Methods and apparatus to detect bleeding vessels

Abstract

According to one aspect, a processor device in communication with an endoscopic device obtains a spectrum image of bleeding in an upper gastrointestinal (GI) area of a patient. A filter is applied to the spectrum image to generate a pre-enhanced image. The filter enhances the spectrum image at one or more light wavelengths in the light spectrum. The pre-enhanced image is analyzed to identify an area of interest that represents a portion of the upper Gl area with an active bleed. A contrast enhancement technique is applied to the area of interest in the pre-enhanced image to generate an enhanced contrast image. Spatial filters are applied to the enhanced contrast image to produce a final colorized image with defined blood vessels in the upper Gl area of the patient.

We claim: 
     
         1 - 20 . (canceled) 
     
     
         21 . A computer-implemented method for enhancing images, the method comprising:
 receiving a spectrum image of a target area of a patient, the target area including a plurality of blood vessels, wherein one or more of the plurality of blood vessels are bleeding vessels causing pooling blood to be viewed in the spectrum image;   generating a pre-enhanced image based on a first filter and a second filter applied to the spectrum image, wherein the first filter enhances light absorption at a first wavelength, wherein the second filter enhances light absorption at a second wavelength different from the first wavelength, and wherein the first filter and the second filter provide image differentiation of the bleeding vessels from the pooling blood in the pre-enhanced image;   generating an enhanced contrast image by applying a contrast enhancement technique to the pre-enhanced image; and   generating a final colorized image by applying one or more spatial filters to the enhanced contrast image.   
     
     
         22 . The computer-implemented method of  claim 21 , wherein each of the first wavelength and the second wavelength are wavelengths at which a light absorption rate of oxygenated hemoglobin differs from a light absorption rate of deoxygenated hemoglobin to provide the image differentiation of the bleeding vessels from the pooling blood based on a decreased oxygenated hemoglobin in the pooling blood. 
     
     
         23 . The computer-implemented method of  claim 22 , wherein the first filter enhances light absorption in the spectrum image at the first wavelength at which deoxygenated hemoglobin has a lower absorption factor than oxygenated hemoglobin. 
     
     
         24 . The computer-implemented method of  claim 22 , wherein the second filter enhances light absorption in the spectrum image at the second wavelength at which oxygenated hemoglobin has a lower absorption factor than deoxygenated hemoglobin. 
     
     
         25 . The computer-implemented method of  claim 21 , wherein the first filter is a 490 nanometer (nm) filter, and wherein the second filter is a filter in a range of 630 nm to 640 nm. 
     
     
         26 . The computer-implemented method of  claim 25 , wherein the second filter is a 630 nm filter, and wherein generating the pre-enhanced image comprises:
 generating the pre-enhanced image further based on a third filter, wherein the third filter is a 640 nm filter.   
     
     
         27 . The computer-implemented method of  claim 21 , wherein generating the enhanced contrast image comprises:
 applying a trained classifier to the pre-enhanced image, wherein the trained classifier is configured to classify the bleeding vessels from the pooling blood; and   applying a first artificial color to the bleeding vessels classified by the trained classifier and a second artificial color different from the first artificial color to the pooling blood classified by the trained classifier.   
     
     
         28 . The computer-implemented method of  claim 21 , wherein generating the enhanced contrast image comprises:
 applying a histogram contrast enhancement (HCE) algorithm to the pre-enhanced image.   
     
     
         29 . The computer-implemented method of  claim 21 , wherein applying the one or more spatial filters comprises:
 applying one or more of an averaging filter, a smoothing filter, a zero-padding filter, a symmetrical filter, a circular filter, a low pass filter, or a high pass filter.   
     
     
         30 . The computer-implemented method of  claim 21 , wherein the final colorized image represents a recolorization of the enhanced contrast image. 
     
     
         31 . The computer-implemented method of  claim 21 , further comprising:
 prior to generating the enhanced contrast image, analyzing the pre-enhanced image to identify an area of interest, wherein the area of interest includes at least a portion of the target area including the bleeding vessels.   
     
     
         32 . The computer-implemented method of  claim 31 , wherein the contrast enhancement technique is applied to the pre-enhanced image to provide further image differentiations within the area of interest beyond the bleeding vessels from the pooling blood. 
     
     
         33 . A computer-implemented method for enhancing medical images, the method comprising:
 receiving a spectrum image of a target area of a patient, the target area including a plurality of blood vessels, wherein one or more of the plurality of blood vessels are bleeding vessels that cause pooling blood having decreased oxygenated hemoglobin;   generating a pre-enhanced image that defines the bleeding vessels from the pooling blood based on a first filter and a second filter applied to the spectrum image, wherein the first filter enhances light absorption in the spectrum image at a first wavelength at which deoxygenated hemoglobin has a known lower absorption factor than oxygenated hemoglobin, and the second filter enhances light absorption in the spectrum image at a second wavelength at which oxygenated hemoglobin has a known lower absorption factor than deoxygenated hemoglobin;   generating an enhanced contrast image by applying a contrast enhancement technique to the pre-enhanced image; and   generating a final colorized image by applying one or more spatial filters to the enhanced contrast image.   
     
     
         34 . The computer-implemented method of  claim 33 , wherein the first wavelength is 490 nanometers (nm), and wherein the second wavelength is in a range of 630 nm to 640 nm. 
     
     
         35 . The computer-implemented method of  claim 33 , wherein generating the enhanced contrast image comprises:
 applying a trained classifier to the pre-enhanced image, wherein the trained classifier is configured to classify the bleeding vessels from the pooling blood; and   applying a first artificial color to the bleeding vessels classified by the trained classifier and a second artificial color different from the first artificial color to the pooling blood classified by the trained classifier.   
     
     
         36 . The computer-implemented method of  claim 33 , wherein generating the enhanced contrast image comprises:
 applying a histogram contrast enhancement (HCE) algorithm to the pre-enhanced image.   
     
     
         37 . The computer-implemented method of  claim 33 , wherein applying the one or more spatial filters comprises:
 applying one or more of an averaging filter, a smoothing filter, a zero-padding filter, a symmetrical filter, a circular filter, a low pass filter, or a high pass filter.   
     
     
         38 . The computer-implemented method of  claim 34 , wherein generating the enhanced contrast image further comprises:
 prior to generating the enhanced contrast image, analyzing the pre-enhanced image to identify an area of interest, wherein the area of interest includes at least a portion of the target area including the bleeding vessels; and   applying the contrast enhancement technique to the area of interest to provide further image differentiations within the area of interest beyond the bleeding vessels from the pooling blood.   
     
     
         39 . A computer-implemented method for enhancing medical images, the method comprising:
 receiving a spectrum image of a target area of a patient, the target area including a plurality of blood vessels obfuscated in the spectrum image;   generating a pre-enhanced image that defines the plurality of blood vessels based on a first filter and a second filter applied to the spectrum image, wherein the first filter is a 490 nanometer (nm) filter and the second filter is a filter in a range of 630 nm to 640 nm;   generating an enhanced contrast image by applying a contrast enhancement technique to the pre-enhanced image; and   generating a final colorized image by applying one or more spatial filters to the enhanced contrast image.   
     
     
         40 . The computer-implemented method of  claim 39 , wherein generating the enhanced contrast image comprises:
 applying the contrast enhancement technique to an identified area of interest in the pre-enhanced image to provide further image differentiations beyond the plurality of blood vessels defined by the pre-enhanced image.