Fluorescence-based detection of problematic cellular entities
Inventors
Pesala, Bala • RADHAKRISHNAN, Geethanjali • KUMAR SHA, Bikki • King, John
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12094117-B2
Publication Date
2024-09-17
Expiration Date
Abstract
Techniques are for detecting presence of a problematic cellular entity in a target. In an example, using an analysis model, a fluorescence-based image is analyzed. The analysis model is trained using a number of reference fluorescence-based images for detecting the presence of problematic cellular entities in targets. Based on the analysis, a problematic cellular entity present in the target is detected. To perform the detection, the analysis model is trained to differentiate between the fluorescence in the fluorescence-based image emerging from the problematic cellular entity and the fluorescence in the fluorescence-based image emerging from regions other than the problematic cellular entity.
Core Innovation
The invention provides a device and corresponding system for examining a target using filter-less fluorescence-based detection. A first light source illuminates the target such that a marker in the target fluoresces, while a second light source illuminates the target without causing the marker to fluoresce. An image sensor directly receives light emitted in response to both illuminations without an optical bandpass filter being disposed between the image sensor and the target, and captures a plurality of images based on the light emitted.
A processor analyzes a first fluorescence-based image comprising fluorescence emerging from the target and analyzes a second image to identify oxygenation at a plurality of regions of the target. The device and system detect the presence of a problematic cellular entity in the target by using an analysis model based on the first image and the identified oxygenation across the plurality of regions. The analysis model is trained using a plurality of reference fluorescence-based images and differentiates between fluorescence emerging from the problematic cellular entity and fluorescence emerging from regions other than the problematic cellular entity.
The framework supports examining oxygenation at multiple regions while simultaneously detecting the problematic cellular entity. The related independent claims also include transmitting a result to the device and using polarizers integrated with light sources and/or the image sensor.
Claims Coverage
The independent claims include five inventive features, each grounded in multiple image capture without an optical bandpass filter and analysis using a trained model.
Two-light-source excitation and non-fluorescing illumination
Illuminating the target with a first light source for causing a marker in the target to fluoresce and with a second light source that does not cause the marker in the target to fluoresce.
Filter-less direct imaging without optical bandpass filter
Configuring an image sensor to directly receive light emitted by the target in response to the first and second light sources without an optical bandpass filter disposed between the image sensor and the target, and capturing a plurality of images based on the light emitted.
Trained analysis model differentiating problematic-entity fluorescence
Training an analysis model using a plurality of reference fluorescence-based images to detect the presence of problematic cellular entities and to differentiate between fluorescence emerging from the problematic cellular entity and fluorescence emerging from regions other than the problematic cellular entity.
Oxygenation identification across target regions for detection support
Analyzing a second image of the captured plurality of images to identify oxygenation at a plurality of regions of the target, and detecting the presence of the problematic cellular entity based on the analysis of the first image and the identified oxygenation at the plurality of regions.
Reporting detection result to the coupled device
Transmitting to the device a result of the analysis indicating whether the problematic cellular entity is present in the target.
Collectively, the independent claims require filter-less multi-image acquisition using a two-light-source arrangement and direct sensor reception without an optical bandpass filter, together with a trained analysis model that differentiates fluorescence associated with the problematic cellular entity from fluorescence in other regions. The claims further require identifying oxygenation at multiple regions and using that identified oxygenation to support detection, with system language specifying transmission of the presence or absence result to the device.
Stated Advantages
Filter-less fluorescence-based detection without an optical bandpass filter being disposed between the image sensor and the target.
Detects the presence of a problematic cellular entity by differentiating fluorescence from the problematic cellular entity versus fluorescence from regions other than the problematic cellular entity.
Identifies oxygenation at a plurality of regions of the target and uses the identified oxygenation to support detection of a problematic cellular entity.
Documented Applications
Pathogen detection in a target, including detecting presence of a problematic cellular entity and differentiating and classifying using an analysis model trained on reference fluorescence-based images [procedural detail omitted for safety].
Identifying oxygenation at a plurality of regions of the target, including tissue oxygenation estimation as part of the analysis used with detection of the problematic cellular entity.
Anomaly detection by analyzing a white-light image captured using a second light source.
Thermal imaging of the problematic cellular entity using a thermal sensor configured for thermal imaging [procedural detail omitted for safety].
Pathogen characterization including gram type and taxonomic classification (family, genus, species, and strain) based on analysis of a fluorescence-based image.
Use of polarizers integrated with the first light source and/or the image sensor, including cross-polarizer geometry, to minimize interference.
Interested in licensing this patent?