Advertisement

Efficient cell classification of mitochondrial images by using deep learning

  • Muhammad Shahid IqbalEmail author
  • Saeed El-Ashram
  • Sajid Hussain
  • Tamoor Khan
  • Shujian Huang
  • Rashid Mehmood
  • Bin Luo
Research Article
  • 36 Downloads

Abstract

Key challenges for affected cells, evolutionary biology and precision medicine include the effect of drug and understanding viscosity and intensity of drug-treated cells. However, this is extremely difficult because the enormous cells are affected by the drug. We developed a deep learning-based framework DNCIC that can accurately predict normal mitochondria and drug-affected cells that are rare or not observed. For optimization, we used a convolutional neural network and trained using a dataset of mitochondrial images, which were collected through the confocal microscope. The obtained algorithm was validated on the normal and affected cell images. We have trained CNN that can classify (normal and affected cells) two-photon excited fluorescence probe images. The proposed model has classified images and videos with 98% accuracy. Our results provided a foundation for drug-affected cell diagnosis.

Keywords

Cell classification Mitochondria Deep learning and drug 

Notes

Acknowledgements

The authors are grateful to the School of Computer Sciences, Anhui University Hefei, China, for their support and cooperation.

Author contributions

MSI, SEA, SH, TK, RM and BL developed the model and analyzed the data. SH analyzed the data, made new compounds and provided the dataset of normal and drug images. All authors read and approved the final version of the manuscript.

