http://iet.metastore.ingenta.com
1887

Combining the use of CNN classification and strength-driven compression for the robust identification of bacterial species on hyperspectral culture plate images

Combining the use of CNN classification and strength-driven compression for the robust identification of bacterial species on hyperspectral culture plate images

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Huge streams of diagnostic images are expected to be produced daily in the emerging field of digital microbiology imaging because of the ongoing worldwide spread of Full Laboratory Automation systems. This is redefining the way microbiologists execute diagnostic tasks. In this context, the authors want to assess the suitability and effectiveness of a deep learning approach to solve the diagnostically relevant but visually challenging task of directly identifying pathogens on bacterial growing plates. In particular, starting from hyperspectral acquisitions in the VNIR range and spatial-spectral processing of cultured plates, they approach the identification problem as the classification of computed spectral signatures of the bacterial colonies. In a highly relevant clinical context (urinary tract infections) and on a database of acquired hyperspectral images, they designed and trained a convolutional neural network for pathogen identification, assessing its performance and comparing it against conventional classification solutions. At the same time, given the expected data flow and possible conservation and transmission needs, they are interested in evaluating the combined use of classification and lossy data compression. To this end, after selecting a suitable wavelet-based compression technology, they test coding strength-driven operating points looking for configurations able to provably prevent any classification performance degradation.

