Multispectral image capture

Abstract

The method for screening includes illuminating a sample with light at a first wavelength from a screen of the system while the system is in a predetermined position relative to the sample. The method also includes capturing a first image of the sample with a camera of the system while the system is in the predetermined position and the sample is illuminated with light at the first wavelength. The method also includes illuminating the sample with light at a second wavelength from the screen while the system is in the predetermined position. The method also includes capturing a second image of the sample with the camera while the system is in the predetermined position and the sample is illuminated with light at the second wavelength. The method also includes combining the first and second images to generate a multispectral image.

Description

[Technical Field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates generally to systems and methods for taking multispectral images, and more particularly to systems and methods for taking and analyzing multispectral images to detect biomarkers in a sample using a phone as part of colorectal cancer (CRC) screening. [Background technology]

[0002] Colonoscopy is an endoscopic procedure commonly used to screen for colorectal cancer or detect other abnormalities in the colon and rectum. During a colonoscopy, a long, flexible tube (i.e., a colonoscope) is inserted into the rectum. A tiny video camera at the tip of the tube allows the physician to view the inside of the entire colon. If necessary, polyps or other types of abnormal tissue can be removed through the scope during a colonoscopy. Tissue samples can also be taken (e.g., biopsies) during a colonoscopy. However, it would be useful to have a convenient, non-invasive system and method that provides an alternative to screening for colorectal cancer. Summary of the Invention

[0003] A method of screening is disclosed. The method includes illuminating a sample with light at a first wavelength from a screen of the system while the system is in a predetermined position relative to the sample. The method also includes capturing a first image of the sample using a camera of the system while the system is in the predetermined position and the sample is illuminated with light at the first wavelength. The method also includes illuminating the sample with light at a second wavelength from the screen while the system is in the predetermined position. The method also includes capturing a second image of the sample using the camera while the system is in the predetermined position and the sample is illuminated with light at the second wavelength. The method also includes combining the first and second images to generate a multispectral image. The method also includes measuring spectral features in the multispectral image.

[0004] A method for performing colorectal cancer (CRC) screening is also disclosed. The method includes identifying a position of a system relative to a sample. The system includes a phone or tablet with a screen on its front side and a camera positioned above the screen. The sample includes stool, saliva, sweat, blood, urine, skin, or a combination thereof. The method also includes instructing a user holding the phone or tablet to move the phone or tablet to a predetermined position according to the identified position. Moving the phone or tablet can change the distance between the front side and the sample, change the angle between the front side and the sample, or both. The method also includes illuminating the sample with light of a first wavelength from the screen while the phone or tablet is in the predetermined position. The method also includes capturing a first image of the sample using the camera while the phone or tablet is in the predetermined position and the sample is illuminated with light of the first wavelength. The method also includes illuminating the sample with light of a second wavelength from the screen while the phone or tablet is in the predetermined position. The sample is illuminated with light of the second wavelength after the first image is captured. The first and second wavelengths are different. The method also includes capturing a second image of the sample with the camera while the phone or tablet is in place and the sample is illuminated with light at the second wavelength. The method also includes combining the first and second images to generate a multispectral image. The method also includes measuring spectral features at each pixel in the multispectral image using a spectral processing algorithm executed on the system. The method also includes identifying a concentration of a biomarker in the sample based at least in part on the spectral features. The biomarker includes hemoglobin, bilirubin, calprotectin, albumin, fatty acids, hydrogen sulfide, or a combination thereof. The method also includes identifying the person from whom the sample was taken as being at increased risk for a condition based at least in part on the concentration of the biomarker.

[0005] A system for conducting screening is also disclosed. The system includes a screen configured to emit light that illuminates a sample. The screen is configured to vary the wavelength of the light between a first wavelength and a second wavelength, where the first and second wavelengths are different. The system also includes a camera configured to capture a first image of the sample while the sample is illuminated with light at the first wavelength and a second image of the sample while the sample is illuminated with light at the second wavelength. The system also includes a computing system configured to combine the first and second images to generate a multispectral image, measure spectral features in the multispectral image, and identify the person from whom the sample was taken as being at increased risk for a predetermined condition based at least in part on the spectral features. [Brief explanation of the drawings]

