Camera-based hemoglobin detection

Abstract

A method for detecting a molecule in a sample includes applying a first filter to an image at a first wavelength. The method also includes applying a second filter to the image at a second wavelength. The method also includes applying a third filter to the image at a third wavelength. The first, second and third wavelengths are within a predetermined wavelength range, and the first, second and third wavelengths are different from one another. The method also includes detecting a spectral signature of the molecule in the sample in the image after the first, second and third filters have been applied to the image. The method also includes determining whether the molecule is present in the sample based at least in part on the detected spectral signature.

Description

[[Technical Field]]

[0001] The present disclosure generally relates to systems and methods for detecting molecules in a sample. More specifically, the present disclosure relates to systems and methods for camera-based (e.g., spectrum-based) hemoglobin detection in fecal samples. [[Background Art]]

[0002] Colonoscopy is an endoscopic procedure commonly used for screening colorectal cancer or detecting other abnormalities in the colon and rectum. In colonoscopy, a long, flexible tube (i.e., a colonoscope) is inserted into the rectum. A small video camera is attached to the distal end of the tube, allowing a physician to observe the interior of the entire colon. If necessary, polyps or other types of abnormal tissue can also be resected through the scope during colonoscopy. It is also possible to collect tissue samples (e.g., biopsies) during colonoscopy. However, it would be convenient to have alternative simple and non-invasive systems and methods for colorectal cancer screening. [[Summary of the Invention]] [[Problem to be Solved by the Invention]]

[0003] According to one aspect of the present disclosure, a method for detecting a molecule in a sample is disclosed. The method comprises applying a first filter to an image at a first wavelength. The method also comprises applying a second filter to the image at a second wavelength. The method further comprises applying a third filter to the image at a third wavelength. The first, second, and third wavelengths are within a predetermined wavelength range, and the first, second, and third wavelengths are different from each other. The method also comprises detecting a spectral signature of the molecule in the sample in the image after the first, second, and third filters are applied to the image. The method further comprises determining whether the molecule is present in the sample based at least in part on the detected spectral signature.

[0004] A method for detecting hemoglobin in a stool sample is also disclosed. The method includes acquiring an image of the stool sample with a camera. The method also includes applying a first band-transmittance filter at a first wavelength to the image as the image is acquired. The method also includes applying a second band-transmittance filter at a second wavelength to the image as the image is acquired. The method also includes applying a third band-transmittance filter at a third wavelength to the image as the image is acquired. The first, second, and third wavelengths are between 450 nm and 690 nm. The third wavelength is between the first and second wavelengths. The method also includes detecting the spectral signature of hemoglobin in the stool sample in the image after the first, second, and third band-transmittance filters have been applied to the image. The spectral signature includes absorption characteristics. Detecting the spectral signature involves performing continuum removal on spectral signatures between 450 nm and 690 nm by removing the gradient from the spectral signature while preserving the absorption characteristics using linear interpolation. Performing continuum removal involves determining a first product of the weights and the absorption characteristic value at a first wavelength, determining a second product of the complement of the weights and the absorption characteristic value at a second wavelength, and determining the sum of the first and second products. Detecting the spectral signature also involves determining the bandwidth ratio of the absorption characteristics for each pixel in the image. The bandwidth ratio includes the ratio of the sum to the absorption characteristic value at a third wavelength. The method also involves summing the bandwidth ratios for the pixels in the image. The method also involves determining the presence of hemoglobin in the stool sample, at least in part, based on the summing of the bandwidth ratios.

[0005] A system for detecting molecules in a sample is also disclosed. The system includes a camera configured to capture an image of the sample. The system also includes a computing system. The computing system is configured to detect spectral signatures of molecules in the sample in the image after first, second, and third filters have been applied to the image. The computing system is also configured to determine whether or not molecules are present in the sample, at least in part, based on the detected spectral signatures. [Brief explanation of the drawing]

