Wearable devices for examining targets

Abstract

Wearable devices for examining a target are disclosed. The target may be suspected of having a problematic cellular entity, such as a pathogen, cancerous tissue, or necrotic tissue. The wearable device includes a light source assembly with light sources that emit excitation radiation at predetermined wavelengths to illuminate the target and cause fluorescence. An image sensor assembly captures fluorescence-based images of the target in response to illumination. A processor analyzes the captured images using an analysis model trained on reference fluorescence-based images to detect presence of problematic cellular entities. The processor generates an extended reality environment and renders results corresponding to the detection for viewing by a wearer. The wearable device may capture additional images including white light images, oxygenation-based images, and three-dimensional images for enhanced detection. The analysis model may classify problematic cellular entities by family, genus, species, gram type, or strain.

Description

WEARABLE DEVICES FOR EXAMINING TARGETSBACKGROUND

[0001] A target, such as a wound region in a human body, a wound region in an animal body, an edible product, a tissue sample extracted from a human body, a surface that is to be sterile, and the like, can include one or more problematic cellular entities. A cellular entity is made of one or more cells, such as unicellular organisms, multicellular organisms, tissues, or the like. A problematic cellular entity causes harm to living beings’ health, such as plant, animal, or human health or objects’ health. For instance, a problematic cellular entity is a pathogen that causes a disease in human beings. A cancerous tissue is a problematic cellular entity, which indicates the presence of tumor. As another example, the problematic cellular entity may cause harm to objects as well. For instance, a problematic cellular entity present in an edible product may contaminate the edible product and may cause harm to a person consuming the edible product. In another example, a problematic cellular entity may be present in objects, such as surgical blade, used in surgeries, and may cause harm to the surgical procedure. The presence of a problematic cellular entity on a target, such as a human body or an edible product, is to be detected, for example, to prevent the occurrence of a disease, to render a person free of a disease, and the like.BRIEF DESCRIPTION OF DRAWINGS

[0002] The features, aspects, and advantages of the present subject matter will be better understood with regard to the following description and accompanying figures. The use of the same reference number in different figures indicates similar or identical features and components.

[0003] Fig. 1 illustrates a wearable device for examining a target, in accordance with an implementation of the present subject matter.

[0004] Fig. 2 illustrates a method for examining a target, in accordance with an implementation of the present subject matter.

[0005] Fig. 3 illustrates a method for examining a target, in accordance with an implementation of the present subject matter.

[0006] Fig. 4 illustrates a wearable device for examining a target, in accordance with an implementation of the present subject matter.

[0007] Fig. 5 illustrates a method for examining a target, in accordance with an implementation of the present subject matter.

[0008] Fig. 6 illustrates training of an analysis model, in accordance with an implementation of the present subject matter.

[0009] Fig. 7 illustrates a wearable device for examining a target, in accordance with an implementation of the present subject matter.

[0010] Fig. 8 illustrates a wearable device connected to a processor, in accordance with an implementation of the present subject matter.

[0011] Fig. 9 illustrates a wearable device connected to a clip-on assembly, in accordance with an implementation of the present subject matter.

[0012] Fig. 10 illustrates a wearable device for examining a target, in accordance with an implementation of the present subject matter; and

[0013] Fig. 11 illustrates a wearable device for examining a target, in accordance with an implementation of the present subject matter.

[0014] Throughout the drawings, identical reference numbers designate similar elements, but may not designate identical elements. The figures are not necessarily to scale, and the size of some parts may be exaggerated to illustrate the example shown with better clarity. Moreover, the drawings provide examples and / or implementations consistent with the description; however, the description is not limited to the examples and / or implementations provided in the drawings.DETAILED DESCRIPTION

[0015] Targets, such as wound regions in a human body, wound regions in an animal body, regions in plant body, edible products, tissue samples extracted from a human body, surfaces that are to be sterile, and the like, may include problematic cellular entities. In this regard, to render the human body or animal body devoid of such problematic cellular entities, presence ofproblematic cellular entities on a target is to be accurately detected. Typically, presence of problematic cellular entities are conventionally detected using various techniques. For instance, a problematic cellular entity, such as a pathogen, is performed using a culture method. Accordingly, a sample is taken from a site that is expected to have a pathogen infection using a swab / deep tissue biopsy. Subsequently, the sample is subjected to an appropriate culture medium, in which the pathogen expected to be in the site grows with time. The pathogen, if any, in the site is then isolated and identified using biochemical methods. If the problematic cellular entities correspond to cancerous tissue, tissue biopsy is taken. Further, the tissue biopsy is examined under microscopy with staining techniques, such as hematoxylin and Eosin staining, Muci carmine staining, Papanicolaou stain, and the like, or without staining techniques, to identify if the tissue is a cancerous tissue. However, the aforementioned methods are cumbersome, require specialized microbiology facilities, and takes multiple days to identify the infection and classify the pathogen or the cancerous tissue.

[0016] In some cases, detection and classification of problematic cellular entities is performed based on autofluorescence arising from native biomarkers in the problematic cellular entities. The native biomarkers may be, for example, Nicotinamide Adenine Dinucleotide (Phosphate) Hydrogen (NAD(P)H), Flavins, Porphyrins, Pyoverdine, tyrosine, and tryptophan. The autofluorescence arising from the biomarkers may be unique to them and may be useful for detection and classification of the problematic cellular entities.

[0017] Although autofluorescence can be used for the detection and classification, the autofluorescence arising from the native biomarkers is weak, and may not be easily detected. Further, in addition to the autofluorescence, the light emerging from a target may include background light and excitation light, which may interfere with the emitted autofluorescence. Therefore, the detection and classification of the problematic cellular entities using autofluorescence is relatively less accurate.

[0018] In some scenarios, one or more imaging devices are used to facilitate identification of problematic cellular entities. For instance, imagesensors, such as fluorescence imaging devices, multispectral imaging devices, and the like, may be used to facilitate identification of problematic cellular entities. However, such imaging devices are specialized and inspection of problematic cellular entities using such devices is cumbersome. Further, some devices require separate apparatuses for different light sources, handheld scopes, and the like, to facilitate identification of the problematic cellular entities. Therefore, the conventional imaging devices are complex in operation, require multiple components, and are bulky in nature.

[0019] The present subject matter relates to wearable devices for examining targets. Using the present subject matter, a wearable device can be used for detecting and visualizing problematic cellular entities in targets. Further, a quick and accurate detection of problematic cellular entities can be achieved using Artificial Intelligence (Al) techniques.

[0020] A wearable device may enable examining a target. The target may be suspected of having a problematic cellular entity, such as a pathogen, a cancerous tissue, and the like. The target may be, for example, a wound in a body part of a human or an animal, a tissue sample of a human or an animal, an object that is to be free of pathogens, such as an edible product, a laboratory equipment, or a sanitary equipment, and the like. The wearable device may be, for example, a head-up display device (HUD). In an example, the wearable device may be in the form of eyeglasses. Hereinafter, the wearable device will be explained with reference to eyeglasses. As will be understood, the wearable device may be worn by a user (referred to as wearer).

[0021] The wearable device may include one or more light sources that emit excitation radiation at a predetermined range of wavelengths. At least one of the light sources may be in a predetermined range of wavelengths that causes a marker in the target to fluoresce when illuminated. In particular, the emitted excitation radiation may be of a single wavelength or a wavelength band that causes one or more markers in the target to fluoresce when illuminated. The one or more markers may be part of the problematic cellular entity. The fluorescence emitted by the one or more markers that is part of the problematic cellular entity may be referred to as autofluorescence.

[0022] In an example, an exogenous marker, such as a synthetic marker like Indocyanine Green (ICG) or methylene blue may be sprayed on the target to cause detection of the problematic cellular entity in the target. The exogenous marker may bind to cellular entities, such as deoxyribonucleic acid (DNA), Ribonucleic acid (RNA), proteins, blood, biochemical markers, and the like, which may cause the target to fluoresce. The fluorescence emitted by the added synthetic marker may also be referred to as exogenous fluorescence. The one or more light sources that cause the markers in the target to fluoresce will be referred to as a first set of light sources.

[0023] The exogenous marker may comprise at least one of Indocyanine Green (ICG), methylene blue, Fluorescein, Rhodamine, Alexa Fluor dyes, and Cyanine dyes. The exogenous marker may be applied to the target, and the illumination by the light source assembly may cause the exogenous marker to emit fluorescence for detection of the problematic cellular entity. Different exogenous markers may be selected based on the type of target and the type of problematic cellular entity to be detected. In one example, the problematic cellular entity comprises at least one of a pathogen, a bacterium, a fungus, a cancerous tissue, a necrotic tissue, or combinations thereof

[0024] Further, in another example, at least one of the light sources may be in a wavelength band without causing a marker in the target to fluoresce. In such scenarios, the target may reflect the light emitted by the at least one of the light sources. The one or more light sources that do not cause the markers in the target to fluoresce will be referred to as a second set of light sources. The light sources may, for example, include Ultraviolet (UV)-based light source, an Infra-Red (IR)-based light source, Near InfraRed (NIR)-based light source, Visible light source.

[0025] The second set of light sources may emit radiation at a second predetermined range of wavelengths to illuminate the target without causing the target to emit fluorescence. The second predetermined range of wavelengths may be different from the predetermined range of wavelengths of the first set of light sources. In an example, the second predetermined range ofwavelengths may comprise wavelengths in the visible region or the Near-lnfra Red (NI ) region.

[0026] In an example, the image sensor may be configured to directly receive the light emitted by the target in response to illumination of the target by the fluorescent light sources. In other words, an optical bandpass filter may not be disposed between the image sensor and the target. Here, the light is said to be directly received by the image sensor because the light emitted is not filtered by an optical bandpass filter before capturing the image. In another example, the wearable device may also include one or more emission filters. Each of the emission filters may remove one or more wavelength bands from the emitted light.

[0027] In an example, the image sensor may capture a first plurality of images formed based on the light emitted by the target. If the target includes a marker that fluoresces, the captured image includes fluorescence and may be referred to as a fluorescence-based image. Therefore, the fluorescence-based images may include fluorescence emerging from the target. In another example, the image sensor may capture a second plurality of images formed based on the light reflected by the target. In a yet another example, the image sensor may capture a third plurality of images formed based on the light reflected by the target. In a further example, the image sensor may capture a fourth plurality of images based on the light reflected by the target. The second plurality of images, the third plurality of images, and the fourth plurality of images may not include fluorescence. Further, in an example, the image sensor may capture one or more images that are transmitted by the target for the analysis and the detection of the problematic cellular entities.

[0028] In an example, the wearable device may include a built-in processor to analyze the first plurality of images (the fluorescence-based images), the second plurality of images, the third plurality of images, the fourth plurality of images. In addition, in an example, the built-in processor may analyze the one or more images transmitted by the target.

[0029] The analysis may be done using an analysis model that is trained for detecting the presence of problematic cellular entities in targets. Forinstance, the analysis model may be an Al model. The analysis model may include an artificial neural network (ANN) model or a machine learning (ML) model other than an ANN model, such as a support vector machine (SVM) model, logistic regression model, random forest model, and the like, or a combination thereof. In another example, the analysis model may include both an ANN model and a ML model. In an example, the analysis model may be a single Large Language Models (LLM) or multi-modal large language models (LLM).

[0030] The analysis by the analysis model may include analyzing the fluorescence in the fluorescence-based image, such as the wavelengths of fluorescence. The processor may detect presence of a problematic cellular entity in the target based on the analysis of the fluorescence-based image using the analysis model. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained. For instance, the analysis model may be trained using a plurality of reference fluorescencebased images for detecting the presence of problematic cellular entities in targets. The analysis model may be trained to differentiate between fluorescence in the fluorescence-based image emerging from the problematic cellular entity and fluorescence in the fluorescence-based image emerging from regions other than the problematic cellular entity. For example, the analysis model may differentiate between fluorescence emerging from a wound region having a pathogen and fluorescence emerging from a skin surrounding the wound region..

[0031] In an example, the image sensor assembly may comprise an image sensor configured to directly receive light emitted by the target without filtering by an optical bandpass filter. In such scenarios, the analysis model may be trained to differentiate between fluorescence in the fluorescence-based images emerging from the problematic cellular entity and fluorescence in the fluorescence-based images emerging from regions other than the problematic cellular entity. The training of the analysis model to differentiate between fluorescence regions enables accurate detection of the problematic cellularentity even in the absence of optical bandpass filters between the target and the image sensor.

[0032] In addition, in an example, the processor may include analyzing the image of the second plurality of images. The second plurality of images may correspond to the white light images. In such a scenario, the processor may detect presence of a problematic cellular entity in the target based on the analysis of the fluorescence-based image and based on the image of the second plurality of images using the analysis model. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained. For instance, the analysis model may be trained using a plurality of reference fluorescence-based images and a plurality of white light images.

[0033] In yet another example, the processor may include analyzing the image of the third plurality of images using the analysis model. The analysis of the image of the third plurality of images may include identification of oxygenation at a plurality of regions in the target. In such a scenario, the processor may detect presence of a problematic cellular entity in the target based on the analysis of the fluorescence-based image and based on the identified oxygenation. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained using a plurality of reference fluorescence-based images and the third plurality of images.

[0034] The processor may determine tissue oxygenation at the target based on analysis of the third plurality of images. The tissue oxygenation may comprise at least one of deoxygenated hemoglobin of the target, oxygenated hemoglobin of the target, oxygen saturation of the target, skin perfusion, and oxyhemoglobin. The processor may analyze, using the analysis model, the first plurality of images and the third plurality of images to detect presence of the problematic cellular entity on the target based on the determined tissue oxygenation. The analysis model may be trained using a plurality of reference fluorescence-based images and a plurality of reference oxygenation-based images to detect presence of problematic cellular entities in targets.

[0035] In yet another example, the processor may include analyzing the image of the fourth plurality of images using the analysis model. The fourth plurality of images may correspond to three-dimensional images. The processor may detect presence of a problematic cellular entity in the target based on the analysis of the fluorescence-based image and based on the analysis of the three-dimensional image. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained using a plurality of reference fluorescence-based images and the fourth plurality of images.

[0036] In a yet further example, the processor may include analyzing the fluorescence-based image, an image of the second plurality of images, an image of the third plurality of images, an image of the fourth plurality of images using the analysis model, or a combination thereof. The processor may detect presence of a problematic cellular entity in the target based on the analysis of the fluorescence-based image, based on the analysis of the image of the second plurality of images, based on the identified oxygenation at the plurality of regions in the target, based on the analysis of the three-dimensional image, or a combination thereof. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained using a plurality of reference fluorescence-based images, the first plurality of images, the second plurality of images, the fourth plurality of images, or a combination thereof.