[0006] [Figure 1] 1 shows a schematic diagram of a system for identifying molecules in a sample, according to an embodiment. [Figure 2A] 1 shows an image of a stool sample having hemoglobin therein, according to an embodiment. [Figure 2B] 1 shows an image of a stool-only (i.e., no hemoglobin) sample, according to an embodiment. [Figure 3] 1 shows a graph illustrating stool samples with hemoglobin versus stool only samples, according to an embodiment. [Figure 4] 1 shows a graph illustrating dose response in hemoglobin detection as the concentration of hemoglobin in stool increases, according to an embodiment. [Figure 5] 1 shows a graph illustrating reflectance versus wavelength for different concentrations of hemoglobin, according to an embodiment. [Figure 6] 1 shows a graph illustrating detection of a spectral signature in an image, according to an embodiment. [Figure 7] 1 shows a flowchart of a method for detecting molecules in a sample, according to an embodiment. [Figure 8]2 shows a schematic diagram of a system (eg, of FIG. 1) for taking images of samples in a toilet, according to an embodiment. [Figure 9] 1 shows a flowchart of a method for performing colorectal cancer (CRC) screening, according to an embodiment. [Figure 10] 1 shows a flowchart of another method for performing colorectal cancer (CRC) screening, according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0007] The presently disclosed subject matter will now be described more fully hereinafter with reference to the accompanying drawings, which illustrate some, but not all, embodiments of the disclosure. Like numerals refer to like elements throughout. The presently disclosed subject matter may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements. Indeed, numerous modifications and other embodiments of the presently disclosed subject matter as set forth herein will come to mind to one skilled in the art to which the presently disclosed subject matter pertains having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Therefore, it should be understood that the presently disclosed subject matter is not limited to the particular embodiments disclosed, and that modifications and other embodiments are intended to be included within the scope of the appended claims.

[0008] Hemoglobin detection by camera FIG. 1 shows a schematic diagram of a system 100 for identifying molecules in a sample, according to an embodiment. The molecules may be or include hemoglobin, bilirubin, calprotectin, albumin, fatty acids, hydrogen sulfide, etc. The sample may be or include stool, urine, saliva, other biological specimens, or combinations thereof. FIG. 2A shows an image 200A of a stool sample 210A having hemoglobin therein, and FIG. 2B shows an image 200B of a stool-only (i.e., no hemoglobin) sample 210B, according to an embodiment.

[0009] System 100 may include camera 110, computing system 120, and test device 130. In one embodiment, camera 110, computing system 120, test device 130, or a combination thereof, may be located together on a single device. For example, at least a portion of system 100 may include, be a part of, or connect to a smartphone, tablet, laptop, etc. Camera 110 may be configured to capture one or more images (e.g., images 200A, 200B) of a sample (e.g., samples 210A, 210B), which may or may not have molecules therein. As part of capturing images 200A, 200B, one or more filters (e.g., three shown: 112, 114, 116) may be applied. In one embodiment, filters 112, 114, 116 may be applied to the lens of camera 110. For example, filters 112, 114, 116 may be or include thin film filters that cover the lens of camera 110. The membrane filters can be manually changed so that three images of a single sample can be taken—one image with each filter. In other embodiments, the filters 112, 114, 116 can be built into (e.g., directly into) the CCD focal plane of the camera 110. In yet other embodiments, a Bayer pattern filter array can be used. In yet other embodiments, the filters 112, 114, 116 can be applied to the images 200A, 200B by the computing system 120.

[0010] The computing system 120 may be configured to analyze the images 200A, 200B to detect the presence and / or amount of a molecule (e.g., hemoglobin) in a sample (e.g., stool). More specifically, the computing system 120 may be configured to detect the molecule's unique spectral signature to distinguish between samples with and without the molecule. FIG. 3 shows a graph illustrating a stool sample 210A with hemoglobin versus a stool-only sample 210B, according to an embodiment. In one example, as the amount of a molecule in a sample increases, the detectability of the molecule also increases in a dose-responsive manner. This is shown in FIG. 4, which shows a graph illustrating the dose-response of hemoglobin detection as the concentration of hemoglobin in the stool increases, according to an embodiment. More specifically, the ratio of specific wavelength features and quantitative comparison of these values obtained across multiple types of operations may help distinguish samples with hemoglobin from samples without hemoglobin.

