[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
research-article

Ensemble of fine‐tuned convolutional neural networks for urine sediment microscopic image classification

Published: 20 January 2020 Publication History

Abstract

In this study, an ensemble of fine‐tuned convolutional neural networks (CNNs) is proposed. As CNN training requires large annotated data, which are lacking in the field of urine sediment microscopic image processing, the authors first pre‐trained the CNNs, including ResNet50 and GoogLeNet, and developed AlexNet on an ImageNet dataset. Thereafter, some of the weights of the pre‐trained CNNs were transferred to the urine sediment microscopic image dataset. To guide fine‐tuning of the learning rate and cascading features, the hierarchical nature of features in different convolutional layers was investigated by visualising the CNN. Then, they combined three CNNs as an ensemble of CNNs to decrease the differences and impurity interference among features of urine sediment microscopic image. These fusion features were employed to train the fully connected neural network for classification. In this study, they improved the accuracy of each CNN by an average of 2.2% through fine‐tuning of the learning rate and cascading features. Moreover, the better experimental results were achieved compared with other state‐of‐the‐art methods and indicated that a 97% classification accuracy can be attained.

6 References

[1]
Koye, D.N., Magliano, D.J., Nelson, R.G., et al: ‘The global epidemiology of diabetes and kidney disease’, Adv. Chronic Kidney Dis., 2018, 25, (2), pp. 121–132
[2]
Baños‐Laredo, M.E., Núñez‐Álvarez, C.A., Cabiedes, J.: ‘Urinary sediment analysis’, Reumatología Clín., 2010, 6, (5), pp. 268–272
[3]
Perazella, M.A.: ‘The urine sediment as a biomarker of kidney disease’, Am. J. Kidney Diseases, 2015, 66, (5), pp. 748–755
[4]
Jooyoung, C., Jin, O.K., Chan, J.B., et al: ‘Coparison of five automated urine sediment analyzers with manual microscopy for accurate identification of urine sediment’, Clin. Chem. Lab. Med., 2019, 57, (11), pp. 1744–1753
[5]
Avci, D., Leblebicioglu, M.K., Poyraz, M.: ‘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), pp. 1–9
[6]
Li, C., Tang, Y.Y., Luo, H.: ‘Join Gabor and scattering transform for urine sediment particle texture analysis’. 2nd Int. Conf. on Cybernetics (CYBCONF), Gdynia, Poland, 2015, pp. 410–415
[7]
LeCun, Y., Kavukcuoglu, K., Farabet, C.: ‘Convolutional networks and applications in vision’. 2010 IEEE Int. Symp. Circuits System, Paris, France, 2010, pp. 253–256
[8]
LeCun, Y., Bengio, Y., Hinton, G.: ‘Deep learning’, Nature, 2015, 521, pp. 436–444
[9]
Gautam, S.N.S., Pradhan, D.K., Chhipa, P.C.: ‘MicroGAN: size‐invariant learning of GAN for super‐resolution of microscopic images’. MICCAI Work., Shenzhen, China, 2019
[10]
Li, T., Jin, D., Du, C., et al: ‘The image‐based analysis and classification of urine sediments using a LeNet‐5 neural network’, Comput. Methods Biomech. Biomed. Eng. Imaging Vis., 2019, pp. 1–6
[11]
Schmidhuber, J.: ‘Deep learning in neural networks: an overview’, Neural Netw., 2015, 61, pp. 85–117
[12]
Zeiler M, D., Fergus, R.: ‘Visualizing and understanding convolutional networks’. Computer Vision – ECCV, Zurich, Switzerland, 2014, pp. 818–833
[13]
Shelhamer, E., Long, J., Darrell, T.: ‘Fully convolutional networks for semantic segmentation’. 2015 IEEE Conf. on Computer Vision and Pattern Recognition, Boston, USA, 2015, pp. 3431–3440
[14]
Ronneberger, O., Fischer, P., Brox, T.: ‘U‐Net: convolutional networks for biomedical image segmentation’. Int. Conf. on Medical Image Computing and Computer Assisted Intervention, Munich, Germany, 2015, pp. 234–241
[15]
Woo, S., Kim, D., Cho, D.: ‘Linknet: relational embedding for scene graph’, 2018
[16]
Phan, H.T.H., Kumar, A., Kim, J.: ‘Transfer learning of A convolutional neural network for HEP‐2 cell image classification’. 2016 IEEE 13th Int. Symp. on Biomedical, Prague, Czech Republic, 2016, pp. 1208–1211
[17]
Sawada, Y., Kozuka, K.: ‘Transfer learning method using multi‐prediction deep Boltzmann machines for a small scale dataset’. 14th IAPR Int. Conf. on Machine Vision Applications, Tokyo, Japan, 2015, pp. 110–113