References

    1. 1)
      • 1. LeCun, Y., Bengio, L., Haffner, P.: ‘Gradient-based learning applied to document recognition’, Proc. IEEE, 1998, 86, (11), pp. 22782324.
    2. 2)
      • 2. Litjens, G., Kooi, T., Bejnordi, B.E., et al: ‘A survey on deep learning in medical image analysis’. arXiv preprint arXiv:1702.05747, 2017.
    3. 3)
      • 3. Serranti, S., Cesare, D., Marini, F., et al: ‘Classification of oat and Groat kernels using NIR hyperspectral imaging’, Talanta, 2013, 103, pp. 276284.
    4. 4)
      • 4. Gowen, A., Feng, Y., Gaston, E., et al: ‘Recent applications of hyperspectral imaging in microbiology’, Talanta, 2015, 137, pp. 4354.
    5. 5)
      • 5. Liang, H.: ‘Advances in multispectral and hyperspectral imaging for archaeology and art conservation’, Appl. Phys. A, 2012, 106, (2), pp. 309323.
    6. 6)
      • 6. Lu, G., Fei, B.: ‘Medical hyperspectral imaging: a review’, J. Biomed. Opt., 2014, 19, (1), pp. 124.
    7. 7)
      • 7. Wug Oh, S., Brown, M.S., Pollefeys, M., et al: ‘Do it yourself hyperspectral imaging with everyday digital cameras’. IEEE Computer Vision and Pattern Recognition, Las Vegas Valley, Nevada, United States, 2016.
    8. 8)
      • 8. Lambrechts, A., Gonzalez, P., Geelen, B., et al: ‘A CMOS-compatible, integrated approach to hyper- and multispectral imaging’. IEEE Int. Electron Devices Meeting, San Francisco, CA USA, 2014, pp. 10.5.110.5.4.
    9. 9)
      • 9. Bourbeau, P., Ledeboer, N.: ‘Automation in clinical microbiology’, J. Clin. Microbiol., 2013, 51, (6), pp. 16581665.
    10. 10)
      • 10. Novak, S., Marlowe, E.: ‘Automation in the clinical microbiology laboratory’, Clin. Lab. Med., 2013, 33, (3), pp. 567588.
    11. 11)
      • 11. Rhoads, D., Sintchenko, V., Rauch, C., et al: ‘Clinical microbiology informatics’, Clin. Microbiol. Rev., 2014, 27, (4), pp. 10251047.
    12. 12)
      • 12. Doern, C.D., Holfelder, M.: ‘Automation and design of the clinical microbiology laboratory’, in Jorgensen, J.H., Pfaller, M.A., Carroll, K.C., et al: ‘Manual of clinical microbiology’ (American Society of Microbiology Press, Washington, DC, 2015, 11th edn.), pp. 4453.
    13. 13)
      • 13. Flores-Mireles, A.L., Walker, J.N., Caparon, M., et al: ‘Urinary tract infections: epidemiology, mechanisms of infection and treatment options’, Nat. Rev. Microbiol., 2015, 13, (5), pp. 269284.
    14. 14)
      • 14. D'Souza, H., Campbell, M., Baron, E.: ‘Practical bench comparison of BBL chromagar orientation and standard two-plate media for urine cultures’, J. Clin. Microbiol., 2004, 42, (1), pp. 6064.
    15. 15)
      • 15. Perry, J., Freydière, A.: ‘The application of chromogenic media in clinical microbiology’, J. Appl. Microbiol., 2007, 103, (6), pp. 20462055.
    16. 16)
      • 16. Chen, Y., Zhao, X., Jia, X.: ‘Spectral-spatial classification of hyperspectral data based on deep belief network’, IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens., 2015, 8, (6), pp. 23812392.
    17. 17)
      • 17. Makantasis, K., Karantzalos, K., Doulamis, A., et al: ‘Deep supervised learning for hyperspectral data classification through convolutional neural networks’. 2015 IEEE Int. Geoscience and Remote Sensing Symp., Milan, Italy, 2015, pp. 49594962.
    18. 18)
      • 18. Zhang, L., Zhang, L., Du, B.: ‘Deep learning for remote sensing data: A technical tutorial on the state of the art’, IEEE Geosci. Remote Sens. Mag., 2016, 4, (2), pp. 2240.
    19. 19)
      • 19. Ma, X., Wang, H., Geng, J., et al: ‘Hyperspectral image classification with small training set by deep network and relative distance prior’. 2016 IEEE Int. Geoscience and Remote Sensing Symp., Beijing, China, 2016, pp. 32823285.
    20. 20)
      • 20. Ferrari, A., Signoroni, A.: ‘Multistage classification for bacterial colonies recognition on solid agar images’. 2014 IEEE Int. Conf. Imaging Systems and Techniques (IST), Island of Santorini, Greece, 2014, pp. 101106.
    21. 21)
      • 21. Ferrari, A., Lombardi, S., Signoroni, A.: ‘Bacterial colony counting by convolutional neural networks’. 2015 37th Annual Int. Conf. IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy, 2015, pp. 74587461.
    22. 22)