[0011] Testing device 130 may be or include a fecal immunological occult blood test (FIT) device or other diagnostic test / information. Testing device 130 may test for molecules in a sample (e.g., stool) before, simultaneously with, or after camera 110 and computing system 120 attempt to detect the presence and / or amount of molecules (e.g., hemoglobin) in the sample (e.g., stool). For example, testing device 130 may be configured to connect to computing system 120 and act as a secondary testing system for molecules after camera 110 and computing system 120 perform image-based detection.

[0012] FIG. 5 illustrates a graph showing reflectance versus wavelength for multiple different concentrations of hemoglobin, according to an embodiment. Each hemoglobin curve can have one or more spectral signatures 510 (e.g., also referred to as features and / or fingerprints) that can be used to detect its presence in various types of samples. The spectral signatures 510 can resemble the letter V (also referred to as a V feature) and / or the letter W (also referred to as a W feature). The spectral signatures 510 can be within a predetermined wavelength range. The predetermined wavelength range can be between about 450 nm and about 690 nm, between about 575 nm and about 625 nm, or between about 600 nm and about 650 nm.

[0013] As described in more detail below, the computing system 120 may perform spectral processing algorithms on the images 200A, 200B to detect the presence of a spectral signature 510 for a molecule (e.g., hemoglobin). To accomplish this, the algorithm may utilize spectral continuum removal and / or band ratio analysis. Continuum removal may use linear interpolation to remove the slope of the spectral signature 510 while preserving one or more spectral absorption features 520A, 520B. As used herein, a spectral absorption feature refers to a change in the shape of a spectral curve. Continuum removal may be performed within a predetermined wavelength range.

[0014] Then, after continuum removal has been performed, a band ratio may be determined for one or more of the absorption features 520A, 520B to measure the ratio of the absorption features 520A, 520B that indicates the amount of chemical associated with the absorption features 520A, 520B present in the sample. In one embodiment, the reflectance value for point 520B may represent the numerator, and the reflectance value for point 520A may be the denominator. The ratio (e.g., numerator / denominator) may be greater than or equal to 1 and positive (i.e., hemoglobin is present).

[0015] 6 shows a graph illustrating detection of a spectral signature in an image, according to an embodiment. Line 610 represents a measured spectrum (e.g., from spectral signature 510). Interpolation can be used to identify spectrum 620, which is a measure of the continuum (e.g., overall shape) of measured spectrum 610.

[0016] Curve 630 can be determined by dividing spectrum 620 by spectrum 610. This is called continuum removal and effectively removes the overall shape of the measured spectrum 610 while preserving (e.g., enhancing) the spectral features (e.g., spectral absorption features 520A, 520B). From the continuum-removed spectrum 630, the spectral depth can be determined using band ratios, as shown along dashed vertical line 640.

[0017] 7 shows a flowchart of a method 700 for detecting molecules in a sample, according to an embodiment. An exemplary sequence of method 700 is provided below, however, one or more steps of method 700 may be performed in a different order, combined, divided into substeps, repeated, or omitted. One or more steps of method 700 may be performed by system 100.

[0018] Method 700 may also include capturing one or more images of the sample, as at 702. For example, this may include capturing image 200A including sample 210A. Image 200A may be captured with camera 110.

[0019] Method 700 may further include applying one or more filters 112, 114, 116 to one or more images 200A, as at 704. As described above, filters 112, 114, 116 may be applied to camera 110 and / or may be applied by computing system 120. Filters 112, 114, 116 may be or include bandpass filters configured to pass a predetermined wavelength range. As described above, for hemoglobin, the predetermined wavelength range may be from about 450 nm to about 690 nm, from about 575 nm to about 625 nm, or from about 600 nm to about 650 nm.

[0020] Each filter 112, 114, 116 may be configured to pass a different wavelength. The first filter 112 may be configured to pass a first wavelength, the second filter 114 may be configured to pass a second wavelength, and the third filter 116 may be configured to pass a third wavelength. The third wavelength may be between the first and second wavelengths. In one embodiment, the first wavelength may be between about 639 nm and about 647 nm, the second wavelength may be between about 623 nm and about 631 nm, and the third wavelength may be between about 628 nm and about 636 nm. In another embodiment, the first wavelength may be about 643 nm, the second wavelength may be about 627 nm, and the third wavelength may be about 632 nm.