[0037] The image sensor assembly may capture a second plurality of images of the target in response to illumination thereof by the second set of light sources, the second plurality of images corresponding to one or more white light images formed based on light reflected by the target; a third plurality of images of the target in response to illumination thereof by the second set of light sources, the third plurality of images corresponding to one or more images formed based on light reflected by the target and associated with identification of oxygenation at a plurality of regions in the target; and a fourth plurality of images of the target in response to illumination thereof by the second set of light sources, the fourth plurality of images corresponding to one or more three-dimensional images formed based on light reflected by the target. The processor may analyze, using the analysis model, the first plurality of images, the second plurality of images, the third plurality of images, and the fourth plurality of images, or combinations thereof, to detect presence of the problematic cellular entity on the target. The analysis model may be trained using a plurality of reference fluorescence-based images, a plurality of reference white light images, a plurality of reference oxygenation-based images, and a plurality of reference three-dimensional images, or combinations thereof, to detect presence of problematic cellular entities in targets.

[0038] The processor may generate a composite image comprising a fluorescence-based image of the first plurality of images, an image of the second plurality of images, an image of the third plurality of images, and an image of the fourth plurality of images, or combinations thereof, depicting presence of the problematic cellular entity in the target. In an example, the composite image may further comprise a thermal image. The composite image may be rendered on the extended reality environment for viewing by the wearer. The composite image may enable the wearer to visualize the problematic cellular entity using multiple imaging modalities simultaneously or selectively.

[0039] In an example, the composite image may be transmitted to a device external to the wearable device, such as a smartphone, a computer, a TV screen, a tablet, a remote display, or the like. The composite image may also be transmitted to a cloud storage platform and may be stored in a cloud storage platform for remote access, consultation, or archival purposes. In another example, the composite image may be live streamed to an external system for real-time viewing by a remotely located medical professional, enabling telemedicine applications, remote consultation, or educational purposes. This real-time feedback capability may reduce the need for repeated surgical interventions and may improve patient outcomes by ensuring thorough removal of infected tissue during the initial procedure. Further, since the wearable device may transmit the result to an external system using the connectivity module, a remotely located medical professional may view theresult in real-time while the wearer examines the target. The wearer may receive guidance from the remotely located medical professional while continuing to examine the target using the wearable device, without requiring the wearer to operate a separate device for communication.

[0040] In another example, the processor may include analyzing the one or more images that are transmitted by the target using the analysis model. The processor may detect presence of a problematic cellular entity in the target based on the analysis.

[0041] The processor may analyze, using the analysis model, the first plurality of images to detect presence of the problematic cellular entity on the target. The analysis model may be trained using a plurality of reference fluorescence-based images to detect presence of problematic cellular entities in targets. The processor may generate a composite image comprising a fluorescence-based image of the first plurality of images, depicting presence of the problematic cellular entity in the target, and render the composite image on the extended reality environment.

[0042] The image sensor assembly may further comprise a thermal sensor for thermal imaging of the target. The thermal sensor may capture one or more thermal images of the target in response to thermal radiation emitted by the target. The thermal images may be used to determine temperature distribution at the target. The processor may analyze, using the analysis model, the first plurality of images and the one or more thermal images to detect presence of the problematic cellular entity on the target. The analysis model may be trained using a plurality of reference fluorescence-based images and a plurality of reference thermal images to detect presence of problematic cellular entities in targets. The processor may generate a composite image comprising a fluorescence-based image of the first plurality of images and a thermal image, depicting presence of the problematic cellular entity in the target, and render the composite image on the extended reality environment.

[0043] In response to the detection, the processor may render a result corresponding to the detection of the problematic cellular entity. In an example, the result may include Augmented Reality or a virtual Reality corresponding tothe detection of the problematic cellular entities. For instance, the result may include detected problematic cellular entities overlaid on the field of view of a user onto a display of the wearable device. Since the wearable device is worn on the head of the wearer and the image sensor assembly is part of the wearable device, the field of view of the image sensor assembly may correspond to the field of view of the wearer. Accordingly, the detected problematic cellular entities may be overlaid on the display at positions corresponding to the positions of the problematic cellular entities in the field of view of the wearer.

[0044] In another example, the result may include virtual environment rendered by the processor. The virtual environment may include the problematic cellular entity on the target provided a composite image. The composite image may include the fluorescence-based image, and / or image of the second plurality of images, and / or image of the third plurality of images, and / or image of the fourth plurality of images.

[0045] The wearable device may generate an extended reality environment for viewing by the wearer of the wearable device. The extended reality environment may comprise at least one of a virtual reality environment and an augmented reality environment. The processor may render a result corresponding to the detection of the problematic cellular entity on the target on the extended reality environment. The extended reality environment may enable the wearer to visualize the detected problematic cellular entities in realtime while examining the target. Since the wearable device is worn on the head of the wearer, for example, the image sensor assembly may capture images of the target as the wearer moves relative to the target, and the processor may continuously analyze the captured images and render updated results on the extended reality environment. The wearer may examine different regions of the target by moving the head, and the wearable device may detect and render results corresponding to each region as the wearer examines the target.

[0046] In an example, the image sensor assembly may capture images, the processor may analyze the captured images using the analysis model, and the processor may render the result on the display or using the projectionelement such that the wearer views detection results in real-time while examining the target.

[0047] The result rendered on the extended reality environment may comprise at least one of: a composite image comprising at least one of a fluorescence-based image of the first plurality of images, a white light image, an oxygenation-based image, a three-dimensional image, a thermal image,; detected problematic cellular entities overlaid on a field of view of the wearer onto a display of the wearable device; one or more alerts triggered when at least one of an intensity of the problematic cellular entity exceeds a threshold intensity and a parameter associated with the detected problematic cellular entity is outside a nominal range; one or more recorded images or videos corresponding to the detection of the problematic cellular entity; and a real-time stream of the result to an external system communicatively coupled to the wearable device. The one or more alerts may notify the wearer when the detected problematic cellular entity exceeds predetermined thresholds or when parameters associated with the problematic cellular entity fall outside acceptable ranges.

[0048] In the present context, the nominal range may be a predetermined range based on clinical standards, user-defined thresholds, or ranges determined during training of the analysis model. The nominal range may vary based on the type of target, the type of problematic cellular entity, or the specific application. For example, the nominal range for oxygen saturation may be different from the nominal range for degree of infection.

[0049] In one example, the intensity of the problematic cellular entity may refer to at least one of fluorescence intensity, signal intensity, and optical intensity associated with the detected problematic cellular entity. The threshold intensity may be a predetermined value based on clinical standards, calibration data, or training of the analysis model.

[0050] In an example, to display the result corresponding to the detection of the problematic cellular entity, the wearable display may include a display. The display may support Augmented reality rendering or virtual realityrendering. In another example, instead of the display, the wearable device may include a projection element to project the result onto eyes of the wearer.

[0051] In addition to detecting the presence of the problematic cellular entity in the target, the analysis model may also classify the problematic cellular entity. For example, if the problematic cellular entity is a pathogen, the analysis model may identify the gram type or species of the problematic cellular entity.

[0052] In an example, the analysis model may be optimized so as to be stored in the built-in processor while also maintaining the accuracy in detection of the problematic cellular entity. The optimization may be performed so as to ensure minimal power consumption, reduced storage, and minimal latency. Since the wearable device is worn by the wearer, the optimization of the analysis model may enable the wearable device to operate using a battery of the power module without requiring connection to an external power source. The optimization may also enable the processor to perform the analysis and render the result in real-time as the wearer examines the target. Therefore, the present subject matter ensures reduced battery drainage and faster analysis with minimal latency.

[0053] In an example, the analysis model may not be stored in the built-in processor but in a processor that is stored in a platform, such as a cloud storage platform. In this regard, the wearable device may transmit the captured images to the processor in the cloud storage platform and the analysis may be performed in the cloud storage platform. In this regard, to transmit one or more data such as the captured images, rendered result, and the like, the wearable device may include one or more connectivity modules, such as cellular connectivity, Bluetooth connectivity, and the like. With the connectivity module, the wearable device may transmit the AR and / or VR display to external systems, such as for live streaming or recorded images / videos for performing surgeries, telemedicine, tele healthcare, education purposes, cloud-based analytics, and the like.

[0054] The connectivity module may transmit at least one of the first plurality of images and the result corresponding to the detection to a location outside the wearable device. The location outside the wearable device mayinclude an external system, a cloud storage platform, a remote server, a display device, or another computing device. The transmission may enable remote viewing, analysis, consultation, or storage of the captured images and the detection results. In an example, the result of the analysis model may be displayed back onto the wearable device. The result may also be shared with any other external device, such as a smartphone, a computer, a TV screen, or the like. In another example, the result of the analysis model may be transmitted to a storage platform, such as an external cloud storage platform, and may be stored in the storage platform.

[0055] The wearable device may include a lens that is part of, for example, a prescription glass. The wearable device may include a clip-on assembly that may include the image sensor, the light sources, the connectivity module, and the processor. The clip-on assembly may be adapted to be mounted onto a pair of eyeglasses, enabling the wearable device to be used with existing eyewear. The lens may enable viewing of the target by the wearer while the processor identifies the problematic cellular entity or the absence of the problematic cellular entity in the target based on the analysis. Since the wearable device is worn by the wearer, for example, the wearer may simultaneously view the target through the lens and view the result corresponding to the detection on the display or as projected onto the eyes of the wearer by the projection element. This simultaneous viewing may enable the wearer to correlate the detected problematic cellular entity with the corresponding location on the target without shifting gaze between the target and a separate display.

[0056] The wearable device may include a control module to control the wearable device. The control module may include one or more audio modules. The audio modules may include, for example, a speaker and a microphone. For instance, the wearer may be able to change the modes of display of the result, changing imaging modes (fluorescence, reflectance, oxygenation, transmittance, and the like), control various components corresponding to the wearable device, and the like. The control module may include tactile feedback module, gesture reading module, and the like. In addition, the wearable devicemay include components, such as excitation filters, polarizers, ranging sensors, thermal sensor, and the like.

[0057] The present subject matter enables detection of problematic cellular entities using a wearable device. Since the analysis model used for detection of the problematic cellular entities is optimized, the present subject matter ensures relatively lesser power consumption in comparison with the conventional imaging devices. Since the wearable device enables transmission of data to external systems, the present subject matter may be provided with a non-medical professional or medical professional may transmit an image, a set of images, one or more videos to remotely located systems. Therefore, with the present subject matter, live-streaming or recorded images or videos of surgeries may be transmitted to the external systems. Accordingly, the present subject matter can be used in applications of education (such as for lab experiments), telemedicine, and the like. The present subject matter can also be used, for example, by a medical professional for additional consultation prior to treatment using the device(s) of the present disclosure. In addition, the present subject matter can also be used, for example, by a surgeon for training understudy, for consultation with another experienced surgeons, and the like, for performing surgeries. The present subject matter can also be used during surgical procedures such as debridement to see if the infectious tissue is being effectively removed. Since the wearable device is hands-free, for example, a surgeon may use both hands for the debridement procedure while simultaneously viewing the detection results rendered on the display or projected onto the eyes of the surgeon. The surgeon may view the detection results without looking away from the target, thereby enabling continuous monitoring of the debridement procedure.

[0058] The present subject matter provides a rapid, optionally filter-less, non-invasive, automatic, and in-situ detection and classification of pathogens using an “opto-computational biopsy” technique. The opto-computational biopsy technique is a technique in which multispectral imaging is used along with the computational models, such as machine learning models, Artificial Neural Network (ANN) models, deep learning models, and the like, for non-invasive biopsy to detect the problematic cellular entities by using a wearable device.

[0059] The present subject matter can be used for detecting the presence of problematic cellular entities in diabetic foot ulcers, surgical site infections, bums, skin, and interior of the body, such as esophagus, stomach, and colon. The device of the present subject matter can be used in the fields of dermatology, cosmetology, plastic surgery, infection management, photodynamic therapy monitoring, and anti-microbial susceptibility testing.

[0060] Further, the device may be used to detect the time-dependent changes in the fluorescence to understand colonization of pathogens and necrotic tissue. In other words, the wearable device may be configured to detect changes from fluorescence between a first imaging of the target relative to a subsequent imaging of the target. For instance, the wearable device may be configured to detect changes in fluorescence between pre-debridement of a wound and post-debridement of the wound and may render the result corresponding to the changes. The detection may enable to accurately remove the dead / unhealthy tissue from the wound.

[0061] In another example, the wearable device may be configured to detect changes in fluorescence between an image of the wound taken on a first day and an image of the wound taken on a subsequent day. Since the wearable device is portable, the same wearable device may be used by the wearer to examine the wound on the first day and on the subsequent day. The wearable device may store the image of the wound taken on the first day in a memory of the wearable device or in a cloud storage platform using the connectivity module. On the subsequent day, the processor may compare the image of the wound taken on the subsequent day with the stored image of the wound taken on the first day to detect the changes in fluorescence. The detection may help in ascertaining healing of the wound and allow a medical practitioner to administer medications according to the detection.

[0062] With the present subject matter, most of the clinically relevant pathogens may be detected and classified in a few minutes. This feature helps in quickly deciding the treatment protocol corresponding to the detectedproblematic cellular entity. Further, data acquisition and analysis may happen automatically. Therefore, the device can be worn by anyone and operated without requiring skillful technicians. The device may also be used for detection and classification of pathogens in resource scarce settings.

[0063] The wearable device of the present subject matter may be used for quantification of various pathogens present in the sample. The wearable device may also be used for identifying problematic cellular entities, such as infections, measuring tissue perfusion, tissue oxygenation, oxyhemoglobin, and the like. The wearable device may be used for monitoring status of the wound. The device may also be used to study wound parameters, such as wound size, wound depth, wound temperature distribution, tissue classification, biofilm information, and degree of contamination. The biofilm information may include at least one of presence of biofilm, extent of biofilm, type of biofilm, thickness of biofilm, and location of biofilm on the wound region. The processor may determine the biofilm information based on analysis of the fluorescencebased images, as biofilms may exhibit characteristic fluorescence patterns.

