بازیابی تصاویر پزشکی ریه با استفاده از درهم سازی با ناظر، انتخاب ویژگی mRMR و شبکه‌های عصبی کانولوشنی عمیق

نوع مقاله : مقاله پژوهشی فارسی

نویسندگان

گروه کامپیوتر، واحد اصفهان (خوراسگان)، دانشگاه آزاد اسلامی، اصفهان، ایران

چکیده

توسعه پزشکی نوین از یک طرف امکان ذخیره‌سازی تصاویر پزشکی را فراهم کرده است و از طرف دیگر بدلیل افزایش روزانه ذخیره‌سازی این قبیل داده، مدیریت و بازیابی آن‌ها را نیز با مشکل مواجه ساخته است. با توجه به آنکه تصاویر پزشکی به عنوان ابزاری قدرتمند در تشخیص زودرس اغلب بیماری‌ها مورد استفاده هستند، ارائه سیستمی توانمند که بتواند از حجم رو به رشد تصاویر پزشکی، تصاویری با محتوای مشابه را بازیابی نماید، در کنترل و درمان بسیار موثر است. در این مقاله یک سیستم بازیابی تصاویر پزشکی مبتنی بر شبکه عصبی سیامی متشکل از دو زیر شبکه کانولوشن با 13 لایه ارائه شده است. برای رسیدن به زیر مجموعه بهینه از ویژگی‌های عمیق استخراج شده توسط سیامی، از تکنیک حداقل افزونگی- حداکثر همبستگی (mRMR) استفاده شده است و پس از درهم‌سازی باینری ویژگی‌ها، بازیابی تصاویر مشابه با استفاده از فاصله Hamming انجام می‌شود. اگر چه مدل مطرح قابلیت بازیابی انواع تصاویر پزشکی سطح خاکستری را دارد، اما برای ارزیابی آن، از دو نوع تصاویر ریه، شامل تصاویر سی‌تی اسکن بیماران کووید-19 در پایگاه داده CT-COV و تصاویر اشعه X بیماران ذات‌الریه در پایگاه Pneumonia استفاده شده است. نتایج حاکی از آن است که روش پیشنهاد شده در پایگاه کووید به ترتیب در 5 و 10 تصویر بازیابی توانسته است به میانگین دقت 93.83‌% و 92.73‌% و در پایگاه داده ذات‌الریه به میانگین دقت 100‌% دست یابد که در مقایسه با روش‌های پیشین توانسته است بازیابی تصاویر ریه را بهبود ببخشد.