References

  1. 1.
    X. Tian et al., A series of water-soluble pyridinium derivatives with two-photon absorption in the near infrared region for mitochondria targeting under stimulated emission depletion (STED) nanoscopy. Dyes Pigments Int. J. 147, 90–98 (2017).  https://doi.org/10.1016/j.dyepig.2017.07.025 CrossRefGoogle Scholar
  2. 2.
    A. Karpathy et al., The Unreasonable Effectiveness of Recurrent Neural Networks. github. http://karpathygithub.io/2015/05/21/rnn-effectiveness (2015)
  3. 3.
    A. Esteva et al., Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115 (2017).  https://doi.org/10.1038/nature21056 ADSCrossRefGoogle Scholar
  4. 4.
    V. Gulshan et al., Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama 22, 2402–2410 (2016).  https://doi.org/10.1001/jama.2016.17216 CrossRefGoogle Scholar
  5. 5.
    G. Litjens et al., A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017).  https://doi.org/10.1016/j.media.2017.07.005 CrossRefGoogle Scholar
  6. 6.
    G. Wharton et al., A minimum dataset for a standard adult transthoracic echocardiogram:a guideline protocol from the British Society of Echocardiography. Echo Res. Pract. 2, G9–G24 (2015).  https://doi.org/10.1530/ERP-14-0079 CrossRefGoogle Scholar
  7. 7.
    H. Khamis et al., Automatic apical view classification of echocardiograms using a discriminative learning dictionary. Med. Image Anal. 36, 15–21 (2017).  https://doi.org/10.1016/j.media.2016.10.007 CrossRefGoogle Scholar
  8. 8.
    C. Knackstedt et al., Fully automated versus standard tracking of left ventricular ejection fraction and longitudinal strain: the FAST-EFs multicenter study. J. Am. Coll. Cardiol. 66, 1456–1466 (2015).  https://doi.org/10.1016/j.jacc.2015.07.052 CrossRefGoogle Scholar
  9. 9.
    S. Narula et al., Machine-learning algorithms to automate morphological and functional assessments in 2D echocardiography. J. Am. Coll. Cardiol. 68, 2287–2295 (2016).  https://doi.org/10.1016/j.jacc.2016.08.062 CrossRefGoogle Scholar
  10. 10.
    J. Park et al., fast and automatic Doppler gate localization in B-mode echocardiogram. Med. Image Comput. Comput. Assist. Interv. 11, 230–237 (2008).  https://doi.org/10.1007/978-3-540-85990-1_28 CrossRefGoogle Scholar
  11. 11.
    P.P. Sengupta et al., Cognitive machine-learning algorithm for cardiac imaging: a pilot study for differentiating constrictive pericarditis from restrictive cardiomyopathy. Circ. Cardiovasc. Imaging 9, 1–3 (2016).  https://doi.org/10.1161/CIRCIMAGING.115.004330 CrossRefGoogle Scholar
  12. 12.
    A. Madani et al., Fast and accurate view classification of echocardiograms using deep learning. NPJ Dig. Med. 1(1), 6 (2018).  https://doi.org/10.1038/s41746-017-0013-1 CrossRefGoogle Scholar
  13. 13.
    D.E. Goldberg, Genetic algorithms in search. Optim. Mach. Learn. 7, 2104–2116 (1990)Google Scholar
  14. 14.
    G.E. Hinton et al., A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527 (2006).  https://doi.org/10.1162/neco.2006.18.7.1527 MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Matthias Seeger, Gaussian processes for machine learning. Int. J. Neural Syst. 14, 69–106 (2004).  https://doi.org/10.1142/S0129065704001899 CrossRefGoogle Scholar
  16. 16.
    Y. LeCun et al., Deep learning. Nature 521, 436–444 (2015).  https://doi.org/10.1038/nature14539 ADSMathSciNetCrossRefGoogle Scholar
  17. 17.
    A.E. Brown et al., A dictionary of behavioral motifs reveals clusters of genes affecting caenorhabditis elegans locomotion. Proc. Natl. Acad. Sci. 110, 791–796 (2013).  https://doi.org/10.1073/pnas.1211447110 ADSCrossRefGoogle Scholar
  18. 18.
    F.J. Ordóñez, D. Roggen, Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors 16, 115 (2016).  https://doi.org/10.3390/s16010115 CrossRefGoogle Scholar
  19. 19.
    Y. Guan, T. Ploetz, Ensembles of Deep LSTM Learners for Activity Recognition Using Wearables. arXiv:1703.09370,  https://doi.org/10.1145/3090076 (2017)
  20. 20.
    P. Wang et al., Feature-based analysis of cell nuclei structure for classification of histopathological images. Digit. Signal Proc. 78, 152–162 (2018).  https://doi.org/10.1016/j.dsp.2018.03.008 CrossRefGoogle Scholar
  21. 21.
    D. Cascio et al., A multi-process system for HEp-2 cells classification based on SVM. Pattern Recogn. Lett. 82, 56–63 (2016).  https://doi.org/10.1016/j.patrec.2016.03.024 CrossRefGoogle Scholar
  22. 22.