[0064] The present subject matter may have different diagnostic modes, such as diagnostic mode, forensic mode, cosmetic mode, surface inspection mode, and education or transmittance modes for usage in various applications. The wearable device of the present subject matter can be used in applications corresponding to monitoring surface contamination, such contamination of edible objects, contamination of objects that are to be sterile, such as surgical blade, lab equipment, and the like. The wearable device may reveal contaminated regions that fluoresce under illumination of the light sources, such as UV light source and / or I R light source, based on the analysis of images of the surface captured under the illumination by the light sources. The wearable device may also quantify the contamination on various surfaces. Accordingly, the present enables guiding thorough cleaning of surfaces, disinfection of surfaces, and to adhere to sterilization protocols. For instance, the wearable device may facilitate studying effectiveness of disinfectants on various hospital surfaces such as beds, walls, hands, gloves, bandages,dressings, catheters, endoscopes, hospital equipment, sanitary devices, and the like.

[0065] The wearable device of the present subject matter may be used in cosmetology applications. For instance, the wearable device of the present subject matter may be used to visualize subdermal features, such as blood flow, pigment distribution, and the like, evaluating vascular flow for cosmetic treatments and skincare routines. For example, the wearable device may be used to detect the presence of Propionibacterium which causes acnes. For the visualization of the subdermal features and evaluation of vascular flow, the wearable device may facilitate illumination of skin by different light sources and may analyze the images captured in response to the illumination of the skin. The visualization of the subdermal features may enable planning and evaluation of treatments. The treatments may include debridement, dressings, topical medicines, antibiotics, hyperbaric oxygen therapy, vacuum assisted closure, negative wound pressure therapy, and the like. The device may also be used during tissue grafting to ensure that the tissue is free of pathogens.

[0066] The wearable device of the present subject matter may be used in forensic investigations. The wearable device may detect bodily fluids, such as blood, mucus, and the like, trace evidence invisible to the naked eye under normal light conditions at places, such as crime scenes and / or forensic labs. For the detection of bodily fluids and tracing evidence, the wearable device may illuminate the target using different light sources and analyze various images corresponding to the target obtained in response to the illumination thereof.

[0067] The wearable device may be used in educational applications and for research applications for activities, such as demonstrating fluorescence, reflectance, and transmittance principles in laboratory settings or classroom settings. In other words, the present subject matter enables assessing ample properties by analyzing how different wavelengths pass through different materials.

[0068] The wearable device of the present subject matter is hands-free, portable, and versatile. For instance, since the wearable device can be worn by the user, the present subject matter replaces various specializedinstruments, such as imaging devices, light sources, and the like, with a single device. The present subject matter may provide real-time analysis to detect and classify problematic cellular entities and visualize contaminants, infections, state of a tissue sample, and the like. The present subject matter has a multispectral capability, such as UV imaging, IR imaging, visible imaging, transmittance imaging, and the like. The present subject matter may facilitate edge-based Al technique or cloud-based Al or a combination of both for the analysis and / or detection and / or visualization of the problematic cellular entities.

[0069] The wearable device can be used for detecting the presence of problematic cellular entities in diabetic foot ulcers, surgical site infections, bums, skin, and interior of the body, such as esophagus, stomach, and colon. The wearable device can also be used in the fields of plastic surgery, photodynamic therapy monitoring, and anti-microbial susceptibility testing. For instance, the wearable device may also be used to study anti-microbial susceptibility / resistance by observing and analyzing the target by exposing the target to various antibiotics. For example, the wearable device may be used to study bacterial growth with nutrients and antibiotics, and corresponding biomarker signatures may be recorded. This information may be used to obtain information on the antibiotics to be prescribed based on the antimicrobial susceptibility of the particular bacteria. As will be understood, antimicrobial susceptibility of other pathogens, such as fungi, can also be identified using the wearable device. Further, dose and concentration of antibiotics can also be decided based on dilution factors, to determine the dosage of the antibiotics or antifungals to be given. The wearable device can also be used for quantification of various pathogens present in the sample. The intensity information at various spectral bands may be obtained from the sample and compared with the fluorescence intensity and / or reflection intensity data from the library database for intensity quantification.

[0070] The wearable form factor of the wearable device provides advantages over non-wearable imaging devices. Since the wearable device is worn by the wearer, the wearer may examine the target while simultaneouslyviewing the detection results without requiring a separate display or monitor. The wearer may use both hands for other tasks, such as surgical procedures, while the wearable device captures images, analyzes the images, and renders the results. The image sensor assembly of the wearable device may capture images from the perspective of the wearer, enabling the detected problematic cellular entities to be overlaid on the field of view of the wearer at positions corresponding to the actual positions of the problematic cellular entities on the target. The portable nature of the wearable device may enable the wearer to examine targets at different locations without requiring transportation of bulky equipment.

[0071] The above and other features, aspects, and advantages of the subject matter will be better explained with regard to the following description, appended claims, and accompanying figures. It should be noted that the description and figures merely illustrate the principles of the present subject matter along with examples described herein and should not be construed as a limitation to the present subject matter. It is thus understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and examples thereof, are intended to encompass equivalents thereof. Further, for the sake of simplicity, and without limitation, the same numbers are used throughout the drawings to reference-like features and components.

[0072] Fig. 1 illustrates a wearable device 100 for examining a target 102, in accordance with an implementation of the present subject matter. The wearable device 100 may be, for example, a Head-up Display (HUD) device. In an example, the wearable device 100 may be eyeglasses. Hereinafter, the wearable device 100 will be explained with reference to the eyeglasses. The wearable device 100 may be used for examining the target 102. The target 102 may be made of one or more cells. For instance, the target 102 may be a wound on a human body part, a wound on an animal body part, a tissue sample, a portion of the human body part or an animal body part, an article that is to be free of pathogens, such as an edible product, a laboratory equipment, a mask,a head mask, a surgical blade, a sanitary device, a sanitary equipment, ambient air, a biochemical assay chip, and a microfluidic chip. In another example, the target 102 may be a bodily fluid, such as pus, blood, urine, saliva, sweat, semen, mucus, plasma, water, and the like, that may be suspected of having a pathogen. In a yet another example, the target 102 may be materials, such as Indocyanine Green (ICG), Fluorescein, Rhodamine, Alexa Fluor dyes, Cyanine dyes, and other similar compounds used in diagnostic or imaging applications.

[0073] The target 102 may be suspected to be having a problematic cellular entity, such as a pathogen, a cancerous tissue, a necrotic tissue, or the like. For instance, the wound may be suspected of having a pathogen in it, which may cause delay in healing of the wound or may cause an infection of the wound. The target 102 may be an edible product, which may have to be tested for the presence of pathogens before supplying it for human consumption. Hereinafter, the target 102 will be explained with reference to the wound on the human body part and the problematic cellular entity will be explained with reference to pathogens.

[0074] The image sensor assembly 110 may include a light source assembly 104. The light source assembly 104 may include a plurality of light sources. Each of the plurality of light sources may include a first set of light sources. The first set of light sources may emit excitation radiation at a predetermined range of wavelengths. In particular, the emitted excitation radiation may be of a single wavelength or a wavelength band that causes one or more markers in the target 102 to fluoresce when illuminated. For instance, the first set of light sources may be, for example UV-based light sources, IR-based light sources, and / or NIR-based light sources. In particular, the plurality of light sources may be UV- Light Emitting Diodes (LEDs), IR LEDs, NIR LEDs, UV Light amplification by stimulated emission of radiation (LASER), IR LASER, and / or NIR LASER. In an example, one or more light sources of the plurality of light sources is a Pulsed Light Emitting Diode (LED) or Pulsed LASER.

[0075] In an example, wavelength bands of the light that are used to elicit fluorescence from the target 102 may include 200 nm-300 nm, 300 nm-400 nm, 400 nm-500 nm, or 500 nm-600 nm. In a particular example, the wavelengthsof the light that are used to elicit fluorescence from the target 102 may include 280 nm, 310 nm, 330 nm, 365 nm, 395 nm, 405 nm, 415 nm, 430 nm, 480 nm, and 520 nm. In an example, the wavelength bands of the light may include 600 nm-700 nm, 700 nm-800 nm, or 800 nm-1000 nm. In a particular example, the wavelength of the light that is used to elicit fluorescence from the target 102 may also include 430 nm, 630 nm, 660 nm, 680 nm, 735nm, 830 nm, 880 nm, 940 nm, and 970 nm.

[0076] In an example, the second set of light sources for illuminating the target 102 without causing the marker in the target 102 to fluoresce. Each of the second set of light sources may be configured to emit the light with a wavelength in a Near-lnfra Red (NIR) region ora visible region. The plurality of light sources may be, for example, homogenous light sources or non-homogenous light sources. In an example, the use of non-homogenous light sources may enable reducing or eliminating background light in light emitted by the target 102.

[0077] In an example, the light source assembly 104 may include other components, such as a first set of excitation filters. Each of the first set of excitation filters may filter the excitation radiation emitted by a light source of the first set of light sources of a predetermined range of wavelengths to pass through thereof to illuminate the target 102. In addition, the light source assembly 104 may include a second set of excitation filters that may be configured to filter the excitation radiation emitted by a light source of the second set of light sources of a predetermined range of wavelengths to pass through thereof.

[0078] In addition, optionally, the light source assembly 104 may include light diffusers and / or polarizers placed in front of the first set of light sources, and / or the second set of light sources, and / or the first set of excitation filters, and / or the second set of excitation filter to better spread the light onto the target 102. A polarizer may be an optical element that lets light waves of a specific polarization pass through while blocking light waves of other polarizations. A polarizer may condition a beam of light of undefined or mixed polarization into a beam of well-defined polarization.

[0079] The wearable device 100 may include an optical module 106. The optical module 106 may include lens 108, an image sensor assembly 110, and a display 111. The lens 108 may correspond to the lens through which a user of the wearable device 100 may be able to view outside environment. The image sensor assembly 110 may include an image sensor. The image sensor may be a multispectral camera configured to capture the light emitted by the target 102 and / or light reflected by the target 102, and / or light transmitted by the target 102 at a plurality of wavelengths. In particular, the multispectral camera may capture the light emitted at wavelengths in visible region, UV region, NIR region, or a combination thereof. In another example, the image sensor may be a charge coupled device (CCD) sensor, a CCD digital camera, a complementary metal-oxide semiconductor (CMOS) sensor, a CMOS digital camera, a single-photon avalanche diode (SPAD), a single-photon avalanche diode (SPAD) array, an Avalanche Photodetector (APD) array, a photomultiplier tube (PMT) array, a NIR sensor, a RGB sensor, a thermal camera, or a combination thereof. In an example, one or more lens 108 (not shown in Fig. 1) may be integrated with the image sensor to focus the light onto the image sensor and to capture the images.

[0080] The image sensor may capture a first plurality of images based on the light emitted by the target 102 in response to the illumination thereof by one or more of the first set of light sources. In an example, the image sensor may be configured to directly receive the light emitted by the target 102 in response to illumination of the target 102 by the plurality of light sources. In other words, an optical bandpass filter may not be disposed between the image sensor and the target 102. Here, the light is said to be directly received by the image sensor because the light emitted is not filtered by an optical bandpass filter before capturing the image.

[0081] In an example, the image sensor may capture a first plurality of images formed based on the light emitted by the target 102 in response to the illumination thereof by the first set of light sources. If the target 102 includes a marker that fluoresces, the captured image includes fluorescence and may bereferred to as a fluorescence-based image. Therefore, the fluorescence-based images may include fluorescence emerging from the target 102.

[0082] In another example, the image sensor may capture a second plurality of images formed based on light reflected by the target 102 in response to illumination thereof by at least one or more light sources of the second set of light sources. The second set of light sources may correspond to the white light images.

[0083] In a yet another example, the image sensor may capture a third plurality of images formed based on the light reflected by the target 102 in response to the illumination thereof by at least one or more light sources of the second set of light sources. The third plurality of images may correspond to identification of oxygenation in the target 102.

[0084] In a further example, the image sensor may include a three-dimensional image sensor. The three-dimensional image sensor may receive light reflected by the target 102 in response to the illumination thereof by the at least one or more light sources of the second set of light sources and may generate a fourth plurality of images of the target 102 based on the reflected light. The fourth plurality of images may be three-dimensional images of the target 102. In an example, instead of being illuminated by the at least one or more light sources of the second set of light sources, the three-dimensional image sensor may include one or more light sources (not shown in Fig. 1) integrated with the three-dimensional image sensor. In such scenarios, the three-dimensional image sensor may receive light reflected by the target 102 in response to the illumination thereof by the one or more light sources integrated with the three-dimensional image sensor. However, in some examples, separate light sources may also be coupled with the three-dimensional image sensor to illuminate the target 102 and to enable capturing of the light reflected by the target 102 due to the illumination. In an example, the three-dimensional image sensor may be a structured-light sensor, a time-of-flight sensor, a stereo sensor, or a combination thereof.

[0085] The image sensor may include a thermal sensor for thermal imaging of the target 102. The image sensor assembly 110 may include aranging sensor operable to determine a distance of the target 102 from the device. In an example, the three-dimensional image sensor may be used as the ranging sensor. In this regard, the three-dimensional image capturing sensor may be operable to determine a distance of the target 102 from the wearable device 100. In an example, three-dimensional image sensor can be used for getting the depth profile of the target. As used herein, the term "image sensor" or "image sensor assembly" may be interchangeably referred to as "imaging device" or "imaging device assembly," respectively. The working of the processor 112 will be explained with reference to Fig. 2 and Fig. 3.

[0086] In an example, the light source assembly 104 may be free of polarizers. In another example, the light source assembly 104 may include a plurality of polarizers (not shown in Fig. 1). For instance, the light source assembly 104 may include a first polarizer positioned between the first set of light sources and the target 102 to let the excitation radiation of the first set of light sources of a first polarization to pass through. Light source assembly 104 may include a second polarizer positioned between the target 102 and the image sensor to let the light emitted by the target 102 of a second polarization to pass through. In an example, the first polarizer may be aligned 90 degrees from the second polarizer. The provision of the polarizer in front of the image sensor may prevent excitation light from entering the image sensor.

[0087] In an example, the first polarization and the second polarization may be same. For instance, in an example, the first polarization and the second polarization may be a Left-Handed Circular polarization (LHCP). In another example, the first polarization and the second polarization may be a Right-Handed Circular Polarization (RHCP). In another example, the first polarization and the second polarization may be different. For instance, the first polarization may be one of: LHCP or RHCP and the second polarization may be other of: LHCP or RHCP. The plurality of polarizers can be combined with the first set of excitation filters.

[0088] The first polarizer may be aligned 90 degrees from the second polarizer. One of the first polarization and the second polarization may comprise a Left-Handed Circular Polarization (LHCP) and the other of the firstpolarization and the second polarization may comprise a Right-Handed Circular Polarization (RHCP). For example, the first polarization may be LHCP and the second polarization may be RHCP, or vice versa. The cross-polarization arrangement may reduce specular reflection and improve detection of fluorescence from the target.