[0021] The method 700 may also include detecting a spectral signature 510 in the image(s) 200A, as at 706. The spectral signature 510 (e.g., a V-shape and / or a W-shape) may be detected by the computing system 120. The spectral signature 510 may be detected after the filters 112, 114, 116 are applied to the image(s) 200A. The spectral signature 510 may be unique to the molecule being detected (e.g., hemoglobin). As mentioned above, the spectral signature 510 may include one or more absorption features 520A, 520B.

[0022] In one embodiment, detecting the spectral signature 510, as in 708, may include performing continuum removal on the spectral signature 510. The continuum removal may be performed within a predetermined wavelength range. The continuum removal may be performed using linear interpolation to remove slope from the spectral signature 510 while preserving one or more absorption features (e.g., absorption feature 520A). In one example, performing continuum removal includes: where w represents a weight value, r(λ1) represents the spectral value of the absorption feature 520A at a first wavelength, and r(λ2) represents the spectral value of the absorption feature 520A at a second wavelength: w×r(λ1)+(1-w)×r(λ2) Equation 1 The weight value w may be specific to the particular molecule being detected. For example, the weight value w may be 0.5156 for hemoglobin.

[0023] In other words, performing continuum removal may include determining a first product of the weight and the spectral value of the absorption feature 520A at a first wavelength, determining a second product of the complement of the weight and the spectral value of the absorption feature 520A at a second wavelength, and determining a sum of the first product and the second product.

[0024] Detecting the spectral signature 510 may additionally or alternatively include determining a band ratio of the absorption feature 520A in the spectral signature 510, as at 610. The band ratio may be determined after continuum removal has been performed. In one example, the band ratio is determined as follows: where r(λ3) represents the spectral value of the absorption feature 520A at a third wavelength: Band ratio = (w × r(λ1) + (1-w) × r(λ2)) / r(λ3) Equation 2 In other words, the numerator of the band ratio may include the sum (from Equation 1) and the denominator of the band ratio may include the value of the spectrum of absorption feature 520A at the third wavelength.

[0025] In one embodiment, the image 200A may include multiple pixels, and the spectral signature 510 may be detected for one or more of the pixels (e.g., a band ratio may be determined). For example, the spectral signature 510 may be detected for all of the pixels in the image 200A (e.g., a band ratio may be determined).

[0026] Method 700 may also include aggregating band ratios for pixels in image 200A, as at 712. One or more techniques may be used to aggregate the band ratios. For example, one technique may include aggregating or counting values above a certain threshold, while another technique may include aggregating or counting values over a certain spatial region. In one embodiment, one of the techniques may be used when the concentration of the molecule in the sample is below a predetermined concentration threshold, and another technique may be used when the concentration of the molecule in the sample is above a predetermined concentration threshold. In other embodiments, multiple techniques may be combined to generate a composite.

[0027] Method 700 may also include identifying a molecule (e.g., hemoglobin) as present in sample 210A, as at 714. Identifying that a molecule is present may be based at least in part on detecting a spectral signature 510, identifying a band ratio, aggregating band ratios, or a combination thereof. Method 700 may be capable of detecting a predetermined mass of a molecule (e.g., hemoglobin) within 1 gram of sample 210A (e.g., stool + hemoglobin). The predetermined mass may be between about 5 micrograms and about 10 micrograms, or between about 10 micrograms and about 20 micrograms, which is below the threshold used by conventional FIT testing in the United States (i.e., 20 micrograms hemoglobin / gram stool).

[0028] Method 700 may also include determining the amount of molecules present in sample 210A, as at 716. Determining the amount of molecules present may be based at least in part on detecting spectral signatures 510, determining band ratios, aggregating band ratios, other mathematical approaches, or a combination thereof. In other embodiments, determining the amount of molecules present may be a function of the band ratio scores by pixels of the sample. The term "function" can be used to refer to any algorithm that takes band ratio scores as input and generates a numerical value to be assigned to the sample.

