Benzerlik Tabanlı Öğrenme Kullanarak Histopatolojik Görüntülerin Sınıflandırılması

Yıl 2024, Cilt: 14 Sayı: 2, 49 – 58, 30.07.2024

Mahmut Kaya Hasan Şakir Bilge

Öz

Benzerlik metriği öğrenme, bir uzaklık öğrenme yaklaşımı olup aynı sınıfa ait örnekler arasındaki benzerliği arttırmayı, farklı sınıflar arasındaki benzerliği ise azaltmayı hedeflemektedir. Son yıllarda derin öğrenmenin elde ettiği başarıyla beraber benzerlik metriği öğrenmenin derin ağ modellerinde başarıyla uygulanabileceği görülmüştür. Bu çalışmada derin metrik öğrenme modellerinden olan Siamese ve Triplet ağ modelleri kullanılarak histopatolojik görüntülerde bir sınıflandırma işlemi gerçekleştirilmiştir. Histopatolojik görüntüler radyologlar tarafından tanı amacıyla kullanılırken sağlıklı ve sağlıksız görüntülerini birbirinden ayırmak oldukça zorlayıcıdır. Bu çalışmada literatürde başarısını kanıtlamış olan transfer öğrenme yöntemleri derin metrik öğrenme modellerine entegre edilmiştir. Yapılan çalışma sonucunda Siamese+VGG19 ağ modelinde %95,39 başarı elde edilirken, Triplet+VGG19 ağ modelinde ise %96,92 sınıflandırma başarısı elde edilmiştir.