[18]
Pan, S.J., Yang, Q.: ‘A survey on transfer learning’, IEEE Trans. Knowl. Data Eng., 2010, 22, (10), pp. 1345–1359
[19]
Wahab, N., Khan, A., Lee, Y.S.: ‘Two‐phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detection’, Comput. Biol. Med., 2017, 85, pp. 86–97
[20]
Xiao, Y., Wu, J., Lin, Z., et al: ‘A deep learning‐based multi‐model ensemble method for cancer prediction’, Comput. Methods Programs Biomed., 2018, 153, pp. 1–9
[21]
Vogado, H.S., Veras, M.S., Araujo, H.D., et al: ‘Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification’, Eng. Appl. Artif. Intell., 2018, 72, pp. 415–422
[22]
Hailiang, L., Jian, W., Yujian, S., et al: ‘An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images’, Sci. Rep., 2018, 8, pp. 1–12
[23]
Hailiang, L., Yongqian, H., Zhijun, Z.: ‘An improved faster R‐CNN for same object retrieval’, IEEE. Access., 2017, 5, pp. 13655–13676
[24]
Yixiong, L., Rui, K., Chunyan, L., et al: ‘An end‐to‐end system for automatic urinary particle recognition with convolutional neural network’, J. Med. Syst., 2018, 42, (9), p. 104
[25]
Xu, X., Zhang, J., Chen, P., et al: ‘Urine sediment detection based on deep learning’. Int. Conf. on Intelligent Computing, 2019, pp. 543–552
[26]
Shin, H.C., Roth, H.R., Gao, M., et al: ‘Deep convolutional neural networks for computer‐aided detection: CNN architectures, dataset characteristics and transfer learning’, IEEE Trans. Med. Imaging, 2016, 35, pp. 1285–1298
[27]
Chen, H., Ni, D., Qin, J., et al: ‘Standard plane localization in fetal ultrasound via domain transferred deep neural networks’, IEEE J. Biomed. Health Inf., 2015, 19, pp. 1627–1636
[28]
Lopes, U.K., Valiati, J.F.: ‘Pre‐trained convolutional neural networks as feature extractors for tuberculosis detection’, Comput. Biol. Med., 2017, 89, pp. 135–143
[29]
Rasti, R., Teshnehlab, M., Phung, S.L.: ‘Breast cancer diagnosis in DCE‐MRI using mixture ensemble of convolutional neural networks’, Pattern Recognit., 2017, 72, pp. 381–390
[30]
Kumar, A., Kim, J., Lyndon, D.: ‘An ensemble of fine‐tuned convolutional neural networks for medical image classification’, IEEE J. Biomed. Health Inf., 2017, 21, (1), pp. 31–40
[31]
Akilan, T., Jonathan Wu, Q.M., Yimin, Y.: ‘Fusion of transfer learning features and its application in image classification’. IEEE 30th Canadian Conf. on Electrical and Computer Engineering, Windsor, Ontario, Canada, 2017
[32]
Szegedy, C., Vanhoucke, V.: ‘Going deeper with convolutions’. IEEE Conf. Comput. Vis. Pattern Recognit, Boston, USA, 2015, pp. 1–9
[33]
He, K., Zhang, X.: ‘Deep residual learning for image recognition’. IEEE Conf. Comput. Vis. Pattern Recognit, Las Vegas, NV, USA, 2016, pp. 770–778
[34]
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘Imagenet classification with deep convolutional neural networks’. Proc. Adv. Neural Inf. Process. Syst., Lake Tahoe, 2012, pp. 1097–1105
[35]
Mishkin, D., Sergievskiy, N., Matas, J.: ‘Systematic evaluation of convolution neural network advances on the imagenet’, Comput. Vis. Image Underst., 2017, 161, pp. 11–19
[36]
LeCun, Y., Boser, B., Denker, J.S., et al: ‘Back propagation applied to handwritten zip code recognition’, Neural Comput., 1989, 1, (4), pp. 541–551
[37]
Jason, Y., Jeff, C., Yoshua, B., et al: ‘How transferable are features in deep neural networks’, Adv. Neural Inf. Process. Syst., 2014, 1, (4), pp. 3320–3328
[38]
Zeiler, M., Taylor, G., Fergus, R.: ‘Adaptive deconvolutional networks for mid and high level feature learning’. 2011 Int. Conf. on Computer Vision, Barcelona, Spain, 2011
[39]
Bengio, Y.: ‘Deep learning of representations for unsupervised and transfer learning’. Proc. of Machine Learning Research, Edinburgh, Scotland, 2012, pp. 17–36
[40]
He, H., Garcia, E.A.: ‘Learning from imbalanced data’, IEEE Trans. Knowl. Data Eng., 2009, 21, (9), pp. 1263–1284
[41]
Chougrad, H., Zouaki, H., Alheyane, O.: ‘Deep convolutional neural networks for breast cancer screening’, Comput. Methods Programs Biomed., 2018, 157, pp. 19–30
[42]
Ting, X., Lei, L., Kai, L., et al: ‘Comparison of transferred deep neural networks in ultrasonic breast masses discrimination’, BioMed. Res. Int., 2018, 2018, pp. 1–9

