Biyomedikal Görüntülerin Sınıflandırılmasında Temel Kapsül Ağ Mimarisinin Performansının Değerlendirilmesi

Year 2023, Volume: 9 Issue: 2, 238 - 247, 31.08.2023

Sümeyra Büşra Şengül , İlker Ali Ozkan

Abstract

Hastalıkların teşhis ve tedavisi için röntgen, bilgisayarlı tomografi (BT), mamografi, ultrason ve manyetik rezonans görüntüleme (MRI) gibi çeşitli görüntüleme teknikleri kullanılmaktadır. Bu medikal görüntülerin doğru analiz edilmesi, hastalığın erken teşhisi ve uygun tedavinin uygulanması için gereklidir. Görüntü analizinde ilgili alanın tanımlanması, büyüklüğü, konumu, yönü gibi bilgiler en iyi tedavi yöntemlerinin belirlenmesinde kritik öneme sahiptir. Evrişimli sinir ağı (CNN) mimarisi, tıbbi görüntü analizinde en yaygın kullanılan derin öğrenme mimarilerinden biridir. Ancak CNN görüntü özelliklerini çıkarırken bu özellikler arasındaki ilişkiyi ölçmekte yetersiz kalmakta, poz (konum, yön, boyut), deformasyon, doku gibi özellikleri gizleyememektedir. Temel Kapsül Ağı (CapsNet) Mimarisi, CNN'in bu dezavantajlarını aşmak ve başarısını artırmak için önerilmiştir. Bu çalışmada tıbbi görüntülerden oluşan MedMNIST veri seti topluluğu kullanılmıştır. CapsNet mimarisinin sınıflandırma performansını değerlendirmek için MedMNIST'te yer alan RetinaMNIST, BreastMNIST ve OrganMNIST-A veri kümeleri kullanılmıştır. Capsnet bu veri setleri üzerinde sırasıyla %54, %83 ve %89 doğruluk elde etmiştir. CapsNet' in gelişmiş CNN modellerine yakın sonuçlar aldığı görülmüştür.

Keywords

CapsNet, Res-Net, Evrişimli Sinir Ağları, Kapsül Ağlar, Medikal Görüntü Analizi

Performance Evaluation of Basic Capsule Network Architecture in Classification of Biomedical Images

Abstract

In order to diagnose and treat diseases, a variety of imaging techniques are used, including X-ray, computed tomography (CT), mammography, ultrasound, and magnetic resonance imaging (MRI). Correct analysis of these medical images is required for early disease detection and application of the appropriate treatment. In image analysis, the identification of the relevant area, as well as information such as its size, location, and direction, are critical in determining the best treatment methods. The convolutional neural network (CNN) architecture is one of the most widely used deep learning architectures in medical image analysis. However, it was stated that CNN was insufficient to measure the relationship between these features while extracting image features, and it could not hide features such as pose (position, direction, size), deformation, and texture. The Basic Capsule Network (CapsNet) Architecture was proposed to overcome CNN's disadvantage and increase success. In this study, MedMNIST dataset collection consisting of medical images was used. The RetinaMNIST, BreastMNIST, and OrganMNIST-A datasets included in MedMNIST were used to evaluate the classification performance of the CapsNet architecture. Capsnet succeeded in these with accuracy rates of 54%, 83%, and 89%, respectively. CapsNet has been shown to produce comparable results to advanced CNN models.

Keywords

CapsNet, Res-Net, Convolutional Neural Networks, Capsule Networks, Medical Image Analysis