Anahtar Kelimeler

Benzerlik metriği öğrenme, siamese, triplet, sınıflandırma

Kaynakça

• [1] T. M. Mitchell, “Machine learning and data mining”. Communications of the ACM, 42(11), 30-36, 1999.
• [2] A. Géron, Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow, O'Reilly Media, Inc., 205, 2022.
• [3] A. Globerson ve S. Roweis. “Metric learning by collapsing classes”, Advances in neural information processing systems, 1-8, 2005.
• [4] F. Wang ve J. Sun, “Survey on distance metric learning and dimensionality reduction in data mining”, Data mining and knowledge discovery, 29(2), 534-564, 2015.
• [5] K. Q. Weinberger ve L. K. Saul, “Distance metric learning for large margin nearest neighbor classification”, Journal of machine learning research, 10, 207-244, 2009.
• [6] J. Schmidhuber, “Deep learning in neural networks: An overview”, Neural networks, 61, 85-117, 2015.
• [7] Y. LeCun, Y. Bengio ve G. Hinton, “Deep learning”,Nature, 521(7553), 436-444, 2015.
• [8] M. Kaya, ve H. Ş. Bilge, “Deep metric learning: A survey”, Symmetry, 11(9), 1066, 2019.
• [9] J. Lu, J. Hu ve J. Zhou, “Deep metric learning for visual understanding: An overview of recent advances”. IEEE Signal Processing Magazine, 34(6), 76-84, 2017.
• [10] R. Hadsell, S. Chopra ve Y. LeCun, “Dimensionality reduction by learning an invariant mapping”, IEEE computer society conference on computer vision and pattern recognition, 1735-1742, 2006.
• [11] E. Hoffer ve N. Ailon, “Deep metric learning using triplet network”, Similarity-Based Pattern Recognition: Third International Workshop, 84-92, 2015.
• [12] M. Peikari, M. J. Gangeh, J. Zubovits, G. Clarke ve A. L. Martel, “Triaging Diagnostically Relevant Regions from Pathology Whole Slides of Breast Cancer: A Texture Based Approach,” IEEE Transactions on Medical Imaging, 35(1), 307–315, 2016.
• [13] I. Goodfellow, Y. Bengio ve A. Courville, Deep learning. MIT press, 2016.
• [14] Y. Duan, J. Lu, J. Feng, ve J. Zhou, “Deep localized metric learning”, IEEE Transactions on Circuits and Systems for Video Technology, 28(10), 2644-2656, 2017.
• [15] G. Dai, J. Xie ve Y. Fang, “Deep correlated holistic metric learning for sketch-based 3D shape retrieval”, IEEE Transactions on Image Processing, 27(7), 3374-3386, 2018.
• [16] B. Harwood, V. Kumar BG, G. Carneiro, I. Reid, ve T. Drummond, “Smart mining for deep metric learning”, In Proceedings of the IEEE international conference on computer vision, 2821-2829, 2017.
• [17] E. Hoffer, ve N. Ailon, “Semi-supervised deep learning by metric embedding”, arXiv preprint arXiv:1611.01449, 2016.
• [18] S. Liao ve L. Shao, “Graph sampling based deep metric learning for generalizable person re-identification”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7359-7368, 2022.
• [19] K. A. Duncanson, S. Thwaites, D. Booth, G. Hanly, W. S. Robertson, E. Abbasnejad, ve D. Thewlis, “Deep metric learning for scalable gait-based person re-identification using force platform data”, Sensors, 23(7), 3392, 2023.
• [20] S. S. Faghih Imani, K. Fouladi‐Ghaleh, ve H. Aghababa, “Generalizable and efficient cross‐domain person re‐identification model using deep metric learning”, IET Computer Vision, 17(8), 993-1004, 2023.
• [21] S. M. Alizadeh, M. S. Helfroush, ve H. Müller, “A novel Siamese deep hashing model for histopathology image retrieval”, Expert Systems with Applications, 225, 120169, 2023.
• [22] X. Li, B. Yang, T. Chen, Z. Gao, ve H. Li, “Multiple instance learning-based two-stage metric learning network for whole slide image classification”, The Visual Computer, 1-16, 2023.
• [23] N. Hashimoto, Y. Takagi, H. Masuda, H. Miyoshi, K. Kohno, M. Nagaishi, … & I. Takeuchi, 2023, “Case-based similar image retrieval for weakly annotated large histopathological images of malignant lymphoma using deep metric learning”, Medical image analysis, 85, 102752, 2023.
• [24] Y. Jin, H. Lu, Z. Li, ve Y. Wang, “A cross-modal deep metric learning model for disease diagnosis based on chest x-ray images”, Multimedia Tools and Applications, 82(21), 33421-33442, 2023.
• [25] A. Zhong, X. Li, D. Wu, H. Ren, K. Kim, Y. Kim, … ve Q. Li, “Deep metric learning-based image retrieval system for chest radiograph and its clinical applications in COVID-19”, Medical Image Analysis, 70, 101993, 2021.
• [26] L. Liu, L. Huang, F. Yin ve Y. Chen, “Offline signature verification using a region based deep metric learning network”, Pattern Recognition, 118, 108009, 2021.
• [27] T. B. Viana, V. L. Souza, A. L. Oliveira, R. M. Cruz ve R. Sabourin, “A multi-task approach for contrastive learning of handwritten signature feature representations”, Expert Systems with Applications, 217, 119589, 2023.
• [28] G. Andresini, A. Appice ve D. Malerba, “Autoencoder-based deep metric learning for network intrusion detection”, Information Sciences, 569, 706-727, 2021.
• [29] Z. Wang, Z. Li, D. He ve S. Chan, “A lightweight approach for network intrusion detection in industrial cyber-physical systems based on knowledge distillation and deep metric learning”, Expert Systems with Applications, 206, 117671, 2022.
• [30] B. Mocanu, R. Tapu ve T. Zaharia, “Multimodal emotion recognition using cross modal audio-video fusion with attention and deep metric learning”, Image and Vision Computing, 133, 104676, 2023.
• [31] X. Chen, L. He, C. Xu, ve J. Liu, “Distance-dependent metric learning”. IEEE Signal Processing Letters, 26(2), 357-361, 2019.
• [32] V. S. Narayanaswamy, J. J. Thiagarajan, H. Song ve A. Spanias, “Designing an effective metric learning pipeline for speaker diarization”, IEEE International Conference on Acoustics, Speech and Signal Processing, 5806-5810, 2019.
• [33] M. Titford, The long history of hematoxylin. Biotechnic & histochemistry, 80(2), 73-78, 2005.
• [34] F. Serin, M. Erturkler, ve M. Gul, “A novel overlapped nuclei splitting algorithm for histopathological images”, Computer methods and programs in biomedicine, 151, 57-70, 2017.
• [35] S. J. Pan, ve Q. Yang, “A survey on transfer learning”, IEEE Transactions on knowledge and data engineering, 22(10), 1345-1359, 2009.
• [36] J. Lu, V. Behbood, P. Hao, H. Zuo, S. Xue, ve G. Zhang, “Transfer learning using computational intelligence: A survey”, Knowledge-Based Systems, 80, 14-23, 2015.
• [37] A. Krizhevsky, I. Sutskever ve G. Hinton, “Imagenet classification with deep convolutional neural networks”, Advances in neural information processing systems, 25, 2010.
• [38] K. Simonyan ve A. Zisserman, “Very deep convolutional networks for large-scale image recognition”, arXiv preprint arXiv:1409.1556, 2014.
• [39] K. He, X. Zhang, S. Ren ve J. Sun, “Deep residual learning for image recognition”, IEEE conference on computer vision and pattern recognition, 770-778, 2016.
• [40] G. Huang, Z. Liu, L. Van Der Maaten ve K. Q. Weinberger, “Densely connected convolutional networks”, IEEE conference on computer vision and pattern recognition, 4700-4708, 2017.
• [41] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, … ve H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications”, arXiv preprint arXiv:1704.04861, 2017.

Toplam 41 adet kaynakça vardır.

Ayrıntılar

Kaynak Göster

Download or read online: Click here