Cancer Detection Systems and Methods

Abstract

A piece of medical information, e.g., a medical image of tissue, may be received for processing and analysis on a computing device or system. A region of the medical image may be analyzed to determine a presence of one or more contours in the region. One or more properties of the one or more contours may be extracted, where the one or more properties are inputted into a first algorithm to determine an indication of cancer for the region. The indication of cancer may be inputted into a second algorithm to generate a cancer score for the region.

What is claimed is: 
     
         1 . A computer-implemented method for cancer detection and quantification comprising:
 receiving a medical image through a communications interface of a computing device over a data network;   analyzing the medical image, with a processor of the computing device, to determine a first subset of contours in the medical image satisfying one or more criterion;   analyzing, with the processor, one or more geometric attributes and one or more contrast attributes of contours included in the first subset of contours to identify a second subset of contours based upon contours satisfying one or more predetermined geometric and contrast attributes;   selecting, with the processor, a third subset of contours from the second subset of contours that corresponds to potential calcifications, the third subset of contours selected based on contours within the second subset satisfying first calcification criteria;   ranking, with the processor, contours included in the third subset of contours based on a selection metric, the selection metric accounting for a combination of contrast and intensity;   grouping, with the processor, contours included in the third subset of contours into nested structures;   selecting, with the processor, calcifications from the nested structures satisfying second calcification criteria;   grouping, with the processor, the selected calcifications into clusters based on one or more of neighboring calcifications and a spatial cluster scale;   classifying, with the processor, the clusters as benign or possible cancer by performing one or more of: a regression analysis on calcifications within the clusters, edge detection, a density analysis of the clusters, and a circularity analysis of the clusters; and   scoring, with the processor, the clusters using an analytic function of geometric and contrast properties of the calcifications within each cluster, and spatial arrangements of the calcifications within each cluster.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the medical image includes one or more of an x-ray image, a computerized tomography (CT) scan, a magnetic resonance (MRI) image, and an ultrasound image. 
     
     
         3 . The computer-implemented method of any of  claims 1  to  2 , further comprising extracting, with the processor, tagged data from the medical image, wherein the medical image is included in a computer file. 
     
     
         4 . The computer-implemented method of  claim 3 , wherein the tagged data includes one or more of a side, a pixel spacing, an orientation, a protocol, and a date. 
     
     
         5 . The computer-implemented method of any of  claims 3  to  4 , wherein the tagged data is included in a Digital Imaging and Communications in Medicine (DICOM) header. 
     
     
         6 . The computer-implemented method of any of  claims 1  to  5 , further comprising converting, with the processor, the medical image to a 4-byte real array of intensities for contouring. 
     
     
         7 . The computer-implemented method of any of  claims 1  to  6 , further comprising selecting, with the processor, intensity levels for determining contours in the medical image. 
     
     
         8 . The computer-implemented method of any of  claims 1  to  7 , wherein the one or more criterion includes that each contour in the first subset of contours is (i) closed and (ii) includes a contour value larger than a surrounding area external to the contour. 
     
     
         9 . The computer-implemented method of any of  claims 1  to  8 , wherein contours not satisfying the one or more criterion are discarded. 
     
     
         10 . The computer-implemented method of any of  claims 1  to  9 , wherein the one or more geometric attributes of contours includes at least one of: a centroid, an area, a perimeter, a circle ratio, and an interior flag. 
     
     
         11 . The computer-implemented method of any of  claims 1  to  10 , wherein the one or more contrast attributes of contours includes at least one of: an intensity, an inward contrast, an outward contrast, and a gradient scale. 
     
     
         12 . The computer-implemented method of any of  claims 1  to  11 , further comprising detecting, with the processor, an object in the image for exclusion from further analysis. 
     
     
         13 . The computer-implemented method of  claim 12 , wherein the object is an external object. 
     
     
         14 . The computer-implemented method of  claim 13 , wherein the object is detected through the object having at least one of: an area greater than a predetermined area, an intensity greater than a predetermined intensity, and a circle ratio greater than a predetermined circle ratio. 
     
     
         15 . The computer-implemented method of any of  claims 1  to  14 , wherein selecting the third subset of contours includes excluding contours located within a predetermined distance from at least one of an edge of the medical image and an edge of tissue. 
     
     
         16 . The computer-implemented method of any of  claims 1  to  15 , wherein the first calcification criteria includes contours having a predetermined area and a predetermined gradient scale. 
     
     
         17 . The computer-implemented method of  claim 16 , wherein the predetermined area is between 0.003 mm 2  and 800 mm 2  and the predetermined gradient scale is less than 1.3 mm. 
     
     
         18 . The computer-implemented method of any of  claims 1  to  17 , wherein the first calcification criteria includes contours having a predetermined intensity, a predetermined circle ratio, a predetermined inward contrast, and a predetermined outward contrast. 
     
     
         19 . The computer-implemented method of  claim 18 , wherein the predetermined intensity is greater than 0.67 times a maximum intensity, the predetermined circle ratio is greater than 0.65, the predetermined inward contrast is greater than 1.06, and the predetermined outward contrast is greater than 1.22. 
     