[0006] [Figure 1] This is a schematic diagram of a system for identifying molecules in a sample, according to one embodiment. [Figure 2] Figure 2A shows an image of a stool sample containing hemoglobin according to one embodiment. Figure 2B shows an image of a stool sample containing only stool (i.e., without hemoglobin) according to one embodiment. [Figure 3] This graph shows a sample of stool containing hemoglobin versus a sample of stool alone, according to one embodiment. [Figure 4] This graph shows the dose-response in hemoglobin detection as the hemoglobin concentration in stool increases, according to one embodiment. [Figure 5] This is a graph showing the reflectance versus wavelength of hemoglobin at multiple different concentrations according to one embodiment. [Figure 6] This is a graph showing the detection of spectral signatures in an image according to one embodiment. [Figure 7] A flowchart of a method for detecting molecules in a sample according to one embodiment is shown. [Modes for carrying out the invention]

[0007] Next, the subject matter currently disclosed will be described more fully below with reference to the accompanying drawings, which show some, though not all, embodiments of this disclosure. The same numbers refer to the same elements throughout. The subject matter currently disclosed can be embodied in many different forms and should not be construed as being limited to the embodiments described herein, but rather these embodiments are provided to satisfy the legal requirements to which this disclosure applies. Indeed, a person skilled in the art to which the subject matter of this disclosure relates, who has an interest in the teachings presented in the foregoing description and the accompanying drawings, will be able to imagine many variations and other embodiments of the subject matter of this disclosure described herein. Therefore, it should be understood that the subject matter disclosed is not limited to the specific embodiments disclosed, and that variations and other embodiments are intended to be included within the scope of the accompanying claims.

[0008] Figure 1 is a schematic diagram of a system 100 for identifying molecules in a sample according to one embodiment. The molecules may be hemoglobin, bilirubin, calprotectin, albumin, fatty acids, hydrogen sulfide, etc., or may include these. The sample may be stool, urine, saliva, another biological specimen, or a combination thereof, or may include these. Figure 2A shows image 200A of a stool sample 210A containing hemoglobin according to one embodiment, and Figure 2B shows image 200B of a stool sample 210B containing only stool (i.e., without hemoglobin) according to one embodiment.

[0009] System 100 may include a camera 110, a computing system 120, and an inspection device 130. In one embodiment, the camera 110, the computing system 120, the inspection device 130, or a combination thereof, may be housed together in a single device. For example, at least part of System 100 may include, be part of, or be connected to a smartphone, tablet, laptop, etc. The 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 contain molecules. As part of the capture of images 200A, 200B, one or more filters (e.g., three are shown: 112, 114, and 116) may be applied. In one embodiment, filters 112, 114, and 116 may be applied to the lens of the camera 110. For example, filters 112, 114, and 116 may be thin-film filters covering the lens of the camera 110, or may include thin-film filters. The membrane filters may be manually modified so that three images (one image per filter) are captured for a single sample. In another embodiment, filters 112, 114, and 116 may be incorporated (e.g., directly) into the CCD focal plane of the camera 110. In yet another embodiment, a Bayer pattern filter array may be used. In yet another embodiment, filters 112, 114, and 116 may be applied to images 200A and 200B by a computing system 120.

[0010] The computing system 120 may be configured to analyze images 200A and 200B to detect the presence and / or amount of molecules (e.g., hemoglobin) in a sample (e.g., stool). More specifically, the computing system 120 may be configured to detect molecular-specific spectral signatures to distinguish between samples containing molecules and samples without molecules. Figure 3 is a graph showing a sample 210A containing hemoglobin versus a sample 210B containing only stool, according to one embodiment. In one example, as the amount of molecules in the sample increases, the detectability of the molecules also increases dose-responsively. This is shown in Figure 4, a graph showing the dose-response in hemoglobin detection as the hemoglobin concentration in stool increases, according to one embodiment. More specifically, ratios of specific wavelength features and quantitative comparisons of these resulting values ​​across multiple types of calculations may be useful in distinguishing hemoglobin-containing samples from non-hemoglobin-containing samples.

[0011] The testing device 130 may be an immunochemical fecal test (FIT) device or other diagnostic tests / information, or may include such tests. The testing device 130 may test molecules (e.g., hemoglobin) in the sample (e.g., stool) before, simultaneously with, or after the camera 110 and computing system 120 attempt to detect the presence and / or quantity of molecules in the sample. For example, the testing device 130 may be connected to the computing system 120 and configured to function as a secondary testing system for molecules after the camera 110 and computing system 120 have performed image-based detection.