کلیدواژه‌ها


[1] H. H. Bhatt and A. P. Mankodia, "A Comprehensive Review on Content-Based Image Retrieval System: Features and Challenges," Data Science Intelligent Applications, vol. 52, pp. 63-74, 2021.
[2] K. Wanjale, T. Borawake, and S. Chaudhari, "Content based image retrieval for medical images techniques and storage methods-review paper," IJCA Journal, vol. 1, no. 19, pp. 105-107, 2010.
[3] T. W. Cai, J. Kim, and D. D. Feng, "Content-based medical image retrieval," in Biomedical information technology: Elsevier, 2008, pp. 83-113.
[4] A. Kumar, J. Kim, W. Cai, M. Fulham, and D. Feng, "Content-based medical image retrieval: a survey of applications to multidimensional and multimodality data," Journal of digital imaging, vol. 26, no. 6, pp. 1025-1039, 2013.
[5] H. A. Al-Jubouri, "Content-based image retrieval: Survey," Journal of Engineering Sustainable Development, vol. 23, no. 03, pp. 42-63, 2019.
[6] C. B. Akgül, D. L. Rubin, S. Napel, C. F. Beaulieu, H. Greenspan, and B. Acar, "Content-based image retrieval in radiology: current status and future directions," Journal of digital imaging, vol. 24, no. 2, pp. 208-222, 2011.
[7] P. Das and A. Neelima, "An overview of approaches for content-based medical image retrieval," International journal of multimedia information retrieval, vol. 6, no. 4, pp. 271-280, 2017.
[8] M. Alkhawlani, M. Elmogy, and H. El Bakry, "Text-based, content-based, and semantic-based image retrievals: a survey," International Journal of Computer and Information Technology, vol. 4, no. 01, pp. 58-66, 2015.
[9] J. Bromley et al., "Signature verification using a “siamese” time delay neural network," International Journal of Pattern Recognition and Artificial Intelligence, vol. 7, no. 04, pp. 669-688, 1993.
[10] D. Chicco, "Siamese neural networks: An overview," Artificial Neural Networks, pp. 73-94, 2021.
[11] J. Bromley, I. Guyon, Y. LeCun, E. Säckinger, and R. Shah, "Signature verification using a" siamese" time delay neural network," Advances in neural information processing systems, pp. 737-737, 1994.
[12] P. Baldi and Y. Chauvin, "Neural networks for fingerprint recognition," neural computation, vol. 5, no. 3, pp. 402-418, 1993.
[13] A. Mehmood, M. Maqsood, M. Bashir, and Y. Shuyuan, "A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease," Brain Sciences, vol. 10, no. 2, pp. 1-15, 2020.
[14] G. Koch, R. Zemel, and R. Salakhutdinov, "Siamese neural networks for one-shot image recognition," in ICML deep learning workshop, 2015, vol. 2: Lille, pp. 1-30.
[15] W. Rawat and Z. Wang, "Deep convolutional neural networks for image classification: A comprehensive review," Neural computation, vol. 29, no. 9, pp. 2352-2449, 2017.
[16] W. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu, and F. Alsaadi, "A survey of deep neural network architectures and their applications," Neurocomputing, vol. 234, pp. 11-26, 2017.
[17] N. Malviya, N. Choudhary, and K. Jain, "Content based medical image retrieval and clustering based segmentation to diagnose lung cancer," Advances in Computational Sciences and Technology, vol. 10, no. 6, pp. 1577-1594, 2017.
[18] K. A. Gladis, "Integration of global and local features based on hybrid similarity matching scheme for medical image retrieval system," nternational Journal of Biomedical Engineering and Technology, vol. 31, no. 3, pp. 292-314, 2019.
[19] Y. Cai, Y. Li, C. Qiu, J. Ma, and X. Gao, "Medical image retrieval based on convolutional neural network and supervised hashing," IEEE Access, vol. 7, pp. 51877-51885, 2019.
[20] H. Kasban, D. Salama, and Applications, "A robust medical image retrieval system based on wavelet optimization and adaptive block truncation coding," Multimedia Tools and Applications, vol. 78, no. 24, pp. 35211-35236, 2019.
[21] N. F. Haq, M. Moradi, and Z. J. Wang, "A Deep Community Based Approach for Large Scale Content Based X-Ray Image Retrieval," Medical Image Analysis,, vol. 68, pp. 1-16, 2020.
[22] K. France and A. Jaya, "Classification and retrieval of thoracic diseases using patch-based visual words: a study on chest x-rays," Biomedical Physics & Engineering Express, vol. 6, no. 2, pp. 1-9, 2020.
[23] H. J. Hwang et al., "Content-Based Image Retrieval of Chest CT with Convolutional Neural Network for Diffuse Interstitial Lung Disease: Performance Assessment in Three Major Idiopathic Interstitial Pneumonias," Korean Journal of Radiology, vol. 22, no. 2, pp. 281-290, 2020.
[24] A. Sze-To and H. Tizhoosh, "Searching for Pneumothorax in Half a Million Chest X-Ray Images," in International Conference on Artificial Intelligence in Medicine, 2020: Springer, pp. 453-462.
[25] N. Darapureddy, N. Karatapu, and T. K. Battula, "Optimal weighted hybrid pattern for content based medical image retrieval using modified spider monkey optimization," 2020.
[26] B. Renita and S. Christopher, "Novel real time content based medical image retrieval scheme with GWO-SVM," Multimed Tools Application, vol. 79, pp. 1-17, 2020.
[27] K. Chethan and R. Bhandarkar, "An Efficient Medical Image Retrieval and Classification using Deep Neural Network," Indian Journal of Science and Technology, vol. 13, no. 39, pp. 4127-4141, 2020.
[28] P. Haripriya and R. Porkodi, "Parallel deep convolutional neural network for content based medical image retrieval," Journal of Ambient Intelligence and Humanized Computing, vol. 12, no. 1, pp. 781-795, 2021.
[29] N. F. Haq, M. Moradi, and Z. J. Wang, "A deep community based approach for large scale content based X-ray image retrieval," Medical Image Analysis, vol. 68, p. 101847, 2021.
[30] B. Hu, B. Vasu, and A. Hoogs, "X-MIR: EXplainable Medical Image Retrieval," in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 440-450.
[31] R. Pinapatruni and S. B. Chigarapalle, "Adversarial image reconstruction learning framework for medical image retrieval," Signal, Image and Video Processing, pp. 1-8, 2022.
[32] P. Hanchuan, L. Fuhui, and C. Ding, "Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 8, pp. 1226-1238, 2005, doi: 10.1109/TPAMI.2005.159.
[33] J. Zhao, Y. Zhang, X. He, and P. Xie, "COVID-CT-Dataset: a CT scan dataset about COVID-19," Machine Learning, pp. 1-14, 2020.
[34] Z. I. Amanullah Asraf. COVID19, Pneumonia and Normal Chest X-ray PA Dataset. [Online]. Available: https://data.mendeley.com/datasets/jctsfj2sfn/1