[0029] Method 700 may also include using test device 130 to confirm the presence of a molecule (e.g., hemoglobin) in sample 210A, as in 718. This may additionally or alternatively include using test device 130 to determine the amount of the molecule present in sample 210A. This step may occur before, simultaneously with, or after one or more of steps 702-716. For example, this step may occur in response to the image-based identification in step 714 and / or step 716.

[0030] In other embodiments, additional diagnostic information may be obtained about the patient instead of or in addition to using the test device 130 (e.g., FIT test). For example, patient history or lab data about the patient may be used to generate a composite score that includes multiple risk variables beyond the spectrum and FIT alone.

[0031] Method 700 may also include performing a colonoscopy, as at 720. The colonoscopy may be performed at least in part in response to determining (at 714) that the molecule is present, determining (at 716) the amount of the molecule present, determining (at 718) that the molecule is present, or a combination thereof.

[0032] Multispectral image capture Conventional digital cameras may be configured to capture broad bands of the wavelength spectrum. For example, the bandwidths of the red, green, and / or blue channels of a conventional color digital camera may exceed 100 nanometers, while the spectral features of interest span tens of nanometers. Images obtained from conventional cameras represent composite and / or integrated intensity levels. For example, the intensity of a pixel for a conventional color digital camera is an average value of the intensity across the bandwidths of the red, green, and / or blue channels. As a result, the ability to characterize the intensity (e.g., of a pixel in an image) at a specific wavelength has not previously been possible.

[0033] The systems and methods described herein can be configured to capture multispectral images using a camera (e.g., camera 110) without the addition or modification of any additional hardware. The systems and methods can also be configured to characterize the intensity (e.g., of pixels in an image) at specific wavelengths. Knowing the intensity at specific wavelengths can provide a unique signature that can be used for detection and / or identification purposes. For example, the systems and methods may be used to detect hemoglobin in a sample (e.g., samples 210A, 210B). As mentioned above, samples 210A, 210B can be or include stool, urine, saliva, other biological specimens, or combinations thereof.

[0034] FIG. 8 shows a schematic diagram of a system 100 (e.g., camera 110) for capturing images (e.g., images 200A, 200B) of stool samples (e.g., samples 210A, 210B) in a toilet 800, according to an embodiment. As mentioned above, system 100 (e.g., camera 110) may include, be part of, or be connected to a smartphone, tablet, laptop, etc. In the embodiment shown in FIG. 8, system 100 is a smartphone, and camera 110 is located on the front side of the smartphone (e.g., the same side as screen 118). For example, camera 110 may be located above screen 118. Although not shown, system 100 may also or alternatively use a flashlight and / or a second camera, both of which may be located on the rear side of the smartphone.

[0035] As shown in FIG. 8 , camera 110 and screen 118 may face a sample (e.g., in toilet 800). Screen 118 may be used as a light source. The wavelength of the light may be adjusted using software within system 100 to emit light at a narrow band of frequencies. The light may then reflect off the sample, toilet 800, the water in toilet 800, or a combination thereof into the camera's field of view and be captured by camera 110. This may be referred to as active imaging. The image captured by camera 110 may be or include one or more, two or more, or three or more narrow band images (tens of nanometers) whose intensities at specific wavelengths can be used for a number of diagnostic or detection purposes. For example, the bandwidth in each image and / or each pixel may be 100 nanometers or less, 50 nanometers or less, 20 nanometers or less, or 10 nanometers or less. Clinical application of this approach may enable the non-invasive detection of biomarkers with known spectral fingerprints and / or wavelength patterns (e.g., hemoglobin) in a variety of human samples, such as stool, saliva, sweat, blood, urine, and skin, among others.

[0036] 9 shows a flowchart of a method 900 for performing colorectal cancer (CRC) screening, according to an embodiment. An exemplary sequence of the method 900 is provided below, however, one or more steps of the method 900 may be performed in a different order, combined, divided into substeps, repeated, or omitted. One or more steps of the method 900 may be performed by the system 100.

[0037] Method 900 may include identifying whether a patient is eligible for CRC screening, as at 902. A patient may be identified as eligible depending on the patient being over a certain age. A patient may also or alternatively be eligible depending on noticing an abnormality (e.g., blood) in the patient's stool or urine.

[0038] If the patient is not eligible, the patient may be referred for other care, as at 904. The patient may also or alternatively see a physician, as at 906, either in person or virtually.