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

[0013] As will be described in more detail below, the computing system 120 may implement a spectral processing algorithm for images 200A, 200B to detect the presence of a spectral signature 510 of a molecule (e.g., hemoglobin). To achieve this, the algorithm may utilize spectral continuum removal and / or bandwidth ratio analysis. Continuum removal may be performed by removing the gradient of the spectral signature 510 while preserving one or more spectral absorption characteristics 520A, 520B using linear interpolation. In this specification, spectral absorption characteristics refer to changes in the shape of the spectral curve. Continuum removal may be performed within a predetermined wavelength range.

[0014] After continuum removal is performed, the band ratio may then be determined for one or more of the absorption characteristics 520A and 520B to measure the ratio of absorption characteristics 520A and 520B, which indicates the amount of chemicals associated with absorption characteristics 520A and 520B present in the sample. In one embodiment, the reflectance value at point 520B may represent the numerator and the reflectance value at point 520A may be the denominator. The ratio (e.g., numerator / denominator) may be 1 or greater when it is positive (i.e., hemoglobin is present).

[0015] Figure 6 is a graph illustrating the detection of a spectral signature in an image according to one embodiment. Line 610 represents the measured spectrum (e.g., from spectral signature 510). Interpolation can be used to determine spectrum 620, which is a measure of the continuum (e.g., the overall shape) of the 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) spectral features (e.g., spectral absorption characteristics 520A, 520B). From the continuum-removed spectrum 630, the spectral depth can be determined using the bandwidth ratio, as shown along the dashed vertical line 640.

[0017] Figure 7 shows a flowchart of method 700 for detecting molecules in a sample according to one embodiment. An exemplary sequence of steps of method 700 is shown below, but 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 include acquiring one or more images of the sample, as in 702. For example, this may include acquiring an image 200A that includes the sample 210A. Image 200A may be acquired by camera 110.

[0019] Method 700 may also include applying one or more filters 112, 114, 116 to the image 200A, as at 704. As described above, the filters 112, 114, 116 may be applied in the camera 110 and / or by the computing system 120. The filters 112, 114, 116 may be, or may include, band-pass filters configured to transmit a predetermined wavelength range. As described above, in the case of 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 of the filters 112, 114, 116 may be configured to transmit different wavelengths. The first filter 112 may be configured to transmit a first wavelength, the second filter 114 may be configured to transmit a second wavelength, and the third filter 116 may be configured to transmit a third wavelength. The third wavelength may be between the first wavelength and the second wavelength. In one example, the first wavelength may be from about 639 nm to about 647 nm, the second wavelength may be from about 623 nm to about 631 nm, and the third wavelength may be from about 628 nm to about 636 nm. In another example, 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] Method 700 may also include detecting a spectral signature 510 in the image 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 200A. The spectral signature 510 may be unique to the molecule to be detected (e.g., hemoglobin). As described above, the spectral signature 510 may include one or more absorption characteristics 520A, 520B.

[0022] In one embodiment, detecting the spectral signature 510 may comprise performing continuum removal on the spectral signature 510, such as at 708. The continuum removal may be performed within a predetermined wavelength range. The continuum removal may be performed using linear interpolation to remove a slope from the spectral signature 510 while retaining an absorption characteristic (e.g., absorption characteristic 520A). In one example, performing continuum removal may comprise: w * r(λ1)+(1-w) * r(λ2)···Formula 1 where w represents a weight value, r(λ1) represents the spectral value of the absorption characteristic 520A at a first wavelength, and r(λ2) represents the spectral value of the absorption characteristic 520A at a second wavelength. 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 comprise determining a first product of the weight and the spectral value of the absorption characteristic 520A at the first wavelength, determining a second product of a complement of the weight and the spectral value of the absorption characteristic 520A at the second wavelength, and determining a sum of the first product and the second product.

[0024] Detecting the spectral signature 510 may also or alternatively comprise determining a band ratio of the absorption characteristic 520A in the spectral signature 510, such as at 610. The band ratio may be determined after the continuum removal has been performed. In one example, the band ratio may comprise: Band ratio=(w * r(λ1)+(1-w) * r(λ2)) / r(λ3)···Formula 2 where r(λ3) represents the spectral value of the absorption characteristic 520A at a third wavelength. In other words, the numerator of the band ratio may comprise the sum (from Formula 1), and the denominator of the band ratio may comprise the spectral value of the absorption characteristic 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 pixels (for example, the bandwidth ratio may be determined). For example, the spectral signature 510 may be detected for all pixels in the image 200A (for example, the bandwidth ratio may be determined).