References

• [1] K. Raza and N. K. Singh, “A Tour of Unsupervised Deep Learning for Medical Image Analysis,” Current Medical Imaging Reviews, vol. 17, no. 9, pp. 1059–1077, Sep. 2021. doi:10.2174/1573405617666210127154257
• [2] S. M. Anwar, M. Majid, A. Qayyum, M. Awais, M. Alnowami, and M. K. Khan, “Medical Image Analysis using Convolutional Neural Networks: A Review,” Journal of Medical Systems, vol. 42, no. 11, p. 226, Oct. 2018. doi:10.1007/s10916-018-1088-1
• [3] M. M. Qanbar and S. Taşdemir, “Detection of Malaria Diseases with Residual Attention Network,” International Journal of Intelligent Systems and Applications in Engineering, vol. 7, no. 4, pp. 238–244, Dec. 2019. doi:10.18201/ijisae.2019457677
• [4] M. Kwabena Patrick, A. Felix Adekoya, A. Abra Mighty, and B. Y. Edward, “Capsule Networks – A survey,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 1, pp. 1295–1310, Jan. 2022. doi: 10.1016/j.jksuci.2019.09.014
• [5] D. Kirbaş, “İntraserebral Kanamanın Tıbbi Tedavisi,” Dusunen Adam The Journal of Psychiatry and Neurological Sciences, vol. 7, no. 4, p. 54, 1994.
• [6] S. Sabour, N. Frosst, and G. Hinton, “Dynamic Routing Between Capsules”, in 31st Conference on Neural Information Processing Systems (NIPS 2017), 4-9 Dec 2017, [Online]. Available: https://proceedings.neurips.cc. [Accessed: 13 Agust 2023].
• [7] X. Zhang and S.-G. Zhao, “Fluorescence microscopy image classification of 2D HeLa cells based on the CapsNet neural network,” Medical & Biological Engineering & Computing, vol. 57, no. 6, pp. 1187–1198, Jun. 2019. doi:10.1007/s11517-018-01946-z
• [8] P. Afshar, A. Mohammadi, and K. N. Plataniotis, “Brain Tumor Type Classification Via Capsule Networks,” in 2018 25th IEEE International Conference on Image Processing (ICIP), Oct. 2018, Athens, Greece. [Online]. Available: https://ieeexplore.ieee.org/document/8451379. [Accessed: Aug. 13, 2023].
• [9] A. Sezer and H.B. Sezer, “Capsule Network-Based Classification Of Rotator Cuff Pathologies From MRI,” Computers & Electrical Engineering, vol. 80, pp. 106480, Dec. 2019. doi: 10.1016/j.compeleceng.2019.106480
• [10] J. Gaddipati, A. Desai, J. Sivaswamy and K. A. Vermeer, "Glaucoma Assessment From OCT İmages Using Capsule Network", in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul. 2019, Berlin, Germany. [Online]. Available: https://ieeexplore.ieee.org/document/8857493. [Accessed: Aug. 13, 2023].
• [11] G. Kumar, S. Chatterjee, and C. Chattopadhyay, “DRISTI: A Hybrid Deep Neural Network For Diabetic Retinopathy Diagnosis,” Signal Image Video Process, vol. 15, no. 8, pp. 1679–1686, Apr. 2021. doi: 10.1007/s11760-021-01904-7
• [12] G. Madhu et al., “Imperative Dynamic Routing Between Capsules Network for Malaria Classification,” Computers, Materials & Continua, vol. 68 no.1, pp. 903-919, Mar. 2021. doi:10.32604/cmc.2021.016114
• [13] J. Yang, R. Shi and B. Ni, "MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis," in 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Apr. 2021, Nice, France. [Online]. Available: https://arxiv.org/abs/2010.14925. [Accessed: Aug. 13, 2023].
• [14] G. E. Hinton, S. Sabour, and N. Frosst, “Matrix capsules with EM routing,” International Conference on Learning Representations, 30 April- 3 May. 2018. [Online]. Available: https://openreview.net/ [Accessed: Aug. 13, 2023].
• [15] R. Liu et al., “DeepDRiD: Diabetic Retinopathy—Grading and Image Quality Estimation Challenge,” Patterns, vol. 3, no. 6, p. 100512, Jun. 2022. doi:10.1016/j.patter.2022.100512
• [16] W. Al-Dhabyani, M. Gomaa, H. Khaled, and A. Fahmy, “Dataset Of Breast Ultrasound İmages,” Data in Brief, vol. 28, pp. 104863, Feb. 2020. doi:10.1016/j.dib.2019.104863
• [17] P. Bilic et al., “The Liver Tumor Segmentation Benchmark (Lits),” Medical Image Analysis, vol. 84, pp. 102680, Feb. 2023. doi:10.1016/j.media.2022.102680