[0039] If the patient is eligible, method 900 may proceed with an in-person or virtual physician visit, as at 908, which may additionally or alternatively include filling a prescription for colorectal cancer screening.

[0040] Method 900 may also include, as at 910, using system 100 to take one or more images (e.g., images 200A, 200B) of a stool sample (e.g., samples 210A, 210B). This may be done at home. The sample may be processed by system 100 to generate results, as at 912. The patient may be instructed to see a doctor, either in person or virtually, depending on the results, as at 906.

[0041] 10 shows a flowchart of a method 1000 for performing colorectal cancer (CRC) screening, according to an embodiment. An exemplary sequence of the method 1000 is provided below, however, one or more steps of the method 1000 may be performed in a different order, combined, divided into substeps, repeated, or omitted. One or more steps of the method 1000 may be performed by the system 100.

[0042] Method 1000 may include determining a position of system 100 relative to the sample (e.g., samples 210A, 210B), as at 1002. More specifically, a user / patient may point a front of system 100 (e.g., smartphone) toward the sample in toilet 800 so that camera 110 and screen 118 face the sample in toilet 800. System 100 may be configured to determine a distance between system 100 (e.g., camera 110 and / or screen 118) and the sample and / or toilet 800. System 100 may also or alternatively be configured to determine an angle between system 100 (e.g., camera 110 and / or screen 118) and the sample and / or toilet 800. System 100 may compare the measured distance and / or angle to a predetermined (e.g., optimal) distance and / or angle and instruct the user / patient to move system 100 to optimize the distance and / or angle.

[0043] Method 1000 may also include illuminating a sample using system 100, as at 1004. More specifically, this may include illuminating a sample in toilet 800 with light from screen 118. The sample may be illuminated with multiple different wavelengths, i.e., one wavelength at a time or multiple different wavelengths simultaneously. For example, the sample may be first illuminated with a first wavelength, and then the sample may be subsequently (or simultaneously) illuminated with a second wavelength. In at least one embodiment, the sample may also be subsequently (or simultaneously) illuminated with a third wavelength. One of the wavelengths may be in the red spectrum, from about 575 nm to about 675 nm (e.g., about 625 nm). Another of the wavelengths may be in the green spectrum, from about 475 nm to about 575 nm (e.g., about 525 nm). Optionally, another of the wavelengths may be in the blue spectrum, from about 420 nm to about 500 nm (e.g., about 460 nm).

[0044] Method 1000 may also include, as at 1006, capturing one or more images (e.g., images 200A, 200B) of one or more samples using system 100. More specifically, this may include capturing multiple images at multiple different wavelengths, frequencies, and / or intensities using camera 110. For example, camera 110 may capture one or more first images of the sample while light illuminating and / or reflecting from screen 118 at a first wavelength. Camera 110 may also subsequently (or simultaneously) capture one or more second images of the sample while light illuminating and / or reflecting from screen 118 at a second wavelength. Camera 110 may also subsequently (or simultaneously) capture one or more third images of the sample while light illuminating and / or reflecting from screen 118 at a third wavelength. Additionally, the effective wavelength of illumination from screen 118 can be adjusted by adding and / or subtracting images illuminated by the flash and / or illuminated by red, green, and / or blue LEDs in screen 118. As described in more detail below, these images can form a multispectral image that can be analyzed using spectral processing algorithms to detect materials of interest (e.g., biomarkers).

[0045] Method 1000 may also include determining whether the quality of the image is greater than a predetermined quality threshold, as at 1008. System 100 (e.g., computing system 120) may determine whether the quality is greater than a predetermined quality threshold. The quality may include spectral quality and / or spatial quality. If the quality is less than the predetermined quality threshold, method 1000 may loop back to step 1002, 1004, or 1006.

[0046] If the quality is above a predetermined quality threshold, method 1000 may proceed to combine the images to generate a multispectral image, as at 1010. More specifically, system 100 (e.g., computing system 120) may combine two or more images (or three or more images) taken at different wavelengths, frequencies, and / or intensities. The images may be combined via addition, subtraction, division, or a combination thereof.

