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-11830190-B2
Publication Date
2023-11-28
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 disclosed invention relates to examining a target by illuminating the target with a first light source to cause a marker in the target to fluoresce within a wavelength band. The target is one of a wound region, a tissue, or a tissue sample, or alternatively is one of an edible product, a laboratory equipment, a sanitary device, a sanitary equipment, a biochemical assay chip, or a microfluidic chip. A fluorescence-based image is captured such that it comprises fluorescence emerging from the target.
A key part of the invention is capturing the fluorescence-based image using an image sensor configured to directly receive light emitted by the target without an optical bandpass filter being disposed between the image sensor and the target. The fluorescence-based image is analyzed by a processor using an analysis model. The analysis model is trained using a plurality of reference fluorescence-based images alone to detect presence of problematic cellular entities in targets.
The detection is performed based on the analysis of the fluorescence-based images alone by differentiating fluorescence in the fluorescence-based image emerging from the problematic cellular entity from fluorescence emerging from regions other than the problematic cellular entity. In the device context, the processor detects, based on the analysis, presence of a problematic cellular entity in the target. In the system context, the processor transmits a result indicating whether the problematic cellular entity is present in the target.
Further aspects include training an analysis model for analyzing fluorescence-based images by receiving a plurality of reference fluorescence-based images alone of targets, where at least some targets have a problematic cellular entity. The reference images are obtained without use of an optical bandpass filter such that the images comprise fluorescent light emitted by the targets and reflected excitation light illuminated upon the targets. An anomaly result corresponding to each reference fluorescence-based image alone is received, and the analysis model is trained so that it detects presence of a problematic cellular entity in a target captured in a first fluorescence-based image.
Claims Coverage
Inventive features are present across four independent claims: device-based examination, device/system-based examination, analysis-model training, and target-examination method. Across these claims, the coverage centers on fluorescence-based imaging without an optical bandpass filter and analysis-model training and detection using reference fluorescence-based images alone.
Fluorescence imaging without an optical bandpass filter for problematic cellular entity detection
Using a first light source to cause a marker in a target to fluoresce, capturing a fluorescence-based image directly with an image sensor without an optical bandpass filter disposed between the image sensor and the target, analyzing the fluorescence-based image using an analysis model trained using a plurality of reference fluorescence-based images alone, and detecting based on the analysis the presence of a problematic cellular entity by differentiating fluorescence emerging from the problematic cellular entity from fluorescence emerging from regions other than the problematic cellular entity.
System that transmits analysis results for fluorescence-based problematic cellular entity detection
Receiving a fluorescence-based image of a target using a coupled device having a first light source to cause a marker in the target to fluoresce and an image sensor that captures the fluorescence-based image without an optical bandpass filter disposed between the image sensor and the target, analyzing the fluorescence-based image using an analysis model trained using a plurality of reference fluorescence-based images alone to detect presence of problematic cellular entities, detecting based on fluorescence differentiation between regions emerging from the problematic cellular entity and regions other than the problematic cellular entity, and transmitting to the device a result indicating whether the problematic cellular entity is present in the target.
Training analysis model using reference fluorescence images alone without optical bandpass filter
Receiving a plurality of reference fluorescence-based images alone of targets, where images are obtained without use of an optical bandpass filter such that the images comprise both fluorescent light emitted by the targets and reflected excitation light illuminated upon the targets, receiving an anomaly result corresponding to each reference fluorescence-based image alone indicating whether the target has a problematic cellular entity, and training the analysis model based on the plurality of reference fluorescence-based images alone and their corresponding anomaly results to allow detection of presence of a problematic cellular entity in a target captured in a first fluorescence-based image.
Method for examining targets using fluorescence-based images alone and differentiation of problematic entity fluorescence
Illuminating a target using a first light source so that light emitted by the first light source on the target causes a marker in the target to fluoresce in a wavelength band, capturing a fluorescence-based image with an image sensor directly receiving light emitted by the target without an optical bandpass filter disposed between the image sensor and the target, analyzing the fluorescence-based image using an analysis model trained using a plurality of reference fluorescence-based images alone for detecting presence of problematic cellular entities, and detecting based on the analysis of the fluorescence-based images alone by differentiating fluorescence emerging from the problematic cellular entity from fluorescence emerging from regions other than the problematic cellular entity.
The independent claims collectively define a fluorescence-based examination approach centered on capturing fluorescence without an optical bandpass filter and using an analysis model trained on reference fluorescence-based images alone. Detection relies on differentiating fluorescence emerging from the problematic cellular entity from fluorescence emerging from other regions, and the system embodiment further transmits a presence/absence result to the device.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Examining a wound region to detect presence of problematic cellular entities.
Examining tissue or a tissue sample to detect presence of problematic cellular entities.
Examining an edible product to detect presence of problematic cellular entities.
Examining laboratory equipment to detect presence of problematic cellular entities.
Examining a sanitary device or sanitary equipment to detect presence of problematic cellular entities.
Examining a biochemical assay chip to detect presence of problematic cellular entities.
Examining a microfluidic chip to detect presence of problematic cellular entities.
Interested in licensing this patent?