      • 22. Andreini, P., Bonechi, S., Bianchini, M., et al: Automatic Image Analysis and Classification for Urinary Bacteria Infection Screening, Catania, Italy, 2015, pp. 635646.
    23. 23)
      • 23. Ferrari, A., Lombardi, S., Signoroni, A.: ‘Bacterial colony counting with convolutional neural networks in digital microbiology imaging’, Pattern Recognit., 2017, 61, pp. 629640.
    24. 24)
      • 24. Yoon, S., Lawrence, K., Park, B.: ‘Automatic counting and classification of bacterial colonies using hyperspectral imaging’, Food Biol. Tech., 2015, 8, (10), pp. 20472065.
    25. 25)
      • 25. Leroux, D., Midahuen, R., Perrin, G., et al: ‘Hyperspectral imaging applied to microbial categorization in an automated microbiology workflow’. Clinical and Biomedical Spectroscopy and Imaging IV, Munich, Germany, 2015, vol. 9537, pp. 19.
    26. 26)
      • 26. Turra, G., Conti, N., Signoroni, A.: ‘Hyperspectral image acquisition and analysis of cultured bacteria for the discrimination of urinary tract infections’. Engineering in Medicine and Biology Society, EMBC, Milan, Italy, 2015, pp. 759762.
    27. 27)
      • 27. Kammies, T., Manley, M., Gouws, P.A., et al: ‘Differentiation of foodborne bacteria using NIR hyperspectral imaging and multivariate data analysis’, Appl. Microbiol. Biotech., 2016, 100, (21), pp. 93059320.
    28. 28)
      • 28. Arrigoni, S., Turra, G., Signoroni, A.: ‘Hyperspectral image analysis for rapid and accurate discrimination of bacterial infections: a benchmark study’, Comput. Biol. Med., 2017, 88, pp. 6071.
    29. 29)
      • 29. Qian, S., Hollinger, A., Bergeron, M., et al: ‘A multidisciplinary user acceptability study of hyperspectral data compressed using an on board near lossless vector quantization algorithm’, Int. J. Remote Sens., 2005, 26, (10), pp. 21632195.
    30. 30)
      • 30. Penna, B., Tillo, T., Magli, E., et al: ‘Transform coding techniques for lossy hyperspectral data compression’, IEEE Trans. Geosci. Remote Sens., 2007, 45, (5), pp. 14081421.
    31. 31)
      • 31. Carvajal, G., Penna, B., Magli, E.: ‘Unified lossy and near-lossless hyperspectral image compression based on jpeg 2000’, IEEE Geosci. Remote Sens. Lett., 2008, 5, (4), pp. 593597.
    32. 32)
      • 32. Garcia-Vilchez, F., Muñoz-Marí, J., Zortea, M., et al: ‘On the impact of lossy compression on hyperspectral image classification and unmixing’, IEEE Geosci. Remote Sens. Lett., 2011, 8, (2), pp. 253257.
    33. 33)
      • 33. Zabala, A., Pons, X.: ‘Effects of lossy compression on remote sensing image classification of forest areas’, Int. J. Appl. Earth Obs. Geoinf., 2011, 13, (1), pp. 4351.
    34. 34)
      • 34. Lee, C., Youn, S., Baek, J.Y., et al: ‘Effects of compression on classification performance and discriminant information preservation in remotely sensed data’. Satellite Data Compression, Communications, and Processing XI, Baltimore, Maryland, United States, 2015, vol. 9501, p. 950103.
    35. 35)
      • 35. Elmer, P., Häfner, M., Tamaki, T., et al: ‘Impact of lossy image compression on cad support systems for colonoscopy’. Int. Workshop on Computer-Assisted and Robotic Endoscopy, Munich, Germany, 2015, pp. 111.
    36. 36)
      • 36. Karami, A., Heylen, R., Scheunders, P.: ‘Hyperspectral image compression optimized for spectral unmixing’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (10), pp. 58845894.
    37. 37)
      • 37. Wasson, S., Walker, W.: ‘Multi-pass encoding of hyperspectral imagery with spectral quality control’. Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXI, Baltimore, Maryland, United States, 2015, vol. 9472, p. 947208.
    38. 38)
      • 38. Kaufman, J.R., Vongsy, K.M., Dill, J.C.: ‘Toward prediction of hyperspectral target detection performance after lossy image compression’. Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXII, Baltimore, Maryland, United States, 2016, vol. 9840, p. 984026.
    39. 39)
      • 39. Lee, C., Youn, S., Lee, E., et al: ‘Two-stage compression of hyperspectral images with enhanced classification performance’. Remotely Sensed Data Compression, Communications, and Processing XII, Baltimore, Maryland, United States, 2016, vol. 9874, p. 98740A.