[0089] While, in an example, the image sensor may receive the light directly from the target 102 without an optical bandpass filter being provided between the image sensor and the target 102, in some examples, the image sensor assembly 110 may include one or more optical bandpass filters. Each of the plurality of optical bandpass filters may be configured to filter light emitted by the target 102 in response to illumination thereof by at least one or more light sources of the first set of light sources and / or the second set of light sources of a predetermined wavelength to pass through thereof. In an example, the optical bandpass filters may have center wavelengths corresponding to the peak emitted fluorescence from various autofluorescence biomarkers or exogenous fluorophores. The optical bandpass filters can be low pass, high pass, single or multiple bandpass filters. The image sensor may capture the filtered light filtered by an optical bandpass filter of the plurality of optical bandpass filters and to capture the first plurality of images, the second plurality of images, the third plurality of images, and the fourth plurality of images formed based on the filtered light.

[0090] In such a scenario, the image sensor assembly 110 may include an emission filter wheel rotatably disposed within the image sensor assembly 110. The emission filter wheel operably coupled to a servo motor. The emission filter wheel may also be manually operated. The emission filter wheel may include the first plurality of optical bandpass filters. As will be understood, based on required optical bandpass filter from out of the plurality of optical bandpass filters, the servo motor may be actuated or the emission filter wheel may be manually rotated, to position the required optical bandpass filter between the target 102 and the image sensor.

[0091] In another example, the image sensor assembly 110 may include a plurality of tunable filters that are electronically controllable to automaticallyfilter specific spectral bands. Each of the plurality of tunable filters may be configured to filter light emitted by the target 102 in response to illumination thereof by at least one or more light sources of the first set of light sources and / or the second set of light sources of a predetermined wavelength to pass through thereof.

[0092] In the above example, the one or more optical bandpass filters, the emission filter wheel, and the plurality of tunable filters are explained to be a part of the image sensor assembly 110. However, in other examples, the one or more optical bandpass filters, the emission filter wheel, and the plurality of tunable filters can be a part of a filter assembly. The filter assembly may be a part of the optical module 106.

[0093] The optical module 106 may include a display 111 for displaying a result corresponding to the detection of the problematic cellular entity. The display 111 may be a HUD and may display an AR and / or VR. In addition, the display 111 may also display 111 a user Interface (Ul). The Ul may be used by a wearer to select different modes of operations. In an example, the different modes of operation may include a diagnostic mode, a forensic mode, a cosmetic mode, a surface inspection mode, an educational mode, and the like. In the diagnostic mode, the wearable device 100 may activate the UV and IR-light sources, may process the images corresponding to the captured images to identify presence of problematic cellular entity, such as bacteria / fungi or tissue oxygenation.

[0094] In the forensic mode and the cosmetic Mode, the user can switch illumination to reveal body fluids, pigments, or sub-surface features relevant to investigations or cosmetic assessments. In the surface inspection model, the wearable device 100 may enable extended field-of-view scanning to detect areas of contamination on various surfaces, such as laboratory equipment, sanitation equipment, masks, helmets, and the like. In the Educational mode, the wearable device 100 may demonstrate light transmission properties through different materials or biological samples in a lab or classroom setting. The wearer may be able to select different modes of operation using the display 111.

[0095] Further, the Ul may also provide the options to switch between AR and VR modes. The display 111 may be, for example, a liquid crystal display (LCD) display, a light emitting diode (LED) display, an organic LED (OLED) display, or the like. For the wearable device corresponding to VR eyeglasses, the display 111 may present the result to the wearer. For the wearable device corresponding to AR eyeglasses, the display 111 may present the result while the wearer views the target through the lens.

[0096] In an example, the Ul may include options for the wearer to select between augmented reality rendering and virtual reality rendering. In response to the wearer selecting augmented reality rendering, the processor may render the result overlaid on the field of view of the wearer as viewed through the lens. In response to the wearer selecting virtual reality rendering, the processor may render the composite image on the display

[0097] In the fluorescence mode, the processor may operate the first set of light sources to cause the target to emit fluorescence and the image sensor assembly may capture the first plurality of images corresponding to fluorescence-based images. In the reflectance mode, the processor may operate the second set of light sources and the image sensor assembly may capture a second plurality of images based on light reflected by the target. In the oxygenation mode, the processor may operate the second set of light sources and the image sensor assembly may capture a third plurality of images for identification of oxygenation at a plurality of regions in the target.

[0098] In a transmittance mode, the processor may operate the second set of light sources and the image sensor assembly may capture images based on light transmitted by the target. The processor may operate the light source assembly and the image sensor assembly based on the received inputs from the wearer via the user interface.

[0099] The wearable device 100 may include a control module 120 to control the wearable device 100. The control module 120 may facilitate change the modes of display of the result, changing modes of operation, changing imaging modes (fluorescence, reflectance, oxygenation, transmittance, and the like), control various components corresponding to the wearable device 100,select various options on the Ul, and the like. Since the wearable device 100 is hands-free, the control module 120 may enable the wearer to control the wearable device 100 using voice commands via the audio modules or using gestures via the gesture reading module, without requiring the wearer to use hands to operate the wearable device 100. This may enable the wearer to continue a procedure, such as a surgical procedure, while controlling the wearable device 100. The control module 120 may include one or more audio modules. The one or more audio modules may include, for example, a speaker and a microphone to enable the wearer to provide inputs through voice. The control module 120 may include tactile feedback module, gesture reading module, and the like. The tactile feedback module may enable provision of tactile feedback to the wearer in response to the selection of one or more options on the Ul. The gesture reading module may enable determining the inputs from the wearer based on gestures made by the wearer. The control module 120 may include one or more buttons to enable the wearer to use and manipulate the wearable device 100 easily.

[0100] The processor may operate the light source assembly and the image sensor assembly based on the received inputs from the wearer via the user interface. For instance, when the wearer selects a mode of operation, such as a diagnostic mode, a forensic mode, a cosmetic mode, a surface inspection mode, or an educational mode, the processor may activate corresponding light sources of the light source assembly and configure the image sensor assembly accordingly. Similarly, when the wearer selects an imaging mode, such as a fluorescence mode, a reflectance mode, an oxygenation mode, or a transmittance mode, the processor may operate the light source assembly to emit appropriate wavelengths and configure the image sensor assembly to capture corresponding images.

[0101] Further, in an example, the wearable device 100 may include a connectivity module 116 for connecting the wearable device 100 to remote systems, such as cloud storage platforms, external systems for tele medicine and tele healthcare, and the like. The connectivity module 116 may, for example, include cellular connection, Bluetooth connection, and the like. Thecellular connection may include 4G-based cellular connection or 5G-based cellular connection. Since the wearable device 100 enables transmission of the result to a cloud server, a non-medical professional or medical professional may transmit the image or series of images to a remotely located medical professional for additional consultation prior to treatment using the wearable device 100.

[0102] The wearable may include a processor 112 to facilitate examination of the target 102. The processor 112 may detect and classify the problematic cellular entity. In addition, the processor 112 may render the result corresponding to the detection of the problematic cellular entity, the classification of the problematic cellular entity, and the like. In addition, the processor 112 may enable provision of AR or VR corresponding to the detection of the problematic cellular entity, as will be discussed in detail later. The processor 112 may be implemented as a microprocessor, a microcomputer, a microcontroller, a digital signal processor, a central processing unit, a combination of Central Processing Unit and a Graphics Processing Unit, a state machine, a logic circuitry, and / or any device that can manipulate signals based on operational instructions. Among other capabilities, the processor 112 may fetch and execute computer-readable instructions included in a memory (not shown in Fig. 1) of the wearable device 100.

[0103] In an example, the processor 112 may operate each of the plurality of light sources, analyze images captured by the image sensor, and perform the detection. Further, in an example, the processor 112 may activate the servo motor to rotate the emission filter wheel to position an optical bandpass filter of the plurality of optical bandpass filters positioned between the target 102 and the image sensor. The processor 112 may also control the plurality of tunable filters to filter specific wavelength or wavelength bands.

[0104] The processor 112 may use an analysis model 114 for performing various activities corresponding to the problematic cellular entities, as will be explained later. The analysis model 114 may be, for example, Artificial Intelligence (Al)-based model. The analysis model 114 may, for example, include an Artificial Neural Network model (ANN), a Machine Learning (ML)model or a combination thereof. In an example, the ANN model may include a deep learning model, such as a transformer model, a convolutional neural network (CNN), a generative adversarial network (GAN), an auto-encoder decoder network, a single or multi-modal large language model or a combination thereof. The ML model may be, for example, a support vector machine (SVM) model or a random forest model or a combination thereof. The analysis model 114 may be trained to perform the detection and classification of the problematic cellular entity, as will be explained later. The processor 112 may also enable streaming the rendered visualization corresponding to problematic cellular entities.

[0105] In an example, the analysis model 114 may use a combination of audio and visual inputs for performing the analysis. For example, audio inputs can include a technician-dictated, such as a doctor-dictated, voice notes while looking at the target, such as a wound. The video inputs may include images captured by the image sensor. In this example, the analysis model 114, such as multi-modal Large Language Model (LLM) or a multi-modal vision language model, may take inputs from both the audio inputs and the video inputs to give an accurate analysis. In an example, the LLM can be a Retrieval Augmented Generation (RAG) augmented large language model, knowledge graph augmented model which will use domain information or patient specific information to give accurate diagnosis and recommendations.

[0106] To enable powering of the components of the wearable device 100, such as the optical module 106, the processor 112, the light sources, and the like, the wearable device 100 may include the power module (not shown in Fig. 1).

[0107] In an example, the wearable device 100 may transmit the result to a remote system, such as a cloud server. For instance, the processor 112 may be configured to transmit the result and the composite image of the first image, the three-dimensional image to a remote system, such as a cloud server, and the like. The remote system may be in electronic communication with the device 100.

[0108] In an example, the processor 112 may generate the extended reality environment and render the result corresponding to the detection of the problematic cellular entity using the combination of Central Processing Unit and Graphics Processing Unit.

[0109] Fig. 2 illustrates a method 200 for examining the target, in accordance with an implementation of the present subject matter. The order in which the method blocks are described is not included to be construed as a limitation, and some of the described method blocks can be combined in any order to implement the method 200, or an alternative method. Additionally, some of the individual blocks may be deleted from the method 200 without departing from the scope of the subject matter described herein. The steps of the method 200 may be performed, for example, by the wearable device 100. In particular, the steps of the method 200 may be performed by the processor 112. The components mentioned herein may correspond to the components of the wearable device 100. The target may correspond to the target 102.

[0110] At step 202, the wearable device may receive an input corresponding to the mode of operation. The input may be received from a wearer of the wearable device. The inputs may be provided using the control module. For instance, using the audio commands (voice inputs), gesture inputs, physical buttons, and the like, the wearer may provide the inputs to select the mode of operation. As mentioned earlier, the mode of operation may be a diagnostic mode, a forensic mode, a cosmetic mode, a surface inspection mode, or an educational mode. Hereinafter, the mode of operation will be explained with reference to a diagnostic mode to detect and classify problematic cellular entity corresponding to a wound region on a human body part.

[0111] At step 204, in response to receiving the inputs, one or more light sources of the plurality of light sources may be operated to emit light to illuminate the target. The one or more light sources operated may correspond to the mode of operation and the type of imaging. For instance, for diagnostic mode, for fluorescence-based imaging, one or more UV light sources, one or more IR light sources, and / or one or more NIR light sources may be operated.Similarly, for reflectance-based imaging, three-dimensional imaging, and oxygenation-identification imaging, NIR light sources and / or visible light sources may be operated. In an example, the operation may indicate switching on of the light sources, switching off of the light sources, time for maintaining the light sources switched on or switched off, frequency of switching on / switching off of the light sources, and the like. In another example, in case of pulsed LEDs used as light sources, the operation may include actuation of one or more of the light source drivers of the plurality of light source drivers to regulate the pulsed LEDs to emit pulses of excitation radiation. The one or more light source drivers may be actuated to regulate the pulsed LEDs at shorter pulse widths, faster frequencies that is to enable faster imaging and to reduce ambient light interference in the light emitted by the target. In an example, the pulse width may range from 0.005 ms to 100s of ns. In an example, the frequency of the pulsed LEDs may be from 100 Hz to tens of MHz. Therefore, the present subject matter enables faster capturing of the first plurality of images and the three-dimensional images and reduces ambient light interference (background interference).

[0112] The emitting of the light by the one or more of the first set of light sources of the plurality of light sources may cause the target to fluoresce. The emitting of the light by the one or more of the second set of light sources of the plurality of light sources may not cause the target to fluoresce.

[0113] At step 206, the image sensor may be actuated. At step 208, one or more images may be captured based on the light received from the target in response to the illumination thereof. In other words, the one or more images may be formed based on the light emitted by the target (in case of fluorescencebased imaging), the light received (in case of white light imaging, three-dimensional imaging, oxygenation imaging), the light transmitted (in case of transmittance-based imaging), thermal imaging (in case of thermal imaging) as will be explained below.

[0114] In an example, the image sensor may capture the first plurality of images formed based on the light emitted by the target. If the target includes a marker that fluoresces, the captured image includes fluorescence. Accordingly,the first plurality of images will be referred to as fluorescence-based images. Therefore, the fluorescence-based images may include fluorescence emerging from the target. The one or more markers may be part of the problematic cellular entity. The fluorescence emitted by the marker that is part of the problematic cellular entity may be referred to as autofluorescence. In an example, an exogenous marker, such as a synthetic marker, may be sprayed on the target to cause detection of the problematic cellular entity in the target 102. The exogenous marker may bind to cellular entities, such as deoxyribonucleic acid (DNA), Ribonucleic acid (RNA), proteins, biochemical markers, and the like, which may cause the target 102 to fluoresce. The fluorescence emitted by the added synthetic marker may also be referred to as exogenous fluorescence.

[0115] In another example, the image sensor may capture a second plurality of images formed based on the light reflected by the target. In a yet another example, the image sensor may capture the third plurality of images formed based on the light reflected by the target. In a further example, the image sensor may capture the fourth plurality of images based on the light reflected by the target. The second plurality of images, the third plurality of images, and the fourth plurality of images may not include fluorescence. Further, in an example, the image sensor may capture one or more images that are transmitted by the target for the analysis and the detection of the problematic cellular entities. Furthermore, the image sensor may capture a plurality of thermal images of the target for the analysis and the detection of the problematic cellular entities.