[0047] Method 1000 may also include measuring spectral features within the multispectral image, as at 1012. Examples of spectral features are described above with respect to FIGS. 5-7. The spectral feature or features may be measured using a spectral processing algorithm executed on system 100 (e.g., computing system 120). In one embodiment, the spectral feature or features may be detected and / or measured at each pixel within the multispectral image. In other embodiments, the spectral feature or features may be measured or detected in aggregate across multiple pixels within the multispectral image. As described below, the spectral feature or features may be (or may be used to detect) a biomarker (e.g., hemoglobin) in the sample.

[0048] Method 1000 may also include identifying the presence of biomarkers in the sample, as at 1014. More specifically, this may include identifying or estimating the presence and / or concentration of one or more biomarkers (e.g., hemoglobin) in sample 210A, 210B using a spectral processing algorithm executed on system 100 (e.g., computing system 120). The presence and / or concentration of one or more biomarkers may be based at least in part on an image, a multispectral image, one or more spectral features, or a combination thereof. The presence or concentration of one or more biomarkers may communicate a probable status of a predetermined condition. Exemplary predetermined conditions may include an increased risk of CRC, absence of blood, presence of inflammation, positive infection, etc.

[0049] Method 1000 may also include identifying a condition of the person from whom the sample was taken, as at 1016. The identification may be based at least in part on the captured image, the multispectral image, the spectral feature(s), the presence and / or concentration of the biomarker(s), or a combination thereof. In one embodiment, identifying the condition may include identifying and / or assigning a score (e.g., 70%) to the multispectral image and / or the spectral feature(s) that indicates the presence of one or more biomarkers in the sample. In other embodiments, identifying the condition may include identifying a likelihood that the person has (or is at increased risk for) CRC.

[0050] Method 1000 may also include displaying the results, as at 1018. For example, the results may be displayed on screen 118 of system 100. The results may be or include a captured image, a multispectral image, one or more spectral features, one or more biomarkers, a likelihood of CRC, a qualitative result (e.g., positive or negative), or a combination thereof. When used in a screening context, the results may indicate the need for further treatment and / or an increased risk of CRC. The results may be shared with a physician.

[0051] Method 1000 may also include providing instructions to seek further testing or medical care (e.g., see a physician), as at 1020. Instructions may be provided by system 100 in response to identification of known biomarkers used for CRC screening purposes that exceed a predetermined threshold (e.g., 20 micrograms hemoglobin / gram stool).

[0052] While the present disclosure has been described in connection with preferred embodiments thereof, it should be understood by those skilled in the art that additions, deletions, modifications, and substitutions not specifically described may be made therein without departing from the spirit and scope of the present disclosure as defined in the claims that follow.

Claims

1. A method of screening, comprising: illuminating the sample with light at a first wavelength from a screen of the system while the system is in position relative to the sample; capturing a first image of the sample using a camera of the system while the system is in the predetermined position and the sample is illuminated with the light at the first wavelength; illuminating the sample with the light at a second wavelength from the screen while the system is in the predetermined position; capturing a second image of the sample with the camera while the system is in the predetermined position and the sample is illuminated with the light at the second wavelength; combining the first and second images to generate a multispectral image; measuring spectral features within the multispectral image; A method for providing the above.

2. 10. The method of claim 1, further comprising identifying a location of the system relative to the sample, the system comprising a phone or tablet with the screen on a front side and the camera positioned above the screen, and the sample comprising stool, saliva, sweat, blood, urine, skin, or a combination thereof.

3. 3. The method of claim 2, further comprising the step of instructing a user holding the phone or tablet to move the phone or tablet to the predetermined position in accordance with the identified position, wherein moving the phone changes the distance between the front side and the sample, changes the angle between the front side and the sample, or both.

4. The method of claim 1 , wherein the sample is illuminated with the light at the second wavelength after the first image is taken.

5. The method of claim 1 , wherein the first and second wavelengths are different.

6. 10. The method of claim 1, wherein the first wavelength is from about 575 nm to about 675 nm and the second wavelength is from about 475 nm to about 575 nm.

7. illuminating the sample with the light at a third wavelength from the screen while the system is in the predetermined position, the first, second, and third wavelengths being different, and the third wavelength being between about 420 nm and about 500 nm; capturing a third image of the sample with the camera while the system is in the predetermined position and the sample is illuminated with the light at the third wavelength; combining the first, second, and third images to generate the multispectral image; The method of claim 6 further comprising:

8. The method of claim 1 , further comprising identifying the person from whom the sample was taken as being at increased risk for a predetermined condition based at least in part on the spectral signature.