    40. 40)
      • 40. Hagag, A., Fan, X., El-Samie, F.E.A.: ‘Lossy compression of satellite images with low impact on vegetation features’, Multidimens. Syst. Signal Process., 2017, 28, (4), pp. 17171736.
    41. 41)
      • 41. Zemliachenko, A.N., Abramov, S.K., Lukin, V.V., et al: ‘Lossy compression of noisy remote sensing images with prediction of optimal operation point existence and parameters’, J. Appl. Remote Sens., 2015, 9, (1), p. 095066.
    42. 42)
      • 42. Bernard, K., Tarabalka, Y., Angulo, J., et al: ‘Spectralspatial classification of hyperspectral data based on a stochastic minimum spanning forest approach’, IEEE Trans. Image Process., 2012, 21, (4), pp. 20082021.
    43. 43)
      • 43. Turra, G., Arrigoni, S., Signoroni, A.: ‘CNN-based identification of hyperspectral bacterial signatures for digital microbiology’. Image Analysis and Processing – ICIAP 2017, Catania, Italy, 2017, pp. 500510.
    44. 44)
      • 44. Savitzky, A., Golay, M.: ‘Smoothing and differentiation of data by simplified least squares procedures’, Analytical Chem., 1964, 36, (8), pp. 16271639.
    45. 45)
      • 45. LeCun, Y., Bengio, Y., Hinton, G.: ‘Deep learning’, Nature, 2015, 521, (7553), pp. 436444.
    46. 46)
      • 46. Chen, Y., Jiang, H., Li, C., et al: ‘Deep feature extraction and classification of hyperspectral images based on convolutional neural networks’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (10), pp. 62326251.
    47. 47)
      • 47. Li, J., Bruzzone, L., Liu, S.: ‘Deep feature representation for hyperspectral image classification’. 2015 IEEE Int. Geoscience and Remote Sensing Symp. (IGARSS), Milan, Italy, 2015, pp. 49514954.
    48. 48)
      • 48. Abadi, M., Barham, P., Chen, J., et al: ‘Tensorflow: a system for large-scale machine learning’. Proc. 12th USENIX Conf. OSDI'16, Savannah, GA, USA, 2016, pp. 265283.
    49. 49)
      • 49. He, K., Zhang, X., Ren, S., et al: ‘Delving deep into rectifiers: surpassing human-level performance on ImageNet classification’. ArXiv e-prints, 2015.
    50. 50)
      • 50. Cortes, C., Vapnik, V.: ‘Support-vector networks’, Mach. Learn., 1995, 20, (3), pp. 273297.
    51. 51)
      • 51. Breiman, L.: ‘Random forests’, Mach. Learn., 2001, 45, (1), pp. 532.
    52. 52)
      • 52. Shaw, G., Manolakis, D.: ‘Signal processing for hyperspectral image exploitation’, IEEE Signal Process. Mag., 2002, 19, (1), pp. 1216.
    53. 53)
      • 53. Christophe, E.: ‘Hyperspectral data compression tradeoff’, in Prasad, S., Bruce, L.M., Chanussot, J.: ‘Optical remote sensing’ (Springer, Berlin, Heidelberg, 2011), pp. 929.
    54. 54)
      • 54. Conoscenti, M., Coppola, R., Magli, E.: ‘Constant SNR, rate control, and entropy coding for predictive lossy hyperspectral image compression’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (12), pp. 74317441.
    55. 55)
      • 55. Signoroni, A., Pezzoni, M., Leonardi, R.: ‘3D-PMDC: a parallelized morphological wavelet codec for 3D medical datasets and teleradiology applications’. Proc. Int. Conf. Image Processing (ICIP), Brussels, Belgium, 2011, pp. 329332.
    56. 56)
      • 56. Lazzaroni, F., Leonardi, R., Signoroni, A.: ‘High-performance embedded morphological wavelet coding’, IEEE Signal Process. Lett., 2003, 10, (10), pp. 293295.
    57. 57)
      • 57. Signoroni, A., Pezzoni, M., Tonoli, C., et al: ‘A comparison of state-of-the art technologies for irreversible compression of large medical datasets’. Proc. Int. Symp. Computer-Based Medical Systems (CBMS), Bristol, UK, 2012, pp. 16.
    58. 58)
      • 58. Ales, F., Uros, S., Bostjan, L.: ‘The impact of image information on compressibility and degradation in medical image compression’, Med. Phys., 2006, 33, (8), pp. 28322838.
    59. 59)
      • 59. Signoroni, A., Tonoli, C., Castiglioni, I.: ‘A study on quality level reproducibility for the usability of irreversible compression in radiological imaging’. 2011 IEEE Nuclear Science Symp. Conf. Recording, October 2011, pp. 31443148.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2018.5237
Loading

Related content

content/journals/10.1049/iet-cvi.2018.5237
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address