[0116] In an example, the image sensor may directly receive the light from the target in response to illumination of the target by the light sources. In other words, an optical bandpass filter may not be disposed between the image sensor and the target. Here, the light is said to be directly received by the image sensor because the light emitted is not filtered by an optical bandpass filter before capturing the image. In another example, the image sensor may receive the light from the target through one or more emission filters. In scenarios where the image sensor receives the light from the target through one or moretunable emission filters, the processor may actuate the appropriate tunable filters for filtering the predetermined wavelength or wavelength bands of light received from the target.

[0117] At step 210, the captured one or more images may be analyzed using an analysis model. The analysis model may correspond to the analysis model 114 explained with reference to Fig. 1. The analysis by the analysis model may include analyzing the fluorescence in the fluorescence-based image, such as the wavelengths of fluorescence. In an example, in addition to or instead of the analysis of the fluorescence-based images, one or more images of the second plurality of images may be analyzed. The second plurality of images may correspond to the white light images. In yet another example, one or more images of the third plurality of images may be analyzed using the analysis model. The analysis of the image of the third plurality of images may include identification of oxygenation at a plurality of regions in the target. In yet further example, the processor may include analyzing the image of the fourth plurality of images using the analysis model. The fourth plurality of images may correspond to three-dimensional images. In another example, the one or more images that are transmitted by the target may be analyzed using the analysis model. In some examples, an image of the plurality of thermal images corresponding to the target may be analyzed.

[0118] At step 212, presence of problematic cellular entities may be detected using the analysis model. For instance, the presence of a problematic cellular entity in the target may be detected based on the analysis of the fluorescence-based image using the analysis model. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained. For instance, the analysis model may be trained using a plurality of reference fluorescence-based images for detecting the presence of problematic cellular entities in targets. The analysis model may be trained to differentiate between fluorescence in the fluorescence-based image emerging from the problematic cellular entity and fluorescence in the fluorescence-based image emerging from regions other than the problematic cellular entity. The analysis model may be trained to differentiate between fluorescence in thefluorescence-based image emerging from the problematic cellular entity and fluorescence in the fluorescence-based image emerging from regions other than the problematic cellular entity. For example, the analysis model may differentiate between fluorescence emerging from a wound region having a pathogen and fluorescence emerging from a skin surrounding the wound region.

[0119] In another example, presence of a problematic cellular entity in the target may be detected based on the analysis of the fluorescence-based image and based on the image of the second plurality of images using the analysis model. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained using a plurality of reference fluorescence-based images and a plurality of reference white light images.

[0120] In a yet another example, presence of a problematic cellular entity in the target may be detected based on the analysis of the fluorescence-based image and based on the identified oxygenation. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained using a plurality of reference fluorescence-based images and a plurality of reference oxygenation-based images.

[0121] In a yet another example, presence of a problematic cellular entity in the target may be detected based on the analysis of the fluorescence-based image and based on the analysis of the three-dimensional image. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained using a plurality of reference fluorescence-based images and a plurality of reference three-dimensional images.

[0122] In another example, presence of a problematic cellular entity in the target may be detected based on the analysis of the fluorescence-based image and based on the analysis of a thermal image of the plurality of thermal images of the target. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained using a plurality of reference fluorescence-based images and a plurality of reference thermal images.

[0123] In a yet further example, presence of problematic cellular entity in the target based on the analysis of the fluorescence-based image, based onthe analysis of the image of the second plurality of images, based on the identified oxygenation at the plurality of regions in the target, based on the analysis of the three-dimensional image of the target, based on the analysis of the thermal image of a plurality of thermal images of the target, or any combinations thereof. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained using a plurality of reference fluorescence-based images, the plurality of reference white-light images, the plurality of reference three-dimensional images, the plurality of reference oxygenation-based images, a plurality of reference thermal images, or any combinations thereof.

[0124] The processor may detect presence of a problematic cellular entity in the target based on the analysis of the one or more transmittance-based images. In this regard, for the detection of the presence of the problematic cellular entities, the analysis model may be trained using a plurality of reference transmittance-based images. In an example, in addition to detection of the problematic cellular entity, the detected problematic cellular entity may be classified. Accordingly, in an example, when the target 102 is a wound region, spatial and spectral features of the wound region may be extracted from the captured images using the analysis model. Further, the location of the wound region may be determined based on the extraction of the spatial and the spectral features by using the analysis model.

[0125] Further, contour of the wound region may be determined based on the extraction of the spatial and the spectral features by using the analysis model. In an example, based on the determination of the contour of the wound region, parameters, such as a length of the wound region, a width of the wound, a perimeter of the wound, an area of the wound, a depth of the wound, or a combination thereof, degree of infection of a wound region, spatial distribution of pathogens in a wound region, a healing rate of the wound region, or a combination thereof, may be determined. Pathogen in the wound region may be determined based on the extraction of the spatial and the spectral features by using the analysis model. The pathogen may be classified by at least oneof: family, genus, species, or strain of the pathogen by using the analysis model.

[0126] Further, in an example, in addition to the detection of the problematic cellular entities, time-dependent changes in fluorescence emerging from the target may be determined. In other words, changes from fluorescence between a first imaging of the target relative to a subsequent imaging of the target may be determined. In an example, changes in fluorescence between pre-debridement of a wound and post-debridement of the wound may be determined. The detection may enable to accurately remove the dead / unhealthy tissue from the wound. In another example, changes in fluorescence between an image of the wound taken on a first time (such as first day) and an image of the wound taken on a subsequent time (such as a second day) may be determined. The detection may help in identifying the wound status on a periodic basis.

[0127] In an example, for the detection and the classification, inputs from the three-dimensional image sensor and / or the ranging sensor may be used. For instance, using the inputs from the three-dimensional image sensor and / or ranging sensor, distance of the target relative to the wearable device and / or distance of the target relative to the three-dimensional image sensor (or the ranging sensor) may be detected. During the analysis of the images (as explained with reference to the step 210), the detected distance may be used to compensate for variation in the distance. In other words, during the processing of the images, the detected distance may be used to compensate for the variation in the distance of the target relative to the wearable device (or the three-dimensional image sensor or the ranging sensor). The detected distance is factored in by the analysis model. The factoring of the detected distance may enable dynamic adjustments, such as scaling, focus correction, intensity normalization, thresholding, and other processing steps corresponding to the images obtained. This may ensure consistent performance in the detection and the classification of the problematic cellular entities regardless of variations in position of the wearer of the wearable device. The technique also ensures that the analysis model accurately detects andclassifies the problematic cellular entities by accounting for spatial variations introduced by proximity of the wearer of the wearable device to the target.

[0128] At step 214, result corresponding to the detection of the problematic cellular entities may be rendered on the display of the wearable device. The result may be viewable by the wearer. The result may be rendered in the form of AR or VR. The result may include composite image of the fluorescence-based image from the plurality of fluorescence-based images, the image from the second plurality of images, the image from the third plurality of images, the image from the fourth plurality of images, the image from the plurality of thermal images, the image from the plurality of transmittance-based images, or any combination thereof. The result may be displayed as a part of the Ul, which may include options to receive inputs from the user to select various options corresponding to the mode of operations, imaging modes, and the like.

[0129] At step 216, the rendered result may be stored in the wearable device, such as in the memory of the wearable device, or in a storage device, such as a Universal Service Bus USB-based storage device, or at a remote storage location, such as a cloud storage platform. In addition, the result corresponding to the detection and classification of pathogens in the target upon the detection and the classification of the pathogen may be transmitted to the external system. In addition, or instead of storing the rendered result, the rendered result may be live streamed (streaming in real-time as the rendering of the result) to an external system using the connectivity module. For instance, the AR and / or VR visualization corresponding to the detection of the problematic cellular entities may be live streamed to an external system for visualizing using the display of the external system. In an example, the rendered result may also be transmitted to a stand-alone display for displaying the result thereof. The storing, the live streaming, the transmitting, the visualization, and the like may be performed in response to receipt of inputs from the wearer. The options to receive the inputs may be provided on the Ul.

[0130] At step 218, one or more alerts may be triggered regarding the result. The triggering of the alerts may be displayed on the display or may bein the form of audio alerts. The alerts may, for example, be provided if the degree of intensity of the problematic cellular entity exceeding a threshold degree, parameters corresponding to the detected problematic cellular entity is outside a nominal range of parameters, and the like. In another example, the alert may include information, such as information on low oxygen saturation at certain locations, and the like.

[0131] In the above examples, the result corresponding to the problematic cellular entities are explained as being visualized in the display. However, in some examples, the wearable device may be used to directly view the target through the lens, as will be explained below.

[0132] Fig. 3 illustrates a method 300 for examining the target, in accordance with an implementation of the present subject matter. The order in which the method blocks are described is not included to be construed as a limitation, and some of the method blocks described can be combined in any order to implement the method 300, or an alternative method. Additionally, some of the individual blocks may be deleted from the method 300 without departing from the scope of the subject matter described herein. The target may correspond to the target 102. The steps of the method 300 may be performed by the wearable device, such as the wearable device 100. In particular, the steps of the method 300 may be performed by a processing unit, such as the processor 112. As will be understood, the components referred to in the method 300 may correspond to the components of the wearable device 100 unless specified otherwise.

[0133] At step 302, the one or more of the plurality of light sources may be operated to emit the light to illuminate the target. The step 302 may be same as the step 204 of Fig. 2.

[0134] At step 304, the image sensor may be actuated in response to the operation of the one or more of the plurality of light source. In another example, the image sensor may be actuated simultaneously when the one or more light sources of the plurality of light sources are operated. The step 304 may be same as the step 206 of Fig. 2.

[0135] At step 306, one or more emission filters may be operated to allow one or more predetermined wavelength or wavelength bands. In an example, the emission filters may be tunable emission filters that may be tuned by the processor to allow predetermined wavelength or wavelength bands of the light to pass through. At step 308, instead of rendering result on the display, the wearable device may facilitate viewing of the target through the lens to identify the problematic cellular entity or the absence of the problematic cellular entity in the target. In other words, the wearer may be able to view the target through the lens and may be able to identify the problematic cellular entity in the target directly without needing to visualize through the display.

[0136] In the above examples, the wearable device is explained to include the display for rendering the result corresponding to the detection of the problematic cellular entity. However, in other examples, in addition to the display, the wearable device may include a projection element, as will be explained below.

[0137] Fig. 4 illustrates a wearable device 400 for examining a target, in accordance with an implementation of the present subject matter. The wearable device 400 may correspond to the wearable device 100. However, in addition to the components of the wearable device 100, the wearable device 400 may include a projection element 402. Therefore, for the sake of brevity, the components of the wearable device 400 that are same as that of the wearable device 100 are not explained here.

[0138] The projection element 402 may be part of the optical module 106. The projection element 402 may include micro-projectors that may be coupled with lens, grating, scanning LASERS, or a combination thereof. The projection element 402 may enable rendering the result corresponding to the detection of the problematic cellular entities onto the eyes of the wearer. The result may include composite image of the fluorescence-based image from the plurality of fluorescence-based images, the image from the second plurality of images, the image from the third plurality of images, the image from the fourth plurality of images, the image from the plurality of thermal images, the image from the plurality of transmittance-based images, or any combination thereof. In anexample, the Ul may be projected onto the eyes of the user. The Ul may include options to receive inputs from the user to select various options corresponding to the mode of operations, imaging modes, and the like. The result may be displayed as a part of the Ul. The result may also include one or more treatments options, such as treatment options to cure the target of the problematic cellular entities.

[0139] Since the wearable device 400 includes both the display 111 and the projection element 402, the wearer of the wearable device 400 may be able to choose to render on the display 111 or to project onto the eyes. The options to choose between the rendering and the projection may be performed by the user using the control module 120, such as using voice commands, input gestures, buttons, or the like.

[0140] Fig. 5 illustrates a method 500 for examining a target, in accordance with an implementation of the present subject matter. The order in which the method blocks are described is not included to be construed as a limitation, and some of the described method blocks can be combined in any order to implement the method 500, or an alternative method. Additionally, some of the individual blocks may be deleted from the method 500 without departing from the scope of the subject matter described herein. The target may correspond to the target 102. The steps of the method 500 may be performed by the wearable device, such as the wearable device 400. In particular, the steps of the method 500 may be performed by a processing unit, such as the processor 112. As will be understood, the components referred to in the method 500 may correspond to the components of the wearable device 400 unless specified otherwise.

[0141] The steps of the method 500, such as step 502, step 504, step 506, step 508, step 510, step 512, step 516, and step 518 may correspond to the steps of the steps of the method 200, such as the step 202, step 204, step 206, step 208, step 210, step 512, step 216, and step 218 respectively. For the sake of brevity, the same steps are not explained here. As will be understood, while the steps of the method 200 are performed by the wearable device 100, the steps of the method 500 are performed by the wearable device 400.

[0142] At step 514, in response to the detection of the presence of the problematic cellular entities, the result corresponding to the detection of the problematic cellular entities may be projected onto the eyes of the user (the wearer of the wearable device). The result may be projected in the form of AR or VR. The result may include composite image of the fluorescence-based image from the plurality of fluorescence-based images, the image from the second plurality of images, the image from the third plurality of images, the image from the fourth plurality of images, the image from the plurality of thermal images, the image from the plurality of transmittance-based images, or any combination thereof. In an example, the projection may be performed using the projection element, such as the projection element 402. The projection element 402 may be operated by the processor, such as the processor 112, to cause the projection.

[0143] In an example, for virtual reality rendering, the projection element 402 may project the composite image comprising the fluorescence-based image and the result onto the eyes of the wearer. For augmented reality rendering, the projection element 402 may project the result onto the lens such that the result is overlaid on the target as viewed by the wearer through the lens.

[0144] In the above example, the method 500 is explained to project the result onto the eyes of the wearer. Accordingly, the method 500 may include receiving inputs from the wearer to project eyes onto the eyes of the wearer prior to projecting the result. However, in another example, the method 500 may include receiving inputs from the wearer to render the result on the display. The rendering of the result on the display may be similar to the step 214 of Fig.2. Prior to receiving the inputs, the method 500 may provide options to the wearer on the Ul to choose between the projection onto the eyes mode or rendering on the display mode and receive inputs based on the selection of the wearer.

[0145] Although in the above examples explained with reference to Fig. 4 and Fig. 5, the wearable device 400 is explained to include the display 111 as well as the projection element 402, in other examples, the wearable device 400may include only the projection element 402 and may not include the display 111.

