Rapid identification of infectious pathogens can save lives and mitigate healthcare expenses. Yet the current turnaround time for microbial identification typically exceeds 24 hours, as the common methods require the cultivation of millions or more bacteria to detect the collective signal. In this study, we propose a hybrid framework of quantitative phase imaging and artificial neural network to facilitate rapid identification at an individual-cell level. Specifically, three-dimensional images of refractive index were acquired for individual bacteria, and an optimized artificial neural network determined the species based on the three-dimensional morphologies, securing 82.5% blind test accuracy at an individual-cell level.
Despite the progress in QPI during the last decades, disseminating QPI to broader communities is still in its infancy. A critical limiting factor has been the limited biochemical specificity of QPI. We hypothesized that high-specificity information could be directly retrieved by incorporating the surrounding RI values in 3D space with aid from machine vision. Specifically, we trained deep convolutional networks to transform RI tomograms to the corresponding fluorescence tomograms. This approach achieved state-of-the-art prediction accuracy and generalization across cell types, which enabled applications to new samples without retraining. Together, QPI data do have substantial biochemical specificity that can be accessed.
Rapid, label-free, volumetric, and automated assessment in microscopy is necessary to assess the dynamic interactions between lymphocytes and their targets through the immunological synapse (IS) and the relevant immunological functions. However, attempts to realize the automatic tracking of IS dynamics have been stymied by the limitations of imaging techniques and computational analysis methods. Here, we demonstrate the automatic three-dimensional IS tracking by combining optical diffraction tomography and deep-learning-based segmentation. The proposed approach enables quantitative spatiotemporal analyses of IS regarding morphological and biochemical parameters related to its protein densities, offering a novel complementary method to fluorescence microscopy for studies in immunology.
The recent progress in machine learning, a subfield of artificial intelligence (AI) with a focus on learning algorithms, is attracting researchers in quantitative phase imaging (QPI). The fast and label-free nature of QPI is ideal for generating large-scale data to train supervised machine learning algorithms. The algorithms discover important structures in large, multidimensional training data to exploit them for augmenting new QPI measurements. Here, we present two major directions in synergistically combining QPI with AI, with a particular focus on a state-of-the-art machine learning technique called deep learning.
One direction is systematic exploitation of QPI data. Employing image classification frameworks, class-dependent characteristics encoded in the images are extracted for rapid diagnosis and screening. This approach has been demonstrated in a wide range of biological systems ranging from microbes to cells to tissues, with various modalities including 2D phase, 3D tomographic, time-lapse, and spectral measurements. In these methods, AI complements limited chemical specificity of QPI by maximally utilizing refractive index information in a data-driven manner.
The second direction is an improvement of QPI methods themselves. In computational side, efficient 2D holographic or 3D tomographic reconstruction was demonstrated using neural networks. For an experimental side, reinforcement learning frameworks are employed for efficient measurements in an adaptive fashion. This direction is relatively unexplored and provides a promising frontier.
We envision that these approaches would form an indispensable toolbox for QPI and facilitate exciting new applications. As QPI is extensively studied and commercialized, rapidly accumulating data for various biological systems would render the methods increasingly powerful.
We demonstrate that simultaneous application of optical clearing agents (OCAs) and complex wavefront shaping in optical coherence tomography (OCT) can provide significant enhancement of penetration depth and imaging quality. OCA reduces optical inhomogeneity of a highly scattering sample, and the wavefront shaping of illumination light controls multiple scattering, resulting in an enhancement of the penetration depth and signal-to-noise ratio. A tissue phantom study shows that concurrent applications of OCA and wavefront shaping successfully operate in OCT imaging. The penetration depth enhancement is further demonstrated for ex vivo mouse ears, revealing hidden structures inaccessible with conventional OCT imaging.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.