     
         20 . The computer-implemented method of any of  claims 1  to  19 , wherein the first calcification criteria includes contours having a predetermined area, a predetermined circle ratio, and at least one of a predetermined inward contrast and a predetermined gradient scale. 
     
     
         21 . The computer-implemented method of  claim 20 , wherein the predetermined area is less than 0.30 mm 2 , the predetermined circle ratio is greater than 0.65, the predetermined inward contrast is greater than 1.04, and the predetermined gradient scale is greater than 0.3 mm. 
     
     
         22 . The computer-implemented method of any of  claims 1  to  21 , wherein the first calcification criteria includes contours having a predetermined area, a predetermined circle ratio, and a predetermined intensity. 
     
     
         23 . The computer-implemented method of any of  claims 1  to  22 , further comprising saving the third subset of contours in a memory of the computing device. 
     
     
         24 . The computer-implemented method of any of  claims 1  to  23 , further comprising identifying, with the processor, calcifications for each nested structure based on at least one of: a contour derivative and a grouping parameter computed for each nested structure. 
     
     
         25 . The computer-implemented method of  claim 24 , wherein the contour derivative measures how rapidly intensity varies across a nested structure. 
     
     
         26 . The computer-implemented method of any of  claims 1  to  25 , further comprising identifying, with the processor, outer contours in each nested structure representing a contour shape and inner contours in each nested structure providing data on internal gradients. 
     
     
         27 . The computer-implemented method of any of  claims 1  to  26 , wherein the second calcification criteria includes a threshold on a contour derivate and a threshold on a grouping parameter. 
     
     
         28 . The computer-implemented method of any of  claims 1  to  27 , further comprising computing cluster properties with the processor. 
     
     
         29 . The computer-implemented method of  claim 28 , wherein the cluster properties include one or more of: a cluster centroid, a cluster half-length, a cluster half-width, an aspect ratio, a principal axis, and a packing fraction. 
     
     
         30 . A computer program product comprising non-transitory computer executable code embodied in a non-transitory computer readable medium that, when executing on one or more computing devices, performs the steps of:
 receiving a medical image through a communications interface of a computing device over a data network;   analyzing the medical image to determine a first subset of contours in the medical image satisfying one or more criterion;   analyzing one or more geometric attributes and one or more contrast attributes of contours included in the first subset of contours to identify a second subset of contours based upon contours satisfying one or more predetermined geometric and contrast attributes;   selecting a third subset of contours from the second subset of contours that corresponds to potential calcifications, the third subset selected based on contours within the second subset satisfying first calcification criteria;   ranking contours included in the third subset of contours based on a selection metric, the selection metric accounting for a combination of contrast and intensity;   grouping the contours included in the third subset of contours into nested structures;   selecting calcifications from the nested structures satisfying second calcification criteria;   grouping the selected calcifications into clusters based on one or more of neighboring calcifications and a spatial cluster scale;   classifying the clusters as benign or possible cancer by performing one or more of: a regression analysis on calcifications within the clusters, edge detection, a density analysis of the clusters, and a circularity analysis of the clusters; and   scoring the clusters using an analytic function of: geometric and contrast properties of the calcifications within each cluster, and spatial arrangements of the calcifications within each cluster.   
     
     
         31 . A system comprising:
 a computing device including a network interface for communications over a data network; and   a cancer score engine having a processor and a memory, the cancer score engine including a network interface for communications over the data network, the cancer score engine configured to receive a medical image from the computing device, the memory configured to store the medical image, and the processor configured to analyze the medical image, generate a cancer score for the medical image, and transmit the cancer score to the computing device for display on a user interface thereof, wherein analysis of the medical image comprises:
 determining a first subset of contours in the medical image satisfying one or more criterion; 
 analyzing one or more geometric attributes and one or more contrast attributes of contours included in the first subset of contours to identify a second subset of contours based upon contours satisfying one or more predetermined geometric and contrast attributes; 
 selecting a third subset of contours from the second subset of contours that corresponds to potential calcifications, the third subset selected based on contours within the second subset satisfying first calcification criteria; 
 ranking contours included in the third subset of contours based on a selection metric, the selection metric accounting for a combination of contrast and intensity; 
 grouping the contours included in the third subset of contours into nested structures; 
 selecting calcifications from the nested structures satisfying second calcification criteria; 
 grouping the selected calcifications into clusters based on one or more of neighboring calcifications and a spatial cluster scale; 
 classifying the clusters as benign or possible cancer by performing one or more of: a regression analysis on calcifications within the clusters, edge detection, a density analysis of the clusters, and a circularity analysis of the clusters; and 
 scoring the clusters using an analytic function to generate the cancer score. 
   
     
     
         32 . A computer-implemented method comprising:
 receiving one or more pieces of medical information for processing and analysis on a computing device, the one or more pieces of medical information including a medical image of tissue;   analyzing, with a processor of the computing device, a region of the medical image to determine a presence of one or more contours in the region;   extracting, with the processor, one or more properties of the one or more contours;   inputting, with the processor, the one or more properties into a first algorithm to determine an indication of cancer for the region;   inputting, with the processor, the indication of cancer into a second algorithm to generate a cancer score for the region; and   generating the cancer score for the region.