[0146] As explained earlier, the analysis model used by the wearable device 100 and the wearable device 400 may be trained using a plurality of reference images. The training of the analysis model will be explained with reference to Fig. 6.

[0147] Fig. 6 illustrates a method 600 for training of an analysis model, in accordance with an implementation of the present subject matter. The order in which the method blocks are described is not included to be construed as a limitation, and some of the described method blocks can be combined in any order to implement the method 600, or an alternative method. Additionally, some of the individual blocks may be deleted from the method 600 without departing from the scope of the subject matter described herein. Herein, the target is explained with reference to wound and the problematic cellular entity will be explained with reference to pathogens. However, it will be understood that the target can be a tissue sample, an edible product, a laboratory equipment, a sanitary device, a sanitary equipment, a biochemical assay chip, a microfluidic chip, a medical equipment, a body fluid, or a combination thereof and the problematic cellular entities can be cancerous tissue, necrotic tissue, and the like. The analysis model may correspond to the analysis model 114.

[0148] At step 602, a plurality of reference fluorescence-based images and / or a plurality of reference white light images and / or a plurality of reference three-dimensional images and / or a plurality of oxygenation-based images and / or a plurality of reference thermal images are tagged with various reference labels. In an example, a plurality of transmittance-based images may also be tagged with various reference labels. The reference labels may include a type of the target (i.e., skin or wound), type of wound region (i.e., slough, bone, and the like), infected pathogen species, gram type, strain, and the like.

[0149] In an example, a plurality of reference thermal images may also be tagged with various reference labels for training the analysis model. The reference thermal images may be used in combination with the reference fluorescence-based images, reference white light images, referenceoxygenation-based images, reference three-dimensional images, and reference transmittance-based images fortraining the analysis model to detect presence of problematic cellular entities based on thermal characteristics of the target. The reference labels may further include a strain of the problematic cellular entity. The strain information may enable the analysis model to distinguish between different strains of the same species of problematic cellular entity, thereby enabling more precise detection and classification.

[0150] At step 604, the tagged images may be pre-processed. In an example, the pre-processing may include converted the images into grayscale, resizing the images, and augmenting the images. Augmenting the images may include rotating the images, flipping the images, and the like.

[0151] At step 606, various features, such as spatial features, spectral features, or a combination thereof may be extracted from the images. In some examples, the spatial features, such as histogram of oriented gradient (HOG) features, Entropy features, Local Binary Patterns (LBP), Scale Invariant Feature Transforms (SIFT), and the like may be extracted from the images. Similarly, in some examples, spectral features may be extracted from the white light images at RGB wavelengths and fluorescence images at various excitation wavelengths. For white light image and the fluorescence image, the spectral features are extracted using Red green blue (RGB), Hue saturation value (HSV) values or any other color map values at each pixel / region. In an example, a machine learning model or a deep learning model can be used to extract the spatial and spectral features. In an example, the features extracted from the images (for example, from the oxygenation-based images) may include Deoxygenated hemoglobin of the target, Oxygenated hemoglobin of the target, Oxygen saturation of the target, depth profile of the target of the target, and the like.

[0152] At step 608, the extracted spatial and spectral features and the tags may be stored in a database in the memory, such as the memory of the wearable device, or a cloud storage platform. The extracted features may be then passed onto the analysis model for detection and spatial mapping of pathogens, as will be described below. For instance, for some pathogens, suchas Pseudomonas Aeruginosa, with the use of spatial features and the excitation wavelength, the pathogens can be detected. For some pathogens, such as Escherichia coli (E-coli), Klebsiella, Staphylococcus, and the like, the detection may be done by extracting a combination of both spatial features and spectral features.

[0153] The steps 602-608 may be repeated for several reference fluorescence-based images, several reference white light images, several reference oxygenation-based images, several reference three-dimensional images, and / or several reference transmittance-based images till the targeted pre-determined target training accuracy is achieved. At step 610, the information in the database may be used for training the analysis model.

[0154] By virtue of the training using the plurality of reference images, the analysis model becomes capable of detecting presence of problematic cellular entities in targets. The analysis model trained using a plurality of reference fluorescence-based images may detect presence of problematic cellular entities in targets based on analysis of fluorescence-based images captured by the image sensor assembly. Similarly, the analysis model trained using a plurality of reference fluorescence-based images and a plurality of reference white light images may detect presence of problematic cellular entities in targets based on analysis of both fluorescence-based images and white light images. The analysis model trained using a plurality of reference fluorescencebased images and a plurality of reference oxygenation-based images may detect presence of problematic cellular entities in targets based on the determined tissue oxygenation. The analysis model trained using a plurality of reference fluorescence-based images and a plurality of reference three-dimensional images may detect presence of problematic cellular entities in targets based on analysis of both fluorescence-based images and three-dimensional images. The analysis model trained using a plurality of reference fluorescence-based images and a plurality of reference transmittance-based images may detect presence of problematic cellular entities in targets based on analysis of both fluorescence-based images and transmittance-based images.

[0155] By virtue of the training, the analysis model becomes capable of identifying a wound in a given image based on the extracted spatial features, spectral features, or a combination thereof, of the image. In other words, the analysis model is capable of performing wound segmentation. In an example, subsequent to the step 610, the method 600 may include a post-processing step, such as connected component labelling, hidden Markov models, and the like, which may be used to smoothen the result of the wound segmentation and thereby improve the accuracy of wound segmentation. As will be understood, the training may be performed for various architectures and hyperparameter configurations. The hyperparameters may correspond to configuration variables that define how the analysis model learns and may control aspects, such as learning rate, number of hidden layers, model complexity, regularization strength, and the like.

[0156] Further, at step 612, the trained analysis model may be optimized to ensure relatively lesser power consumption, lesser resources, and lesser latency. For the optimization, the trained analysis model (trained using various architectures and hyperparameter configurations) may be evaluated for their performance on accuracy, latency, and resource usage. Based on the evaluation, optimized parameters corresponding to the analysis model may be chosen while also ensuring efficiency and performance. In an example, the analysis model, such as U-Net, automated Machine Learning (autoML), or a combination thereof, may be selected due to accuracy and compatibility with edge hardware. For the optimization, analysis model may undergo steps, such as decreasing the precision of the data (for example, use of floating point 16 instead of floating point 32), quantization, Pruning weights of layers of the analysis model, removing certain layers, knowledge distillation, compression of the analysis model, operator fusion, memory optimization, and the like, to minimize computation requirements and memory requirements. In an example, the optimized analysis model may be tailored to a specific edge hardware (processing units), such as Graphical Processing unit (GPU), Tensor Processing Unit (TPU), Digital Signal processor (DSP), or the like. In an example, the tailoring to the specific edge hardware may be, for example,performed using frameworks, such as TensorFlow Lite for deployment. Such tailoring of the analysis model to the specific edge hardware may ensure efficient real-time processing on the edge hardware.

[0157] Upon training of the analysis model, the analysis model may be tested to verify whether it is able to correctly identify wounds in images. Accordingly, at step 614, a test image may be received and may be pre-processed. The pre-processing may be similar to the pre-processing as explained with reference to the 604. Further, a region of interest in a test image is selected. In an example, region of interest can be selected automatically, such as by the analysis model. In another example, region of interest can be selected manually, such as by the wearer.

[0158] At step 616, spatial features of test images are extracted. At step 618, the extracted features are fed to the analysis model to perform the wound segmentation and problematic cellular entity detection and classification. Subsequently, the result of the wound segmentation, problematic cellular entity detection and classification as performed by the analysis model, may be received.

[0159] The analysis model used for the wound segmentation may be different than that used for the pathogen detection and classification. Accordingly, the output of the wound segmentation may be provided by a first analysis model to a second analysis model. The second analysis model may then analyze the fluorescence from the wound region as identified by the first analysis model and then detect and classify the pathogens in the wound region. Alternatively, in an example, the second analysis model may also use the spatial features, information from the first analysis model on wound, bone, tissue region, and the like, in combination with the spectral features for detection and classification of pathogens.

[0160] In an example, the analysis model may include an ANN model and an ML model, each performing a different function. For example, the ML model may be trained to perform wound segmentation, while the ANN model may be trained to detect and classify pathogens. In another example, the ANN model may generate the spectral images from the fluorescence-based image, and theML model may detect and classify pathogens based on the generated spectral images. In an example, in addition to the fluorescence-based image, the ANN model may also generate the spectral image additionally from the white light image, and the ML model.

[0161] In an example, the analysis model may comprise a convolutional neural network (CNN) for extracting spatial features from the images and detecting patterns associated with problematic cellular entities. In another example, the analysis model may comprise a support vector machine (SVM) model for classifying the problematic cellular entities based on the extracted spatial and spectral features. The CNN may be trained using the plurality of reference images to learn hierarchical representations of the problematic cellular entities. The SVM model may be trained using the extracted features to classify the problematic cellular entities by family, genus, species, gram type, or strain.

[0162] In an example, the analysis model may classify the pathogens in a wound into gram positive (GP) and gram negative (GN) pathogens. Further, the analysis model may identify the species of the pathogens in the wound. Further, the analysis model may identify the presence of biofilm in the wound.

[0163] In the above example, the optimization is explained to be performed prior to receiving the test image. However, in other examples, the optimization may be performed after the step 618.

[0164] Fig. 7 illustrates a wearable device 700 for examining the target, in accordance with an implementation of the present subject matter. The wearable device 700 may correspond to the wearable device 100. However, instead of the light source assembly being integrated in the wearable device 700, the light source assembly 702 may be provided separately outside the wearable device 700. In an example, the light source assembly 702 may correspond to the light source assembly 104 and may include same components as the light source assembly 104. For the sake of brevity, the light source assembly 702 is not explained here.

[0165] In an example, the wearable device 700 may also include a projection element, such as the projection element 402, in addition to thedisplay. Accordingly, the wearable device 700 may also correspond to the wearable device 400.

[0166] Fig. 8 illustrates a wearable device 800 connected to a processor 802, in accordance with an implementation of the present subject matter. The wearable device 800 may correspond to the wearable device 100 or the wearable device 400 but may not include a built-in processor, such as the processor 112. Instead, the wearable device 800 may be coupled to an external processor, such as the processor 802. The processor 802 may be a computing device, such as a server, provided at a remote location, such as on the cloud. The processor 802 may include computer(s), servers(s), cloud device(s) or any combination thereof. The wearable device 100 may be connected to the processor 802 over a communication network 801. An analysis model 814 may be provided on the processor 802. The analysis model 814 may correspond to the analysis model explained with reference to Figs. 1-7 (the analysis model 114). The processor 802 may implement the analysis model 814. The processor 802 may correspond to the processor 112. Accordingly, the wearable device 100 may capture the images of the target and may transmit them to the processor 802. The processor 802 may process the images using the analysis model 814, as explained with reference to Fig. 2. As will be understood, the analysis model 814 may correspond to cloud-based Al model. Subsequently, the processor 802 may transmit the result of the analysis to the wearable device 100, which may then display the result on the display 111. The training of the analysis model 814 may be similar to the training explained with reference to Fig. 6.

[0167] While in the above example, it is explained that the wearable device 100 may not include the processor, in another example, the wearable device 100 may include a built-in processor. However, the built-in processor may not perform all the functions performed by the processor 112 rather may only perform some functions performed by the processor 112 and the other functions may be performed by the processor 802.

[0168] Fig. 9 illustrates a wearable device 900 connected to a clip-on assembly 902, in accordance with an implementation of the present subjectmatter. The wearable device 900 may correspond to the wearable device 100 or the wearable device 400. However, the wearable device 900 may be a prescription glass and may have the lens 108 for viewing of the objects. The clip-on assembly 902 may include the other components, such as processor 112, the control module 120, the connectivity module 116, the light source assembly 104, and the optical module 106 having the image sensor assembly 110 and the display 111. The clip-on assembly 902 may be coupled to the wearable device 900 to perform the functions analogous to the wearable device 100 or the wearable device 400. As will be understood, the training of the analysis model may be similar to the training explained with reference to Fig.6.

[0169] In an example, the clip-on assembly may be provided as an independent unit for attachment to various wearable devices. The clip-on assembly may comprise a processor; a light source assembly operably coupled to the processor, the light source assembly comprising a first set of light sources to emit excitation radiation at a predetermined range of wavelengths to illuminate the target and cause the target to emit fluorescence; and an image sensor assembly operably coupled to the processor, wherein the image sensor assembly is to capture a first plurality of images of the target in response to illumination thereof by the light source assembly, the first plurality of images corresponding to fluorescence-based images of the target. The processor of the clip-on assembly may receive the first plurality of images captured by the image sensor assembly; analyze, using an analysis model, the first plurality of images to detect presence of a problematic cellular entity on the target; generate a virtual environment for viewing by a wearer of the wearable device; and render a result corresponding to the detection of the problematic cellular entity on the target on the virtual environment.

[0170] Fig. 10 illustrates a wearable device 1000 for examining a target, in accordance with an implementation of the present subject matter. The wearable device 1000 may correspond to eyeglasses. In particular, the wearable device 1000 may correspond to VR eyeglasses. In other words, a display of the wearable device 1000 may display VR. The wearable device1000 may correspond to the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900. Accordingly, the components of the wearable device 1000 may be, for example, the corresponding components explained with reference to the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900. Here, some of the components of the wearable device 1000 are depicted. For instance, the wearable device 1000 may include one or more light sources 1002, an image sensor 1004, a three-dimensional sensor 1006, one or more emission filters 1008. In another example, the wearable device 1000 may include a ranging sensor instead of the three-dimensional sensor or in addition to the three-dimensional sensor. Further, the one or more emissions filters 1008 may include one or more polarizers. In another example, the one or more emissions filters 1008 may not include one or more polarizers. In addition, the wearable device 1000 may have a headband 1010 to enable wearing of the wearable device 1000 by a user and a frame 1012 to support all the components of the wearable device 1000. The above-mentioned components of the wearable device 1000 may be same as the corresponding components of the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900.

[0171] As will be understood, in an example, the wearable device 1000 may include some or all the components, as was explained with reference to the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900. Further, the functions of the wearable device 1000 may be same as the functions of the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900. Yet further, the functions of each component of the wearable device 1000 (both depicted here and not depicted here) may be same as the functions of the corresponding component of the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900. Accordingly, the wearable device 1000 may perform the method 200, the method 300, the method 500, and the method 600. For the sake of brevity, the same has not been explained here.

[0172] Although in the view depicted herein, the light source is explained to be part of the wearable device 1000, in an example, the light source may be provided outside the wearable device 1000. In such a scenario, the wearable device 1000 may be same as the wearable device 700 and may have same functions and components as the wearable device 700.

