公开(公告)号：US20220260481A1

公开(公告)日：2022-08-18

申请号：US17621979

申请日：2020-07-02

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Aniruddha Ray ,  Yibo Zhang ,  Dino Di Carlo

IPC: G01N15/14 ,  B03C1/01 ,  B03C1/02 ,  G06V20/69 ,  G06V10/82 ,  G06V10/147 ,  G03H1/00

Abstract: A computational cytometer operates using magnetically modulated lensless speckle imaging, which introduces oscillatory motion to magnetic bead-conjugated rare cells of interest through a periodic magnetic force and uses lensless time-resolved holographic speckle imaging to rapidly detect the target cells in three-dimensions (3D). Detection specificity is further enhanced through a deep learning-based classifier that is based on a densely connected pseudo-3D convolutional neural network (P3D CNN), which automatically detects rare cells of interest based on their spatio-temporal features under a controlled magnetic force. This compact, cost-effective and high-throughput computational cytometer can be used for rare cell detection and quantification in bodily fluids for a variety of biomedical applications.

公开(公告)号：US20220206434A1

公开(公告)日：2022-06-30

申请号：US17604416

申请日：2020-04-21

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Yair Rivenson ,  Tairan Liu ,  Yibo Zhang ,  Zhensong Wei

IPC: G03H1/08 ,  G03H1/04 ,  G03H1/26 ,  G06N3/08 ,  G06N3/04

Abstract: A method for performing color image reconstruction of a single super-resolved holographic sample image includes obtaining a plurality of sub-pixel shifted lower resolution hologram images of the sample using an image sensor by simultaneous illumination at multiple color channels. Super-resolved hologram intensity images for each color channel are digitally generated based on the lower resolution hologram images. The super-resolved hologram intensity images for each color channel are back propagated to an object plane with image processing software to generate a real and imaginary input images of the sample for each color channel. A trained deep neural network is provided and is executed by image processing software using one or more processors of a computing device and configured to receive the real input image and the imaginary input image of the sample for each color channel and generate a color output image of the sample.

公开(公告)号：US20220121940A1

公开(公告)日：2022-04-21

申请号：US17503312

申请日：2021-10-17

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Calvin Brown ,  Artem Goncharov ,  Zachary Ballard ,  Yair Rivenson

IPC: G06N3/08 ,  G06T7/174 ,  G01J3/28

Abstract: A deep learning-based spectral analysis device and method are disclosed that employs a spectral encoder chip containing a plurality of nanohole array tiles, each with a unique geometry and, thus, a unique optical transmission spectrum. Illumination impinges upon the encoder chip and a CMOS image sensor captures the transmitted light, without any lenses, gratings, or other optical components. A spectral reconstruction neural network uses the transmitted intensities from the image to faithfully reconstruct the input spectrum. In one embodiment that used a spectral encoder chip with 252 nanohole array tiles, the network was trained on 50,352 spectra randomly generated by a supercontinuum laser and blindly tested on 14,648 unseen spectra. The system identified 96.86% of spectral peaks, with a peak localization error of 0.19 nm, peak height error of 7.60%, and peak bandwidth error of 0.18 nm.

公开(公告)号：US20220114711A1

公开(公告)日：2022-04-14

申请号：US17530471

申请日：2021-11-19

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Yair Rivenson ,  Hongda Wang ,  Harun Gunaydin ,  Kevin de Haan

IPC: G06T5/50 ,  G06T7/00 ,  G06T3/40

Abstract: A microscopy method includes a trained deep neural network that is executed by software using one or more processors of a computing device, the trained deep neural network trained with a training set of images comprising co-registered pairs of high-resolution microscopy images or image patches of a sample and their corresponding low-resolution microscopy images or image patches of the same sample. A microscopy input image of a sample to be imaged is input to the trained deep neural network which rapidly outputs an output image of the sample, the output image having improved one or more of spatial resolution, depth-of-field, signal-to-noise ratio, and/or image contrast.

公开(公告)号：US20220012850A1

公开(公告)日：2022-01-13

申请号：US17294384

申请日：2019-11-14

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Yair Rivenson ,  Yichen Wu

IPC: G06T5/00 ,  G06T7/50 ,  G02B21/36 ,  G02B21/00 ,  G03H1/00 ,  G03H1/26

Abstract: A trained deep neural network transforms an image of a sample obtained with a holographic microscope to an image that substantially resembles a microscopy image obtained with a microscope having a different microscopy image modality. Examples of different imaging modalities include bright-field, fluorescence, and dark-field. For bright-field applications, deep learning brings bright-field microscopy contrast to holographic images of a sample, bridging the volumetric imaging capability of holography with the speckle-free and artifact-free image contrast of bright-field microscopy. Holographic microscopy images obtained with a holographic microscope are input into a trained deep neural network to perform cross-modality image transformation from a digitally back-propagated hologram corresponding to a particular depth within a sample volume into an image that substantially resembles a microscopy image of the sample obtained at the same particular depth with a microscope having the different microscopy image modality.