[0026] Method 700 may also include aggregating bandwidth ratios for pixels in image 200A, as in 712. One or more techniques can be used to aggregate bandwidth ratios. For example, one technique may involve aggregating or counting the number of values ​​exceeding a certain threshold, and another technique may involve aggregating or counting values ​​across a specific spatial region. In one embodiment, one technique may be used when the concentration of molecules in the sample is below a predetermined concentration threshold, and the other technique may be used when the concentration of molecules in the sample exceeds a predetermined concentration threshold. In another embodiment, a combination of multiple techniques may be created to form a composite.

[0027] Method 700 may also include determining the presence of a molecule (e.g., hemoglobin) in sample 210A, as in 714. The determination of the presence of a molecule may be at least in part based on the detection of a spectral signature 510, the determination of a bandwidth ratio, the aggregation of bandwidth ratios, or a combination thereof. Method 700 may be capable of detecting a predetermined mass of a molecule (e.g., hemoglobin) in 1 gram of sample 210A (e.g., stool + hemoglobin). The predetermined mass may be about 5 micrograms to about 10 micrograms, or about 10 micrograms to about 20 micrograms, which is below the threshold used in conventional FIT tests in the United States (i.e., 20 micrograms of hemoglobin / gram stool).

[0028] Method 700 may also include determining the amount of molecules present in sample 210A, as in 716. Determining the amount of molecules present may be at least partially based on detection of spectral signatures 510, determination of bandwidth ratios, aggregation of bandwidth ratios, other mathematical approaches, or a combination thereof. In another embodiment, determining the amount of molecules present may be a function of bandwidth ratio scores from the pixels of the sample. The use of “function” can represent any algorithm that takes bandwidth ratio scores as input and generates a numerical value to be assigned to the sample.

[0029] Method 700 may also include confirming the presence of molecules (e.g., hemoglobin) in the sample 210A using the inspection device 130, as in 718. This may also, or alternatively, include determining the amount of molecules present in the sample 210A using the inspection device 130. 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 an image-based determination in step 714 and / or step 716.

[0030] In another embodiment, instead of using the testing device 130 (e.g., FIT testing), or in addition to it, additional diagnostic information about the patient may be obtained. For example, the patient's medical history or test data 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 in 720. The colonoscopy may be performed at least in part in accordance with the determination that a molecule is present (in 714), the determination of the amount of molecule present (in 716), the determination that a molecule is present (in 718), or a combination thereof.

[0032] While this disclosure is described in relation to its preferred embodiments, those skilled in the art will understand that additions, deletions, modifications, and substitutions not specifically described may be made without departing from the spirit and scope of this disclosure as defined in the appended claims.

Claims

1. A method for detecting molecules in a sample, A step of applying a first filter to an image at a first wavelength, A step of applying a second filter to the image at a second wavelength, A step of applying a third filter to the image at a third wavelength, wherein the first, second, and third wavelengths are within a predetermined wavelength range, and the first, second, and third wavelengths are different from each other. The first, second, and third filters are applied to the image, followed by the step of detecting the spectral signatures of molecules in the sample in the image. The process includes determining whether the molecule is present in the sample based at least partially on the detected spectral signature, The step of detecting the spectral signature is: The steps include performing continuum rejection on the spectral signature within the predetermined wavelength range, The steps include, after the continuum removal is performed, determining the bandwidth of the absorption characteristics of the spectral signature, and determining, at least partially, that the molecule is present in the sample, The step of performing the continuum removal is: Determining the first product of the weight and the value of the absorption characteristic at the first wavelength, Determining a second product of the complement of the weight and the value of the absorption characteristic at the second wavelength, A method comprising determining the sum of the first product and the second product.

2. A method according to claim 1, wherein the molecule comprises hemoglobin, the sample comprises a stool sample, and the spectral signature comprises a V-shaped portion or a W-shaped portion of the curve on a reflectance-to-wavelength graph.

3. The method of claim 2, wherein the step of determining whether or not the molecule is present includes the step of determining that the molecule is present, and the method further, A method comprising the step of confirming the presence of hemoglobin in the stool sample using an immunochemical fecal test (FIT).