[0173] Fig. 11 illustrates a wearable device 1100 for examining a target, in accordance with an implementation of the present subject matter. The wearable device 1100 may correspond to eyeglasses. In particular, the wearable device 1100 may correspond to AR eyeglasses. In other words, a display of the wearable device 1100 may display AR. The wearable device 1100 may correspond to the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900.

[0174] Accordingly, the components of the wearable device 1100 may be, for example, the corresponding components explained with reference to the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900. Here, some of the components of the wearable device 1100 are depicted. For instance, the wearable device 1100 may include one or more light sources 1102, an image sensor 1104, a three-dimensional sensor 1106, one or more emission filters 1108. In another example, the wearable device 1100 may include a ranging sensor instead of the three-dimensional sensor or in addition to the three-dimensional sensor. Further, the one or more emissions filters 1108 may include one or more polarizers. I n another example, the one or more emissions filters 1108 may not include one or more polarizers. In addition, the wearable device 1100 may have one or more arms 1110 to enable wearing of the wearable device 1100 by a user and a frame 1112 to support all the components of the wearable device 1100.

[0175] In an example, the lens of the wearable device 1100 may itself function as an AR display when coupled with a suitable projection system, similar to conventional AR glasses. In such scenarios, the projection system may project images, results, or other visual information directly onto the lens, enabling the wearer to view augmented reality content overlaid on the real-world view through the lens.

[0176] As will be understood, the wearable device 1100 may include some or all the components, as was explained with reference to the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900. Further, the functions of the wearable device 1100 may be same as the functions of the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900. Yet further, the functions of each component of the wearable device 1100 (both depicted here and not depicted here) may be same as the functions of the corresponding component of the wearable device 100, the wearable device 400, the wearable device 800, or the wearable device 900. Accordingly, the wearable device 1100 may perform the method 200, the method 300, the method 500, and the method 600. For the sake of brevity, the same has not been explained here.

[0177] Although in the view depicted herein, the light source is explained to be part of the wearable device 1100, in an example, the light source may be provided outside the wearable device 1100. In such a scenario, the wearable device 1100 may be same as the wearable device 700 and may have same functions and components as the wearable device 700.

[0178] The present subject matter enables detection of problematic cellular entities using a wearable device. Since the analysis model used for detection of the problematic cellular entities is optimized, the present subject matter ensures relatively lesser power consumption in comparison with the conventional imaging devices. Since the wearable device enables transmission of data to external systems, the present subject matter may be provided with a non-medical professional or medical professional may transmit an image, a set of images, one or more videos to remotely located systems. Therefore, with the present subject matter, live-streaming or recorded images or videos of surgeries may be transmitted to the external systems. Accordingly, the present subject matter can be used in applications of education (such as for lab experiments), telemedicine, and the like. The present subject matter can also be used, for example, by a medical professional for additional consultation prior to treatment using the device(s) of the present disclosure. In addition, the present subject matter can also be used, for example, by a surgeon for trainingunderstudy, for consultation with another experienced surgeons, and the like, for performing surgeries.

[0179] The present subject matter provides a rapid, optionally filter-less, non-invasive, automatic, and in-situ detection and classification of pathogens using an “opto-computational biopsy” technique. The opto-computational biopsy technique is a technique in which multispectral imaging is used along with the computational models, such as machine learning models, Artificial Neural Network (ANN) models, deep learning models, and the like, for non-invasive biopsy to detect the problematic cellular entities by using a wearable device.

[0180] The present subject matter can be used for detecting the presence of problematic cellular entities in diabetic foot ulcers, surgical site infections, bums, skin, and interior of the body, such as esophagus, stomach, and colon. The device of the present subject matter can be used in the fields of dermatology, cosmetology, plastic surgery, infection management, photodynamic therapy monitoring, and anti-microbial susceptibility testing.

[0181] Further, the device may be used to detect the time-dependent changes in the fluorescence to understand colonization of pathogens and necrotic tissue. In other words, the wearable device may be configured to detect changes from fluorescence between a first imaging of the target relative to a subsequent imaging of the target. For instance, the wearable device may be configured to detect changes in fluorescence between pre-debridement of a wound and post-debridement of the wound and may render the result corresponding to the changes. The detection may enable to accurately remove the dead / unhealthy tissue from the wound. In another example, the wearable device may be configured to detect changes in fluorescence between an image of the wound taken on a first day and an image of the wound taken on a subsequent day. The detection may help in ascertaining healing of the wound and allow a medical practitioner to administer medications according to the detection.

[0182] With the present subject matter, most of the clinically relevant pathogens may be detected and classified in a few minutes. This feature helpsin quickly deciding the treatment protocol corresponding to the detected problematic cellular entity. Further, data acquisition and analysis may happen automatically. Therefore, the device can be worn by anyone and operated without requiring skillful technicians. The device may also be used for detection and classification of pathogens in resource scarce settings.

[0183] The wearable device of the present subject matter may be used for quantification of various pathogens present in the sample. The wearable device may also be used for identifying problematic cellular entities, such as infections, measuring skin perfusion, tissue oxygenation, oxyhemoglobin, and the like. The wearable device may be used for monitoring status of the wound. The device may also be used to study wound parameters, such as wound size, wound depth, wound temperature distribution, tissue classification, biofilm information, and degree of contamination.

[0184] The present subject matter may have different diagnostic modes, such as diagnostic mode, forensic mode, cosmetic mode, surface inspection mode, and education mode for usage in various applications. The wearable device of the present subject matter can be used in applications corresponding to monitoring of surface contamination, such contamination of edible objects, contamination of objects that are to be sterile, such as surgical blade, lab equipment, and the like. The wearable device may reveal contaminated regions that fluoresce under illumination of the light sources, such as UV light source and / or IR light source, based on the analysis of images of the surface captured under the illumination by the light sources. The wearable device may also quantify the contamination on various surfaces. Accordingly, the present enables guiding thorough cleaning of surfaces, disinfection of surfaces, and to adhere to sterilization protocols. For instance, the wearable device may facilitate studying effectiveness of disinfectants on various hospital surfaces such as beds, walls, hands, gloves, bandages, dressings, catheters, endoscopes, hospital equipment, sanitary devices, and the like.

[0185] The wearable device of the present subject matter may be used in cosmetology applications. For instance, the wearable device of the present subject matter may be used to visualize subdermal features, such as bloodflow, pigment distribution, and the like, evaluating vascular flow for cosmetic treatments and skincare routines. For example, the wearable device may be used to detect the presence of Propionibacterium which causes acnes. For the visualization of the subdermal features and evaluation of vascular flow, the wearable device may facilitate illumination of skin by different light sources and may analyze the images captured in response to the illumination of the skin. The visualization of the subdermal features may enable planning and evaluation of treatments. The treatments may include debridement, dressings, topical medicines, antibiotics, hyperbaric oxygen therapy, vacuum assisted closure, Negative wound pressure therapy, and the like. The device may also be used during tissue grafting to ensure that the tissue is free of pathogens.

[0186] The wearable device of the present subject matter may be used in forensic investigations. The wearable device may detect bodily fluids, such as blood, mucus, and the like, trace evidence invisible to the naked eye under normal light conditions at places, such as crime scenes and / or forensic labs. For the detection of bodily fluids and tracing evidence, the wearable device may illuminate the target using different light sources and analyze various images corresponding to the target obtained in response to the illumination thereof.

[0187] The wearable device may be used in educational applications and for research applications for activities, such as demonstrating fluorescence, reflectance, and transmittance principles in laboratory settings or classroom settings. In other words, the present subject matter enables assessing ample properties by analyzing how different wavelengths pass through different materials.

[0188] The wearable device of the present subject matter is hands-free, portable, and versatile. For instance, since the wearable device can be worn by the user, the present subject matter replaces various specialized instruments, such as image sensors, light sources, and the like, with a single device. The present subject matter may provide real-time analysis to detect and classify problematic cellular entities and visualize contaminants, infections, state of a tissue sample, and the like. The present subject matter has a multispectral capability, such as UV imaging, IR imaging, visible imaging,transmittance imaging, and the like. The present subject matter may facilitate edge-based Al technique or cloud-based Al for the analysis and / or detection and / or visualization of the problematic cellular entities.

[0189] The wearable device can be used for detecting the presence of problematic cellular entities in diabetic foot ulcers, surgical site infections, bums, skin, and interior of the body, such as esophagus, stomach, and colon. The wearable device can also be used in the fields of plastic surgery, photodynamic therapy monitoring, and anti-microbial susceptibility testing. For instance, the wearable device may also be used to study anti-microbial susceptibility / resistance by observing and analyzing the target by exposing the target to various antibiotics. For example, the wearable device may be used to study bacteria grown with nutrients and antibiotics, and corresponding biomarker signatures may be recorded. This information may be used to obtain information on the antibiotics to be prescribed based on the antimicrobial susceptibility of the particular bacteria. As will be understood, antimicrobial susceptibility of other pathogens, such as fungi, can also be identified using the wearable device. Further, dose and concentration of antibiotics can also be decided based on dilution factors, to determine the dosage of the antibiotics or antifungals to be given. The wearable device can also be used for quantification of various pathogens present in the sample. The intensity information at various spectral bands may be obtained from the sample and compared with the fluorescence intensity data and / or reflection intensity data from the library database for intensity quantification.

[0190] Although the present subject matter has been described with reference to specific embodiments, this description is not meant to be construed in a limiting sense. Various modifications of the disclosed embodiments, as well as alternate embodiments of the subject matter, will become apparent to persons skilled in the art upon reference to the description of the subject matter.

Claims

WE CLAIM:

1. A wearable device for examining a target, the wearable device comprising:a processor;a light source assembly operably coupled to the processor, the light source assembly comprising:a first set of light sources to emit excitation radiation at a predetermined range of wavelengths to illuminate the target and cause the target to emit fluorescence;an image sensor assembly operably coupled to the processor, wherein the image sensor assembly is to capture a first plurality of images of the target in response to illumination thereof by the light source assembly, the first plurality of images corresponding to fluorescence-based images of the target; andwherein the processor is to:receive the first plurality of images captured by the image sensor assembly;analyze, using an analysis model, the first plurality of images to detect presence of a problematic cellular entity on the target, wherein the analysis model is trained using a plurality of reference fluorescencebased images to detect presence of problematic cellular entities in targets;generate an extended reality environment for viewing by a wearer of the wearable device; andrender a result corresponding to the detection of the problematic cellular entity on the target on the extended reality environment.

2. The wearable device as claimed in claim 1 , wherein the result comprises at least one of:a composite image comprising at least one of a fluorescence-based image of the first plurality of images, a white light image, an oxygenation-based image, a three-dimensional image,;detected problematic cellular entities overlaid on a field of view of the wearer onto a display of the wearable device;one or more alerts triggered when at least one of an intensity of the problematic cellular entity exceeds a threshold intensity and a parameter associated with the detected problematic cellular entity is outside a nominal range;one or more recorded images or videos corresponding to the detection of the problematic cellular entity; anda real-time stream of the result to an external system communicatively coupled to the wearable device.

3. The wearable device as claimed in claim 1, wherein the light source assembly further comprises:a second set of light sources to emit radiation at a second predetermined range of wavelengths to illuminate the target without causing the target to emit fluorescence.

4. The wearable device as claimed in claim 3, wherein the image sensor assembly is to capture:a second plurality of images of the target in response to illumination thereof by the second set of light sources, the second plurality of images corresponding to one or more white light images formed based on light reflected by the target;a third plurality of images of the target in response to illumination thereof by the second set of light sources, the third plurality of images corresponding to one or more images formed based on light reflected by the target and associated with identification of oxygenation at a plurality of regions in the target; anda fourth plurality of images of the target in response to illumination thereof by the second set of light sources, the fourth plurality of images corresponding to one or more three-dimensional images formed based on light reflected by the target; andwherein the processor is to:analyze, using the analysis model, the first plurality of images, the second plurality of images, the third plurality of images, and the fourth plurality of images, or combinations thereof, to detect presence of the problematic cellular entity on the target, wherein the analysis model is trained using a plurality of reference fluorescence-based images, a plurality of reference white light images, a plurality of reference oxygenation-based images, and a plurality of reference three-dimensional images, or combinations thereof, to detect presence of problematic cellular entities in targets;generate a composite image comprising a fluorescence-based image of the first plurality of images, an image of the second plurality of images, an image of the third plurality of images, and an image of the fourth plurality of images, or combinations thereof, depicting presence of the problematic cellular entity in the target; andrender the composite image on the extended reality environment.

5. The wearable device as claimed in claim 4, wherein the processor is further to determine tissue oxygenation at the target based on analysis of the third plurality of images, wherein the tissue oxygenation comprises at least one of deoxygenated hemoglobin of the target, oxygenated hemoglobin of the target, oxygen saturation of the target, skin perfusion, and oxyhemoglobin.

6. The wearable device as claimed in claim 1, wherein the image sensor assembly further comprises:an image sensor; andone or more emission filters positioned between the target and the image sensor, wherein the one or more emission filters are tunable to allow passing of at least one of a wavelength and a wavelength band of thepredetermined range of wavelengths, such that light passed through the one or more emission filters corresponds to the one or more fluorescence-based images of the first plurality of images.

7. The wearable device as claimed in claim 1, wherein the processor is further to classify, using the analysis model, at least one of a family, a genus, a species, a gram type, and a strain of the problematic cellular entity.

8. The wearable device as claimed in claim 1, wherein the target comprises a wound region, and wherein the processor is further to determine at least one of a length, a width, a perimeter, an area, a depth, a degree of infection, a healing rate, a temperature distribution, a tissue classification, biofilm information, and a degree of contamination of the wound region.

9. The wearable device as claimed in claim 1, further comprising a projection element operably coupled to the processor, wherein the projection element is to project the result corresponding to the detection of the problematic cellular entity onto eyes of the wearer of the wearable device.

10. The wearable device as claimed in claim 1, wherein the target comprises at least one of a wound on a body part, a tissue sample, an edible product, laboratory equipment, a sanitary device, a surgical blade, and a bodily fluid.

11. The wearable device as claimed in claim 1, wherein the problematic cellular entity comprises at least one of a pathogen, a bacterium, a fungus, a cancerous tissue, a necrotic tissue, or combinations thereof.

12. The wearable device as claimed in claim 1, further comprising a lens, wherein the lens enables viewing of the target by the wearer while the processor identifies the problematic cellular entity or the absence of the problematic cellular entity in the target based on the analysis.

