Research ArticleOPTICAL MICROSCOPY

Holographic deep learning for rapid optical screening of anthrax spores

See allHide authors and affiliations

Science Advances  04 Aug 2017:
Vol. 3, no. 8, e1700606
DOI: 10.1126/sciadv.1700606
  • Fig. 1 Holographic deep learning framework for screening of anthrax spores.

    (A) Schematic diagram of QPIU for holographic imaging of individual Bacillus spores. (B) Interferogram formed by spatial modulation. It encodes quantitative phase images of individual spores, as shown in (C). (D) The measured phase images from multiple Bacillus species are used to train a deep neural network using the error backpropagation algorithm. (E) The trained network accurately predicts the corresponding species when independently measured phase images are shown.

  • Fig. 2 Architecture of HoloConvNet.

    When a phase image of an individual spore is taken as the input, the network first processes the images through three rounds of convolution, ReLU nonlinearity, and max pooling layers. Then, two fully connected (and ReLU) layers follow: (i) the last hidden layer under dropout regularization and (ii) the output layer with the class scores. These scores are used to calculate the loss function and to make species predictions in the training and test stages, respectively. Only 10 two-dimensional activation maps per layer are presented with layer-wise scaling for visualization (see table S2 for detailed architecture).

  • Fig. 3 Performance of HoloConvNet.

    (A to C) The test images are used to measure the performance of (A) multiclass classification of the five Bacillus species (B. anthracis, B. thuringiensis, B. cereus, B. atrophaeus, and B. subtilis), (B) binary classification of B. anthracis and the other four species (B. thuringiensis, B. cereus, B. atrophaeus, and B. subtilis), and (C) binary classification of B. anthracis and the two nonmember species of the B. cereus group (B. atrophaeus and B. subtilis). (D) The performance of the proposed method is compared to previous techniques (see the main text). Holographic microscopy and deep learning significantly improve the performance in all cases. (E to G) t-SNE visualization of the CNN codes at the last hidden layer, corresponding to the classification schemes of (A) to (C), which shows the representation learning capability of HoloConvNet. The error bars in (A) to (D) indicate the SD calculated from 10 classification models with different random initializations.

  • Fig. 4 Representation learning by HoloConvNet: Dry mass as a key biological trait.

    The interspecies difference in cellular dry mass is automatically recognized and used for screening of anthrax spores. (A to C) The activation of the “anthrax neuron” at the output layer shows a strong correlation with dry mass. a.u., arbitrary units. (D) Dry mass of individual Bacillus spores calculated from the quantitative phase images. (E) Computationally disabling the dry mass information significantly impairs the performance of HoloConvNet. Dry mass alone is not enough for full performance as well. Data in (D) are presented as box-and-whisker plots displaying median and interquartile ranges. The error bars in (E) indicate the SD calculated from 10 classification models with different random initializations.

Supplementary Materials

  • Supplementary material for this article is available at http://advances.sciencemag.org/cgi/content/full/3/8/e1700606/DC1

    fig. S1. Representative images of individual Bacillus spores.

    fig. S2. Morphological features of individual Bacillus spores.

    fig. S3. Confusion matrices illustrating the performance of HoloConvNet.

    fig. S4. Dry mass of individual Bacillus spores measured on different days.

    fig. S5. Comparison of Listeria identification techniques.

    fig. S6. Dry mass of individual bacteria from the Listeria species.

    table S1. Detailed data on Bacillus spores.

    table S2. Detailed architecture of HoloConvNet.

    table S3. Performance of HoloConvNet on multiclass classification of the five Bacillus species.

    table S4. Performance of HoloConvNet on binary classification of the five Bacillus species.

    table S5. Performance of HoloConvNet on binary classification of the three Bacillus species.

    table S6. Performance of conventional machine learning techniques in morphology-based identification of Bacillus spores.

    table S7. Performance of conventional machine learning techniques in holographic identification of Bacillus spores.

    table S8. Detailed description of the Listeria data.

  • Supplementary Materials

    This PDF file includes:

    • fig. S1. Representative images of individual Bacillus spores.
    • fig. S2. Morphological features of individual Bacillus spores.
    • fig. S3. Confusion matrices illustrating the performance of HoloConvNet.
    • fig. S4. Dry mass of individual Bacillus spores measured on different days.
    • fig. S5. Comparison of Listeria identification techniques.
    • fig. S6. Dry mass of individual bacteria from the Listeria species.
    • table S1. Detailed data on Bacillus spores.
    • table S2. Detailed architecture of HoloConvNet.
    • table S3. Performance of HoloConvNet on multiclass classification of the five Bacillus species.
    • table S4. Performance of HoloConvNet on binary classification of the five Bacillus species.
    • table S5. Performance of HoloConvNet on binary classification of the three Bacillus species.
    • table S6. Performance of conventional machine learning techniques in morphology-based identification of Bacillus spores.
    • table S7. Performance of conventional machine learning techniques in holographic identification of Bacillus spores.
    • table S8. Detailed description of the Listeria data.

    Download PDF

    Files in this Data Supplement:

Navigate This Article