A new super resolution Faster R-CNN model based detection and classification of urine sediments

• Autorzy: Avci Derya , Sert Eser , Dogantekin Esin , Yildirim Ozal , Tadeusiewicz Ryszard , Plawiak Pawel

Identyfikatory

DOI

10.1016/j.bbe.2022.12.001

• Języki publikacji: EN

Abstrakty

EN

The diagnosis of urinary tract infections and kidney diseases using urine microscopy images has gained significant attention of medical community in recent years. These images are usually created by physicians’ own rule of thumb manually. However, this manual urine sediment analysis is usually labor-intensive and time-consuming. In addition, even when physicians carefully examine an image, an erroneous cell recognition may occur due to some optical illusions. In order to achieve cell recognition in low-resolution urine microscopy images with a higher level of accuracy, a new super resolution Faster Region-based Convolutional Neural Network (Faster R-CNN) method is proposed. It aims to increase resolution in low-resolution urine microscopy images using self-similarity based single image super resolution which was used during the pre-processing. Denoising based Wiener filter and Discrete Wavelet Transform (DWT) are used to de-noise high resolution images, respectively, to increase the level of accuracy for image recognition. Finally, for the feature extraction and classification stages, AlexNet, VGFG16 and VGG19 based Faster R-CNN models are used for the recognition and detection of multi-class cells. The model yielded accuracy rates are 98.6%, 96.4% and 96.2% respectively.

Słowa kluczowe

EN

Faster R-CNN; super resolution; urine sediment; discrete wavelet transform; DWT; Wiener filter

PL

super rozdzielczość; osad moczu; dyskretna transformata falkowa; DWT; filtr Wienera

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2023
• Tom: Vol. 43, no. 1
• Strony: 58--68
• Opis fizyczny: Bibliogr. 43 poz., rys., tab., wykr.

Twórcy

autor

Avci Derya

• Vocational School of Technical Sciences, Firat University, Elazig, Turkey

autor

Sert Eser

• Department of Computer Engineering, Malatya Turgut Özal University, Malatya, Turkey

autor

Dogantekin Esin

• Gaziantep Public Health Directorate, Gaziantep, Turkey

autor

Yildirim Ozal

• Department of Software Engineering, Firat University, Elazig, Turkey

autor

Tadeusiewicz Ryszard

• AGH University of Science and Technology, Department of Biocybernetics and Biomedical Engineering, Krakow, Poland

autor

Plawiak Pawel

• Department of Computer Science, Faculty of Computer Science and Telecommunications, Cracow University of Technology, Krakow, Poland
• Institute of Theoretical and Applied Informatics, Polish Academy of Sciences, Gliwice, Poland