公开(公告)号：US20210264214A1

公开(公告)日：2021-08-26

申请号：US17261542

申请日：2019-03-29

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Yair Rivenson ,  Zhensong Wei

IPC: G06K9/62 ,  G06N3/08 ,  G06K9/00

Abstract: A deep learning-based digital staining method and system are disclosed that provides a label-free approach to create a virtually-stained microscopic images from quantitative phase images (QPI) of label-free samples. The methods bypass the standard histochemical staining process, saving time and cost. This method is based on deep learning, and uses a convolutional neural network trained using a generative adversarial network model to transform QPI images of an unlabeled sample into an image that is equivalent to the brightfield image of the chemically stained-version of the same sample. This label-free digital staining method eliminates cumbersome and costly histochemical staining procedures, and would significantly simplify tissue preparation in pathology and histology fields.

公开(公告)号：US20210209337A1

公开(公告)日：2021-07-08

申请号：US15734225

申请日：2019-06-04

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Zoltan Gorocs

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/254 ,  G06T7/215 ,  G06K9/62 ,  G01N15/14 ,  B01L3/00 ,  H04N5/225 ,  G03H1/00 ,  G03H1/04

Abstract: An imaging flow cytometer device includes a housing holding a multi-color illumination source configured for pulsed or continuous wave operation. A microfluidic channel is disposed in the housing and is fluidically coupled to a source of fluid containing objects that flow through the microfluidic channel. A color image sensor is disposed adjacent to the microfluidic channel and receives light from the illumination source that passes through the microfluidic channel. The image sensor captures image frames containing raw hologram images of the moving objects passing through the microfluidic channel. The image frames are subject to image processing to reconstruct phase and/or intensity images of the moving objects for each color. The reconstructed phase and/or intensity images are then input to a trained deep neural network that outputs a phase recovered image of the moving objects. The trained deep neural network may also be trained to classify object types.

公开(公告)号：US20190316172A1

公开(公告)日：2019-10-17

申请号：US16464681

申请日：2017-11-29

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Omai Garner ,  Dino Di Carlo ,  Steve Wei Feng

IPC: C12Q1/18 ,  G01N21/25 ,  G06K9/00 ,  G06K9/24

Abstract: A method of performing antimicrobial susceptibility testing (AST) on a sample uses a reader device that mounts on a mobile phone having a camera. A microtiter plate containing wells preloaded with the bacteria-containing sample, growth medium, and drugs of differing concentrations is loaded into the reader device. The wells are illuminated using an array of illumination sources contained in the reader device. Images of the wells are acquired with the camera of the mobile phone. In one embodiment, the images are transmitted to a separate computing device for processing to classify each well as turbid or not turbid and generating MIC values and a susceptibility characterization for each drug in the panel based on the turbidity classification of the array of wells. The MIC values and the susceptibility characterizations for each drug are transmitted or returned to the mobile phone for display thereon.

公开(公告)号：US20190294108A1

公开(公告)日：2019-09-26

申请号：US16359609

申请日：2019-03-20

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Yair Rivenson ,  Yichen Wu ,  Yibo Zhang ,  Harun Gunaydin

IPC: G03H1/22 ,  G03H1/04 ,  G06N3/08

Abstract: A method of performing phase retrieval and holographic image reconstruction of an imaged sample includes obtaining a single hologram intensity image of the sample using an imaging device. The single hologram intensity image is back-propagated to generate a real input image and an imaginary input image of the sample with image processing software, wherein the real input image and the imaginary input image contain twin-image and/or interference-related artifacts. A trained deep neural network is provided that is executed by the image processing software using one or more processors and configured to receive the real input image and the imaginary input image of the sample and generate an output real image and an output imaginary image in which the twin-image and/or interference-related artifacts are substantially suppressed or eliminated. In some embodiments, the trained deep neural network simultaneously achieves phase-recovery and auto-focusing significantly extending the DOF of holographic image reconstruction.

公开(公告)号：US10365214B2

公开(公告)日：2019-07-30

申请号：US15111472

申请日：2015-01-12

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Qingshan Wei

IPC: G01N21/31 ,  H04N5/232 ,  H04N5/235 ,  G06T7/40 ,  G01N33/18 ,  G06T7/00 ,  H04N5/225 ,  G06T7/90 ,  G01N15/06

Abstract: The concentration of mercury in a sample is measured by a reader secured to a camera-containing mobile electronic device. The reader has holders for sample and control solutions. First and second light sources emitting light at different colors illuminate the sample and control holders. Each holder contains gold nanoparticles, thymine-rich aptamers, and sodium chloride. The light sources illuminate the sample and control holders. An image is captured of the transmitted light through the sample and control holders, wherein the image comprises two control regions of interest and two sample regions of interest. The device calculates the intensity of the two control regions of interest and the two sample regions of interest and generates intensity ratios for the sample and control, respectively, at each color. The device calculates a normalized color ratio based on the intensity ratios and outputs a concentration of mercury based on the normalized color ratio.