4. The method according to claim 1, wherein the predetermined wavelength range is between 450 nm and 690 nm, and the third wavelength is between the first and second wavelengths.

5. A method according to claim 1, wherein the continuum removal is performed using linear interpolation to remove the gradient from the spectral signature while maintaining the absorption characteristics.

6. A method according to claim 1, wherein the bandwidth ratio includes the ratio of the sum to the value of the absorption characteristic at the third wavelength.

7. A method according to claim 1, wherein the bandwidth ratio is determined for each pixel in the image.

8. A method according to claim 7, further comprising the step of determining the amount of the molecule present in the sample based at least in part on the aggregation of the bandwidth ratios.

9. A method for detecting hemoglobin in a stool sample, The process involves capturing an image of the stool sample with a camera, The process includes applying a first band-transmission filter at a first wavelength to the image when the image is acquired, The process involves applying a second band-transmission filter at a second wavelength to the image when the image is captured, A step of applying a third band-transmission filter to the image at a third wavelength when the image is acquired, wherein the first, second, and third wavelengths are between 450 nm and 690 nm, and the third wavelength is between the first and second wavelengths. The first, second, and third band-transmission filters are applied to the image, and the step of detecting the spectral signature of the hemoglobin in the stool sample in the image is to be performed, wherein the spectral signature includes absorption characteristics, and the step of detecting the spectral signature is to be performed, The process includes the step of performing continuum removal on the spectral signature between 450 nm and 690 nm by removing the gradient from the spectral signature while maintaining the absorption characteristics using linear interpolation, wherein the step of performing continuum removal is: Determining the first product of the weight and the value of the absorption characteristic at the first wavelength, Determining a second product of the complement of the weight and the value of the absorption characteristic at the second wavelength, This includes determining the sum of the first product and the second product, A step of determining the bandwidth ratio of the absorption characteristics for each pixel in the image, wherein the bandwidth ratio includes the ratio of the sum to the value of the absorption characteristics at the third wavelength, A step of summarizing the bandwidth ratio for pixels in the image, A method comprising the step of determining, at least partially, that the hemoglobin is present in the stool sample based on the aggregation of the bandwidth ratios.

10. A method according to claim 9, wherein the first wavelength is about 639 nm to about 647 nm, the second wavelength is about 623 nm to about 631 nm, and the third wavelength is about 628 nm to about 636 nm.

11. A method according to claim 9, wherein the spectral signature includes a V-shaped portion or a W-shaped portion of a curve on a reflectance-to-wavelength graph.

12. A method according to claim 9, further comprising the step of determining the amount of hemoglobin present in the stool sample based at least in part on the aggregation of the bandwidth ratios.

13. A method according to claim 9, further comprising the step of confirming the presence of hemoglobin in the stool sample using an immunochemical fecal test (FIT) after it has been determined that hemoglobin is present in the stool sample.

14. A system for detecting molecules in a sample, A camera configured to capture an image of the aforementioned sample, A computing system, After the first, second, and third filters are applied to the image, the spectral signatures of molecules in the sample in the image are detected. The system includes a computing system configured to determine whether the molecule is present in the sample, based at least partially on the detected spectral signature. Detecting the spectral signature means Performing continuum rejection on the spectral signature within a predetermined wavelength range, After the continuum removal is performed, the band ratio of the absorption characteristics of the spectral signature is determined, wherein the molecule is determined to be present in the sample, at least partially, based on the band ratio. Performing the aforementioned continuum removal means Determining the first product of the weight and the value of the absorption characteristic of the first filter at the wavelength, Determining the second product of the complement of the weight and the value of the absorption characteristic of the second filter at the wavelength, A system that includes determining the sum of the first product and the second product.

15. The system according to claim 14, wherein the first, second, and third filters are applied to the lens of the camera before the image is captured, and the wavelength of the third filter is between the wavelengths of the first and second filters.

16. The system according to claim 14, wherein the first, second, and third filters are applied by the computing system after the image has been acquired, and the wavelength of the third filter is between the wavelengths of the first and second filters.

17. A system according to claim 14, wherein the molecule comprises hemoglobin, the sample comprises a stool sample, and the computing system further comprises an immunochemical fecal test (FIT) configured to confirm the presence of hemoglobin in the stool sample after determining that hemoglobin is present in the stool sample.

Images