Bibliografia

• [1] Liang Y, Tang Z, Yan M, Liu J. Object detection based on deep learning for urine sediment examination. Biocybern Biomed Eng 2018;38(3):661-70.
• [2] Li T, Jin D, Du C, Cao X, Chen H, Yan J, et al. The image-based analysis and classification of urine sediments using a LeNet-5 neural network. Computer Methods Biomech Biomed Eng: Imaging Visual 2020;8(1):109-14.
• [3] İnce FD, Ellidağ HY, Koseoğlu M, Simsek N, Yalçın H, Zengin MO. The comparison of automated urine analyzers with manual microscopic examination for urinalysis automated urine analyzers and manual urinalysis. Practical Lab Med 2016;5:14-20.
• [4] Avci D, Leblebicioglu MK, Poyraz M, Dogantekin E. A new method based on adaptive discrete wavelet entropy energy and neural network classifier (ADWEENN) for recognition of urine cells from microscopic images independent of rotation and scaling. J Med Syst 2014;38(2):7.
• [5] Liang Y, Fang B, Qian J, Chen L, Li C, Liu Y. False positive reduction in urinary particle recognition. Expert Syst Appl 2009;36(9):11429-38.
• [6] Shen ML, Zhang R. Urine sediment recognition method based on svm and adaboost. IEEE, in: 2009 International Conference on Computational Intelligence and Software Engineering, pp. 1-4.
• [7] Almadhoun MD, El-Halees A. Automated recognition of urinary microscopic solid particles. J Med Eng Technol 2014;38(2):104-10.
• [8] Too EC, Yujian L, Njuki S, Yingchun L. A comparative study of fine-tuning deep learning models for plant disease identification. Comput Electron Agric 2019;161:272-9.
• [9] Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks, in: Advances in neural information processing systems 2012, pp. 1097-1105.
• [10] Ren S, He K, Girshick R, Sun J. Faster r-cnn: Towards real-time object detection with region proposal networks, in: Advances in neural information processing systems, 2015, pp. 91-99.
• [11] Savelli B, Bria A, Molinara M, Marrocco C, Tortorella F. A multi-context CNN ensemble for small lesion detection. Artif Intell Med 2020;103 101749.
• [12] Özyurt F, Sert E, Avcı D. An expert system for brain tumor detection: Fuzzy C-means with super resolution and convolutional neural network with extreme learning machine. Med Hypotheses 2020;134 109433.
• [13] Özyurt F, Sert E, Avci E, Dogantekin E. Brain tumor detection based on Convolutional Neural Network with neutrosophic expert maximum fuzzy sure entropy. Measurement 2019;147 106830.
• [14] Sert E, Özyurt F, Doğantekin A. A new approach for brain tumor diagnosis system: single image super resolution based maximum fuzzy entropy segmentation and convolutional neural network. Med Hypotheses 2019;133 109413.
• [15] Zhang K, Wu Q, Liu A, Meng X. Can deep learning identify tomato leaf disease? Adv Multimed 2018.
• [16] Li P, Zhao W. Image fire detection algorithms based on convolutional neural networks. Case Stud Thermal Eng 2020;19 100625.
• [17] Zhao Y, Hao K, He H, Tang X, Wei B. A visual long-short-term memory based integrated CNN model for fabric defect image classification. Neurocomputing 2020;380:259-70.
• [18] Kang R, Liang Y, Lian C, Mao Y. CNN-based automatic urinary particles recognition, 2018. arXiv preprint arXiv:1803.02699.
• [19] Ji Q, Li X, Qu Z, Dai C. Research on urine sediment images recognition based on deep learning. IEEE Access 2019;7:166711-20.
• [20] Pan J, Jiang C, Zhu T. Classification of urine sediment based on convolution neural network, in: AIP Conf., vol. 1955, Apr. 2018, Art. no. 040176.
• [21] Zhang X, Chen G, Saruta K, Terata Y. Detection and classification of RBCs and WBCs in urine analysis with deep network, in: ACHI 2018 The Eleventh International Conference on Advances in Computer-Human Interactions, ACHI, 2018, pp. 194-198.
• [22] http://www.meddean.luc.edu/lumen/MedEd/MEDICINE/ PULMONAR/Renal/Atlas/urineatlas_f.htm (Access date May 2021).
• [23] https://www.klimud.org/public/atlas/idrar/web/meded.ucsd. edu/isp/1994/im-quiz/urine.htm (Access date May 2021).
• [24] https://www.shutterstock.com/tr/search/urine+sediment (Access date May 2021).
• [25] https://www.idexx.pl/files/sedivue-urine-sediment-guide. pdf (Access date May 2021).
• [26] https://www.idexx.com/files/urine-sediment-guide.pdf (Access date May 2021).
• [27] https://www.labce.com/urine-microscopic_old.aspx (Access date May 2021).
• [28] https://www.analyticon-diagnostics.com/downloads/flyer/ m2xfzr_en.pdf (Access date May 2021).
• [29] http://www.nephro-slovenia.si/images/pdf/urex/Urine_ sediment_particles.pdf (Access date May 2021).
• [30] https://www.nursing.arizona.edu/sites/default/files/2017% 20CSI%20Microscopy%20Sample%20Slides.pdf (Access date May 2021).
• [31] https://eclinpath.com/category/urinalysis/ (Access date May 2021).
• [32] http://www.medchem.upol.cz/en/URINE%20SEDIMENT.pdf (Access date May 2021).
• [33] Huang JB, Singh A, Ahuja N. Single image super-resolution from transformed self-exemplars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 5197-5206.
• [34] Jiang X, Wang N, Xin J, Yang X, Yu Y, Gao X. Image super-resolution via multi-view information fusion networks. Neurocomputing 2020;402:29-37.
• [35] Zhang J, Shao M, Yu L, Li Y. Image super-resolution reconstruction based on sparse representation and deep learning. Signal Process Image Commun 2020;87 115925.
• [36] Ekstrom MP. Realizable Wiener filtering in two dimensions. IEEE Trans Acoust, Speech, Signal Proc, ASSP 1982;30:31-40.
• [37] Park CR, Kang SH, Lee Y. Median modified Wiener filter for improving the image quality of gamma camera images. Nucl Eng Technol 2020;52(10):2328-33.
• [38] Akbar JM. Joint method using Akamatsu and discrete wavelet transform for image restoration. Appl Computing Informatics 2020.
• [39] Mohammed Siddeq. De-Noise Color or Gray level images by using Hybred DWT with Wiener filter (https:// www.mathworks.com/matlabcentral/fileexchange/33442-denoise-color-or-gray-level-images-by-using-hybred-dwt-withwiener-filter), MATLAB Central File Exchange. Retrieved May 18, 2020.
• [40] Ni S, Qian Q, Zhang R. Malware identification using visualization images and deep learning. Comput Secur 2018;77:871-85.
• [41] Scaife N, Carter H, Traynor P, Butler KR. Cryptolock (and drop it): stopping ransomware attacks on user data, in: 2016 IEEE 36th International Conference on Distributed Computing Systems (ICDCS), IEEE, pp. 303-312.
• [42] Namanya AP, Awan IU, Disso JP, Younas M. Similarity hash based scoring of portable executable files for efficient malware detection in IoT. Futur Gener Comput Syst 2020;110:824-32.
• [43] Vasan D, Alazab M, Wassan S, Safaei B, Zheng Q. Image-based malware classification using ensemble of CNN architectures (IMCEC). Comput Secur 2020;101748.

Uwagi

PL

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023)