanta, GA, USA 2016;p.560–566.