    M.R. Hasan et al., Classification of cancer cells using computational analysis of dynamic morphology. Comput. Methods Programs Biomed. 156, 105–112 (2018).  https://doi.org/10.1016/j.cmpb.2017.12.003 CrossRefGoogle Scholar
  23. 23.
    H. Khamis et al., Automatic apical view classification of echocardiograms using a discriminative learning dictionary. Med. Image Anal. 36, 15–21 (2017).  https://doi.org/10.1016/j.media.2016.10.007 CrossRefGoogle Scholar
  24. 24.
    A. Janowczyk, A. Basavanhally, A. Madabhushi, Stain normalization using sparse autoencoders (STANOSA): application to digital pathology. Comput. Med. Imaging Graph. 57, 50–61 (2017)CrossRefGoogle Scholar
  25. 25.
    A. Sethi, L. Sha, A.R. Vahadane, R.J. Deaton, N. Kumar, V. Macias, P.H. Gann, Empirical comparison of color normalization methods for epithelial-stromal classification in h and e images. J. Pathol. Inf. 7, 17 (2016).  https://doi.org/10.4103/2153-3539.179984 CrossRefGoogle Scholar
  26. 26.
    P.S. Douglas et al., ACCF/ASE/AHA/ASNC/HFSA/HRS/SCAI/SCCM/SCCT/SCMR 2011 appropriate use criteria for echocardiography. J. Am. Coll. Cardiol. 57(9), 1126–1166 (2011).  https://doi.org/10.1016/j.jacc.2010.11.002 CrossRefGoogle Scholar
  27. 27.
    K. Doi, Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput. Med. Imaging Graph. 31, 198–211 (2007).  https://doi.org/10.1016/j.compmedimag.2007.02.002 CrossRefGoogle Scholar
  28. 28.
    F. Winsberg et al., Detection of radiographic abnormalities in mammograms by means of optical scanning and computer analysis 1. Radiology 89, 211–215 (1967).  https://doi.org/10.1148/89.2.211 CrossRefGoogle Scholar
  29. 29.
    H. Yoshida et al., Computerized detection of colonic polyps at ct colonography on the basis of volumetric features. Radiology 222, 327–336 (2002).  https://doi.org/10.1148/radiol.2222010506 CrossRefGoogle Scholar
  30. 30.
    L. Monnier-Cholley et al., Computer-aided diagnosis for detection of interstitial opacities on chest radiographs. AJR Am. J. Roentgenol. 171, 1651–1656 (1998).  https://doi.org/10.2214/ajr.171.6.9843307 CrossRefGoogle Scholar
  31. 31.
    M.R. Arbabshirani et al., Single subject prediction of brain disorders in neuroimaging: promises and pitfalls. Neuroimage 145, 137–165 (2016).  https://doi.org/10.1016/j.neuroimage.2016.02.079 CrossRefGoogle Scholar
  32. 32.
    T. Freer et al., Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center 1. Radiology 220, 781–786 (2001).  https://doi.org/10.1148/radiol.2203001282 CrossRefGoogle Scholar
  33. 33.
    J.J. Fenton et al., Influence of computer-aided detection on performance of screening mammography. N. Engl. J. Med. 356, 1399–1409 (2007).  https://doi.org/10.1056/NEJMoa066099 CrossRefGoogle Scholar
  34. 34.
    K. He et al., Delving deep into rectifiers: surpassing human level performance on imagenet classification, in Proceedings of the IEEE International Conference on Computer Vision (IEEE Computer Society, Washington, 2015), pp. 1026–1034Google Scholar
  35. 35.
    H. Greenspan et al., Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans. Med. Imaging 35, 1153–1159 (2016).  https://doi.org/10.1109/TMI.2016.2553401 CrossRefGoogle Scholar
  36. 36.
    V. Gulshan et al., Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316, 2402–2410 (2016).  https://doi.org/10.1001/jama.2016.17216 CrossRefGoogle Scholar
  37. 37.
    A. Esteva et al., Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017).  https://doi.org/10.1038/nature21056 ADSCrossRefGoogle Scholar
  38. 38.
    A.A.A. Setio et al., Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans. Med. Imaging 35, 1160–1169 (2016).  https://doi.org/10.1109/TMI.2016.2536809 CrossRefGoogle Scholar
  39. 39.
    Q. Dou et al., Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks. IEEE Trans. Med. Imaging 35, 1182–1195 (2016).  https://doi.org/10.1109/TMI.2016.2528129 CrossRefGoogle Scholar

Copyright information

© The Optical Society of India 2019

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyAnhui UniversityHefeiChina
  2. 2.College of Life Science and EngineeringFoshan UniversityFoshanChina
  3. 3.Faculty of ScienceKafrelsheikh UniversityKafr El SheikhEgypt
  4. 4.School of Applied Sciences and Humanities (NUSASH)National University of TechnologyIslamabadPakistan
  5. 5.School of Economic Information EngineeringSouthwestern University of Finance and EconomicsChengduPeople’s Republic of China
  6. 6.College of Information Science and TechnologyBeijing Normal UniversityBeijingChina

Personalised recommendations