13. The wearable device as claimed in claim 1 , further comprising:a display to display a user interface (Ul), wherein the Ul is to receive inputs from the wearer to select at least one of a mode of operation and an imaging mode, wherein the mode of operation comprises at least one of a diagnostic mode, a forensic mode, a cosmetic mode, a surface inspection mode, and an educational mode, and wherein the imaging mode comprises at least one of a fluorescence mode, a reflectance mode, and an oxygenation mode; andwherein the processor is to operate the light source assembly and the image sensor assembly based on the received inputs.

14. The wearable device as claimed in claim 1 , further comprising:a first polarizer positioned between the first set of light sources and the target to allow excitation radiation of a first polarization to pass through; and a second polarizer positioned between the target and an image sensor of the image sensor assembly to allow light emitted by the target of a second polarization to pass through,wherein the first polarizer is aligned 90 degrees from the second polarizer, and wherein one of the first polarization and the second polarization comprises a Left-Handed Circular Polarization (LHCP) and the other of the first polarization and the second polarization comprises a Right-Handed Circular Polarization (RHCP).

15. The wearable device as claimed in claim 1, wherein the image sensor assembly comprises an image sensor configured to directly receive light emitted by the target without filtering by an optical bandpass filter, and wherein the analysis model is trained to differentiate between fluorescence in the fluorescence-based images emerging from the problematic cellular entity and fluorescence in the fluorescence-based images emerging from regions other than the problematic cellular entity.

16. The wearable device as claimed in claim 1 , wherein the analysis model comprises at least one of an Artificial Neural Network (ANN) model, a Machine Learning (ML) model, a convolutional neural network (CNN), a support vector machine (SVM) model, and a large language model (LLM).

17. The wearable device as claimed in claim 1 , wherein the extended reality environment comprises at least one of a virtual reality environment and an augmented reality environment.

18. The wearable device as claimed in claim 1 , wherein the wearable device corresponds to an eyeglass.

19. The wearable device as claimed in claim 1 , wherein the wearable device is a head-up display device (HUD).

20. A clip-on assembly for a wearable device for examining a target, the clip-on assembly comprising:a processor;a light source assembly operably coupled to the processor, the light source assembly comprising:a first set of light sources to emit excitation radiation at a predetermined range of wavelengths to illuminate the target and cause the target to emit fluorescence;an image sensor assembly operably coupled to the processor, wherein the image sensor assembly is to capture a first plurality of images of the target in response to illumination thereof by the light source assembly, the first plurality of images corresponding to fluorescence-based images of the target; andwherein the processor is to:receive the first plurality of images captured by the image sensor assembly;analyze, using an analysis model, the first plurality of images to detect presence of a problematic cellular entity on the target, wherein the analysis model is trained using a plurality of reference fluorescencebased images to detect presence of problematic cellular entities in targets;generate a virtual environment for viewing by a wearer of the wearable device; andrender a result corresponding to the detection of the problematic cellular entity on the target on the virtual environment.

21. The clip-on assembly as claimed in claim 20, wherein the light source assembly further comprises:a second set of light sources to emit radiation at a second predetermined range of wavelengths to illuminate the target without causing the target to emit fluorescence.

22. The clip-on assembly as claimed in claim 21 , wherein the image sensor assembly is to capture a third plurality of images of the target in response to illumination thereof by the second set of light sources, the third plurality of images corresponding to one or more images formed based on light reflected by the target and associated with identification of oxygenation at a plurality of regions in the target; andwherein the processor is to:determine tissue oxygenation at the target based on analysis of the third plurality of images;analyze, using the analysis model, the first plurality of images and the third plurality of images to detect presence of the problematic cellular entity on the target based on the determined tissue oxygenation, wherein the analysis model is trained using a plurality of reference fluorescence-based images and a plurality of reference oxygenation-based images to detect presence of problematic cellular entities in targets;generate a composite image comprising a fluorescence-based image of the first plurality of images and an image of the third plurality of images, depicting presence of the problematic cellular entity in the target; and render the composite image on the virtual environment.

23. The clip-on assembly as claimed in claim 22, wherein the tissue oxygenation comprises at least one of deoxygenated hemoglobin of the target, oxygenated hemoglobin of the target, oxygen saturation of the target, skin perfusion, and oxyhemoglobin.

24. The clip-on assembly as claimed in claim 20, wherein the image sensor assembly further comprises:an image sensor; andone or more emission filters positioned between the target and the image sensor, wherein the one or more emission filters are tunable to allow passing of at least one of a wavelength and a wavelength band of the predetermined range of wavelengths, such that light passed through the one or more emission filters corresponds to the one or more fluorescence-based images of the first plurality of images.

25. The clip-on assembly as claimed in claim 20, wherein an exogenous marker is applied to the target, and wherein the illumination by the light source assembly causes the exogenous marker to emit fluorescence for detection of the problematic cellular entity, wherein the exogenous marker comprises at least one of Indocyanine Green (ICG), methylene blue, Fluorescein, Rhodamine, Alexa Fluor dyes, and Cyanine dyes.

26. A wearable device for examining a target, the wearable device comprising:a pair of eyeglasses having a lens; anda clip-on assembly adapted to be mounted onto the pair of eyeglasses, the clip-on assembly comprising:a processor;a light source assembly operably coupled to the processor, the light source assembly comprising:a first set of light sources to emit excitation radiation at a predetermined range of wavelengths to illuminate the target and cause the target to emit fluorescence;an image sensor assembly operably coupled to the processor, wherein the image sensor assembly is to capture a first plurality of images of the target in response to illumination thereof by the light source assembly, the first plurality of images corresponding to fluorescence-based images of the target; andwherein the processor is to:receive the first plurality of images captured by the image sensor assembly;analyze, using an analysis model, the first plurality of images to detect presence of a problematic cellular entity on the target, wherein the analysis model is trained using a plurality of reference fluorescencebased images to detect presence of problematic cellular entities in targets;generate a virtual environment for viewing by a wearer of the wearable device; andrender a result corresponding to the detection of the problematic cellular entity on the target on the virtual environment.

27. The wearable device as claimed in claim 26, wherein the pair of eyeglasses is a prescription glass.

28. The wearable device as claimed in claim 26, wherein the light source assembly further comprises:a second set of light sources to emit radiation at a second predetermined range of wavelengths to illuminate the target without causing the target to emit fluorescence.

29. The wearable device as claimed in claim 28, wherein the image sensor assembly is to capture:a second plurality of images of the target in response to illumination thereof by the second set of light sources, the second plurality of images corresponding to one or more white light images formed based on light reflected by the target;a third plurality of images of the target in response to illumination thereof by the second set of light sources, the third plurality of images corresponding to one or more images formed based on light reflected by the target and associated with identification of oxygenation at a plurality of regions in the target; anda fourth plurality of images of the target in response to illumination thereof by the second set of light sources, the fourth plurality of images corresponding to one or more three-dimensional images formed based on light reflected by the target; andwherein the processor is to:analyze, using the analysis model, the first plurality of images, the second plurality of images, the third plurality of images, and the fourth plurality of images, or combinations thereof, to detect presence of the problematic cellular entity on the target, wherein the analysis model is trained using a plurality of reference fluorescence-based images, a plurality of reference white light images, a plurality of reference oxygenation-based images, and a plurality of reference three-dimensional images, or combinations thereof, to detect presence of problematic cellular entities in targets;generate a composite image comprising a fluorescence-based image of the first plurality of images, an image of the second plurality of images, an image of the third plurality of images, and an image of the fourth plurality of images, or combinations thereof, depicting presence of the problematic cellular entity in the target; andrender the composite image on the virtual environment.

30. A system for examining a target, the system comprising:a wearable device adapted to be worn on a head of a wearer, the wearable device comprising:a light source assembly comprising a first set of light sources to emit excitation radiation at a predetermined range of wavelengths to illuminate the target and cause the target to emit fluorescence;an image sensor assembly to capture a first plurality of images of the target in response to illumination thereof by the light source assembly, the first plurality of images corresponding to fluorescencebased images of the target; anda connectivity module to transmit the first plurality of images; and a processor communicatively coupled to the connectivity module of the wearable device, wherein the processor stores an analysis model, wherein the analysis model is trained using a plurality of reference fluorescence-based images to detect presence of problematic cellular entities in targets, andwherein the processor is to:receive the first plurality of images from the wearable device; analyze, using the analysis model, the first plurality of images to detect presence of a problematic cellular entity on the target;generate a virtual environment for viewing by the wearer of the wearable device; andrender a result corresponding to the detection of the problematic cellular entity on the target on the virtual environment.

31. The system as claimed in claim 30, wherein the light source assembly further comprises:a second set of light sources to emit radiation at a second predetermined range of wavelengths to illuminate the target without causing the target to emit fluorescence.

32. The system as claimed in claim 31 , wherein the image sensor assembly is to capture a third plurality of images of the target in response to illumination thereof by the second set of light sources, the third plurality of images corresponding to one or more images formed based on light reflected by the target and associated with identification of oxygenation at a plurality of regions in the target; andwherein the processor is to:determine tissue oxygenation at the target based on analysis of the third plurality of images;analyze, using the analysis model, the first plurality of images and the third plurality of images to detect presence of the problematic cellular entity on the target based on the determined tissue oxygenation, wherein the analysis model is trained using a plurality of reference fluorescence-based images and a plurality of reference oxygenation-based images to detect presence of problematic cellular entities in targets;generate a composite image comprising a fluorescence-based image of the first plurality of images and an image of the third plurality of images, depicting presence of the problematic cellular entity in the target; and render the composite image on the virtual environment.

33. The system as claimed in claim 32, wherein the tissue oxygenation comprises at least one of deoxygenated hemoglobin of the target, oxygenated hemoglobin of the target, oxygen saturation of the target, skin perfusion, and oxyhemoglobin.

34. The system as claimed in claim 30, wherein the image sensor assembly further comprises:an image sensor; andone or more emission filters positioned between the target and the image sensor, wherein the one or more emission filters are tunable to allow passing of at least one of a wavelength and a wavelength band of the predetermined range of wavelengths, such that light passed through the one ormore emission filters corresponds to the one or more fluorescence-based images of the first plurality of images.

35. The system as claimed in claim 30, wherein the analysis model comprises at least one of an Artificial Neural Network (ANN) model, a Machine Learning (ML) model, a convolutional neural network (CNN), a support vector machine (SVM) model, and a large language model (LLM).

36. The system as claimed in claim 30, wherein the processor is further to classify the problematic cellular entity by at least one of a family, a genus, a species, a gram type, and a strain of the problematic cellular entity.

37. A method for examining a target using a wearable device, the method comprising:illuminating, by a light source assembly comprising a first set of light sources, the target with excitation radiation at a predetermined range of wavelengths to cause the target to emit fluorescence;capturing, by an image sensor assembly, a first plurality of images of the target in response to illumination thereof by the light source assembly, the first plurality of images corresponding to fluorescence-based images of the target;receiving, by a processor, the first plurality of images from the image sensor assembly;analyzing, by the processor using an analysis model, the first plurality of images to detect presence of a problematic cellular entity on the target, wherein the analysis model is trained using a plurality of reference fluorescence-based images to detect presence of problematic cellular entities in targets;generating, by the processor, a virtual environment for viewing by a wearer of the wearable device; andrendering a result corresponding to the detection of the problematic cellular entity on the target on the virtual environment.

38. The method as claimed in claim 37, further comprising: illuminating, by a second set of light sources of the light source assembly, the target with radiation at a second predetermined range of wavelengths without causing the target to emit fluorescence.

39. The method as claimed in claim 38, further comprising:capturing, by the image sensor assembly, a third plurality of images of the target in response to illumination thereof by the second set of light sources, the third plurality of images corresponding to one or more images formed based on light reflected by the target and associated with identification of oxygenation at a plurality of regions in the target;determining, by the processor, tissue oxygenation at the target based on analysis of the third plurality of images;analyzing, by the processor using the analysis model, the first plurality of images and the third plurality of images to detect presence of the problematic cellular entity on the target based on the determined tissue oxygenation, wherein the analysis model is trained using a plurality of reference fluorescence-based images and a plurality of reference oxygenation-based images to detect presence of problematic cellular entities in targets;generating, by the processor, a composite image comprising a fluorescence-based image of the first plurality of images and an image of the third plurality of images, depicting presence of the problematic cellular entity in the target; andrendering the composite image on the virtual environment.

40. The method as claimed in claim 39, wherein the tissue oxygenation comprises at least one of deoxygenated hemoglobin of the target, oxygenated hemoglobin of the target, oxygen saturation of the target, skin perfusion, and oxyhemoglobin.

41. The method as claimed in claim 37, further comprising:selectively passing, by one or more emission filters positioned between the target and an image sensor of the image sensor assembly, at least one of a wavelength and a wavelength band of the predetermined range of wavelengths, such that light passed through the one or more emission filters corresponds to the one or more fluorescence-based images of the first plurality of images.

42. The method as claimed in claim 37, further comprising:classifying, by the processor using the analysis model, the problematic cellular entity by at least one of a family, a genus, a species, a gram type, and a strain of the problematic cellular entity.

43. The method as claimed in claim 37, wherein the target comprises a wound region, and wherein the method further comprises:determining, by the processor, at least one of a length, a width, a perimeter, an area, a depth, a degree of infection, a healing rate, a temperature distribution, a tissue classification, biofilm information, and a degree of contamination of the wound region.

44. The method as claimed in claim 37, further comprising:transmitting, by a connectivity module, at least one of the first plurality of images and the result corresponding to the detection to a location outside the wearable device.

45. The method as claimed in claim 37, wherein the problematic cellular entity comprises at least one of a pathogen, a bacterium, a fungus, a cancerous tissue, a necrotic tissue, or combinations thereof.

46. A method for training an analysis model for detecting a problematic cellular entity on a target, the method comprising:receiving a plurality of reference images, wherein the plurality of reference images comprises at least one of reference fluorescence-basedimages, reference white light images, reference oxygenation-based images, reference three-dimensional images, and reference thermal images;tagging the plurality of reference images with a plurality of reference labels, wherein the plurality of reference labels comprise at least one of a type of the target, a type of the problematic cellular entity, a species of the problematic cellular entity, a gram type of the problematic cellular entity, and a strain of the problematic cellular entity;pre-processing the plurality of reference images tagged with the plurality of reference labels;extracting a plurality of spatial features and a plurality of spectral features from the plurality of reference images; andtraining the analysis model using the plurality of spatial features and the plurality of spectral features to detect presence of the problematic cellular entity on the target.

Images