• [18] M. Sokolova and G. Lapalme, “A Systematic Analysis Of Performance Measures For Classification Tasks,” Information Processing and Management, vol. 45, no. 4, pp. 427–437, July 2009. doi: 10.1016/j.ipm.2009.03.002
• [19] X. Guo, “CapsNet-Keras.” Aug. 10, 2023. Accessed: Aug. 13, 2023. [Online]. Available: https://github.com/XifengGuo/CapsNet-Keras
• [20] D. Adla, G. V. R. Reddy, P. Nayak, G. Karuna, “Deep Learning-Based Computer Aided Diagnosis Model For Skin Cancer Detection And Classification,” Distrib and Parallel Databases, vol. 40, no. 4, pp. 717–736, Dec. 2022. doi: 10.1007/s10619-021-07360-z
• [21] T. Kavitha et. al., “Deep Learning Based Capsule Neural Network Model for Breast Cancer Diagnosis Using Mammogram Images,” Interdisciplinary Sciences: Computational Life Sciences, vol. 14, no. 1, pp. 113–129, Mar. 2022. doi:10.1007/s12539-021-00467-y
• [22] R. LaLonde, P. Kandel, C. Spampinato, M. B. Wallace and U. Bagci, "Diagnosing Colorectal Polyps in the Wild with Capsule Network", in 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Apr. 2020, Iowa, USA. [Online]. Available: https://arxiv.org/abs/2001.03305. [Accessed: Aug. 13, 2023].
• [23] S. C. Satapathy, M. Cruz, A. Namburu, S. Chakkaravarthy, and M. Pittendreigh, “Skin Cancer classification using Convolutional Capsule Network (CapsNet),” Journal of Scientific & Industrial Research, vol. 79, no. 11, Art. no. 11, Apr. 2020. doi:10.56042/jsir.v79i11.35913
• [24] M. Ali and R. Ali, “Multi-Input Dual-Stream Capsule Network for Improved Lung and Colon Cancer Classification,” Diagnostics, vol. 11, no. 8, pp.1485, Aug. 2021. doi: 10.3390/diagnostics11081485
• [25] C. Peng, Y. Zheng, and D.-S. Huang, “Capsule Network Based Modeling of Multi-omics Data for Discovery of Breast Cancer-Related Genes,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 17, no. 5, pp. 1605–1612, Sep. 2020. doi:10.1109/TCBB.2019.2909905
• [26] F. Xue and J. Jiang, “Dynamic Enhanced Magnetic Resonance Imaging versus Ultrasonic Diffused Optical Tomography in Early Diagnosis of Breast Cancer,” Journal of Healthcare Engineering, vol. 2022, p. e4834594, Apr. 2022, doi: 10.1155/2022/4834594
• [27] Y. A. Üncü, G. Sevim, and M. Canpolat, “Approaches to preclinical studies with heterogeneous breast phantom using reconstruction and three-dimensional image processing algorithms for diffuse optical imaging,” International Journal of Imaging Systems and Technology, vol. 32, no. 1, pp. 343–353, 2022. doi: 10.1002/ima.22648
• [28] Y. A. Üncü, G. Sevim, T. Mercan, V. Vural, E. Durmaz, and M. Canpolat, “Differentiation of tumoral and non-tumoral breast lesions using back reflection diffuse optical tomography: A pilot clinical study,” International Journal of Imaging Systems and Technology, vol. 31, no. 4, pp. 2023–2031, 2021. doi: 10.1002/ima.22578
• [29] K. M. S. Uddin, M. Zhang, M. Anastasio, and Q. Zhu, “Optimal breast cancer diagnostic strategy using combined ultrasound and diffuse optical tomography,” Biomed. Opt. Express, BOE, vol. 11, no. 5, pp. 2722–2737, May 2020. doi: 10.1364/BOE.389275
• [30] E. Y. Chae et al., “Development of digital breast tomosynthesis and diffuse optical tomography fusion imaging for breast cancer detection,” Scientific Reports, vol. 10, no. 1, Art. no. 1, Aug. 2020. doi:10.1038/s41598-020-70103-0
• [31] M. Yeo et al., “Review of deep learning algorithms for the automatic detection of intracranial hemorrhages on computed tomography head imaging,” Journal of NeuroInterventional Surgery, vol. 13, no. 4, pp. 369–378, Apr. 2021. doi: 10.1136/neurintsurg-2020-017099
• [32] T. Danişman et al., “Predıctıng The Locatıon Of The Uterıne Cervıcal Os From 2d Images Wıth Cnn” JESD, vol. 8, no. 5, Art. no. 5, Dec. 2020. doi: 10.21923/jesd.828457
• [33] S. S. Yadav and S. M. Jadhav, “Deep convolutional neural network based medical image classification for disease diagnosis,” J Big Data, vol. 6, no. 1, p. 113, Dec. 2019, doi: 10.1186/s40537-019-0276-2.