9. 10. The method of claim 1, further comprising determining a concentration of a biomarker in the sample based at least in part on the spectral features, the biomarker comprising hemoglobin, bilirubin, calprotectin, albumin, fatty acids, hydrogen sulfide, or a combination thereof.

10. 10. The method of claim 9, further comprising identifying the person from whom the sample was taken as being at increased risk for a predetermined condition based at least in part on the biomarkers, wherein the sample comprises feces underwater in a toilet, the biomarkers in the sample comprise hemoglobin, and the predetermined condition comprises colorectal cancer (CRC).

11. 1. A method for performing colorectal cancer (CRC) screening, comprising: identifying a location of the system relative to the sample, the system comprising a phone or tablet with a screen on the front side and a camera positioned above the screen, the sample comprising stool, saliva, sweat, blood, urine, skin or a combination thereof; instructing a user holding the phone or tablet to move the phone or tablet to a predetermined position according to the identified position, wherein moving the phone or tablet changes the distance between the front side and the sample, changes the angle between the front side and the sample, or both; illuminating the sample with the light of a first wavelength from the screen while the phone or tablet is in the predetermined position; taking a first image of the sample with the camera while the phone or tablet is in the predetermined position and the sample is illuminated with the light at the first wavelength; illuminating the sample with the light at a second wavelength from the screen while the phone or tablet is in the predetermined position, the sample being illuminated with the light at the second wavelength after the first image is taken, the first and second wavelengths being different; taking a second image of the sample with the camera while the phone or tablet is in the predetermined position and the sample is illuminated with the light at the second wavelength; combining the first and second images to generate a multispectral image; measuring spectral characteristics at each pixel in the multispectral image using a spectral processing algorithm executed on the system; determining a concentration of a biomarker in the sample based at least in part on the spectral signature, the biomarker comprising hemoglobin, bilirubin, calprotectin, albumin, fatty acids, hydrogen sulfide, or a combination thereof; identifying the individual from whom the sample was taken as being at increased risk for a predetermined condition based at least in part on the concentration of the biomarker; A method for providing the above.

12. 12. The method of claim 11, wherein the sample comprises stool, the biomarker in the sample comprises hemoglobin, and the predetermined condition comprises colorectal cancer (CRC).

13. 12. The method of claim 11, wherein the sample is located below the surface of the water in a toilet.

14. 12. The method of claim 11, further comprising displaying on the screen the first image, the second image, the multispectral image, the spectral features, the biomarkers, the concentrations of the biomarkers, or a combination thereof.

15. 12. The method of claim 11, further comprising providing instructions to seek further testing or medical treatment in response to the concentration of the biomarker exceeding a predetermined threshold.

16. 1. A system for conducting screening, comprising: a screen configured to emit light to illuminate a sample, the screen configured to vary the wavelength of the light between a first wavelength and a second wavelength, the first and second wavelengths being different; a camera configured to take a first image of the sample while the sample is illuminated with the light at the first wavelength and to take a second image of the sample while the sample is illuminated with the light at the second wavelength; A computing system combining the first and second images to generate a multispectral image; measuring spectral features within the multispectral image; and identifying the person from whom the sample was taken as being at increased risk for a predetermined condition based at least in part on the spectral signature; a computing system configured to: A system comprising:

17. 17. The system of claim 16, comprising a phone or tablet with the screen on the front side and the camera located above the screen.

18. 20. The system of claim 17, wherein the computing system is also configured to identify a concentration of a biomarker in the sample based at least in part on the spectral features, and wherein the identification that the person from whom the sample was taken is at increased risk for the predetermined condition is based at least in part on the concentration of the biomarker.

19. 20. The system of claim 18, wherein the sample comprises underwater feces in a toilet, the biomarkers in the sample comprise hemoglobin, and the predetermined condition comprises colorectal cancer (CRC).

20. 20. The system of claim 19, wherein the screen is further configured to display the first image, the second image, the multispectral image, the spectral features, the biomarkers, the concentrations of the biomarkers, or a combination thereof after the sample is illuminated and the first and second images are taken.

Images