Cited By

View all
  • (2024)Deep Multi-Modal Fusion Model for Identification of Eight Different Particles in Urinary SedimentApplied Computer Systems10.2478/acss-2024-000529:1(35-44)Online publication date: 15-Aug-2024
  • (2023)An IoT and Deep Learning-Based Smart Healthcare Framework for Thyroid Cancer DetectionACM Transactions on Internet Technology10.1145/3637062Online publication date: 11-Dec-2023
  • (2023)Swin-LBP: a competitive feature engineering model for urine sediment classificationNeural Computing and Applications10.1007/s00521-023-08919-w35:29(21621-21632)Online publication date: 18-Aug-2023

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image IET Computer Vision
IET Computer Vision  Volume 14, Issue 1
February 2020
47 pages
EISSN:1751-9640
DOI:10.1049/cvi2.v14.1
Issue’s Table of Contents

Publisher

John Wiley & Sons, Inc.

United States

Publication History

Published: 20 January 2020

Author Tags

  1. image classification
  2. medical image processing
  3. feature extraction
  4. learning (artificial intelligence)
  5. convolutional neural nets

Author Tags

  1. urine sediment microscopic image processing
  2. pre-trained CNNs
  3. urine sediment microscopic image dataset
  4. learning rate
  5. cascading features
  6. convolutional layers
  7. fully connected neural network
  8. fine-tuned convolutional neural networks
  9. urine sediment microscopic image classification
  10. CNN training
  11. impurity interference
  12. classification accuracy

Qualifiers

  • Research-article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 22 Dec 2024

Other Metrics

Citations

Cited By

View all
  • (2024)Deep Multi-Modal Fusion Model for Identification of Eight Different Particles in Urinary SedimentApplied Computer Systems10.2478/acss-2024-000529:1(35-44)Online publication date: 15-Aug-2024
  • (2023)An IoT and Deep Learning-Based Smart Healthcare Framework for Thyroid Cancer DetectionACM Transactions on Internet Technology10.1145/3637062Online publication date: 11-Dec-2023
  • (2023)Swin-LBP: a competitive feature engineering model for urine sediment classificationNeural Computing and Applications10.1007/s00521-023-08919-w35:29(21621-21632)Online publication date: 18-Aug-2023

View Options

View options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media