Method for generating quantitative data from medical imaging data

Abstract

A method of generating quantitative parameters of lesions in a visceral organ and of the pancreaticobiliary duct from volumetric medical imaging scan data is described, wherein the scan shows all or part of the visceral organ. The method comprises: locating a location of at least one lesion in a visceral organ on medical imaging scan data; segmenting the at least one detected lesion and determining one or more quantitative structural parameters of the at least one segmented lesion; performing segmentation on the volume of the medical imaging scan data to identify a tubular catheter in a visceral organ within the volume of the medical imaging scan; calculating, for at least one segmented tubular catheter within the volume of medical imaging scan data, at least one set of quantitative structural parameters along at least one direction of the length of the tubular catheter; and generating at least one set of quantitative structural parameters of the at least one segmented tubular catheter. An apparatus for performing the method is also described.

Description

Technical Field

[0001] This invention relates to the analysis of medical scanning imaging data. In particular, it relates to the analysis of medical scanning imaging data to assess cystic lesions in visceral organs and the pancreas and bile ducts. Background Technology

[0002] Cystic lesions, particularly pancreatic cystic lesions, are common incidental findings during abdominal imaging. Most cystic lesions remain asymptomatic and benign throughout a patient's life. However, a small percentage will become malignant and develop into pancreatic cancer. Given that pancreatic cancer is often only detected at a late stage with a very poor prognosis, the ability to monitor incidentally detected cystic lesions offers the opportunity to diagnose pancreatic cancer early, ideally even before it becomes malignant. This early diagnosis can open the door to effective surgical treatments that would be impossible in later stages of the disease. The remaining challenge is to differentiate cystic lesions requiring such intervention from benign lesions.

[0003] Because of the large number of lesions detected, accurate identification of benign and malignant pancreatic lesions is particularly important. More than 2% of the population and more than 20% of those over 70 years of age have asymptomatic pancreatic cystic lesions, resulting in the incidental detection of more than 800,000 cystic lesions in the United States each year. As previously mentioned, these lesions can serve as precursors to pancreatic cancer and therefore require surveillance. However, the majority will remain completely benign, making the identification of rare, high-risk lesions crucial. The confusion surrounding pancreatic cystic lesions leads to significant overtreatment and surveillance, costing an estimated $5.3 billion annually in the United States.

[0004] Pancreatic cystic lesions exhibit good image contrast on T2-weighted magnetic resonance imaging (MRI), therefore current monitoring protocols rely on non-invasive MRI and magnetic resonance cholangiopancreatography (MRCP) to assess the lesions. Figure 1 shows a schematic diagram of a human subject, illustrating the location of various organs, including parts of the digestive system, liver, gallbladder, and pancreas. MRI scans using MRCP sequences are recommended in guidelines and are commonly used for monitoring patient health. Figure 2 MRI images of this region from human subjects are shown. MRCP is an MRI technique used for imaging the bile ducts and pancreatic ducts. Pancreatic cystic lesions also exhibit high contrast in MRCP images. When monitoring pancreatic cystic lesions, MRCP images are used to: manually assess the size of the pancreatic duct and pancreatic lesion, and qualitatively assess the interaction between the lesion and the pancreatic duct.

[0005] There is a known method for the quantitative measurement of the bile duct and pancreatic duct. This method is described in EP3443533B and... Figure 3 As shown in the image. Figure 3 As shown, known methods include standardized protocols for image acquisition, tubular enhancement and segmentation, quantitative biliary tree models, and metrics for determining the entire tree and individual ducts. This method forms the basis of an existing product known as MRCP+. Figure 4(a) is an example report showing MRCP analysis results for healthy subjects. Figure 4(b) is an example report showing MRCP analysis results for subjects with chronic pancreatitis. However, this existing method cannot measure pancreatic lesions or the interaction of pancreatic lesions with any ducts.

[0006] Figures 4(a) and 4(b) show the MRCP+ models and corresponding reports used to quantify the pancreatic ducts in healthy volunteers and subjects with chronic pancreatitis. As shown, no stenosis or dilatation was detected in healthy subjects, but multiple stenosis and dilatation were detected in subjects with chronic pancreatitis.

[0007] Clinical guidelines recommend that radiologists manually measure features on medical scan images (such as cystic lesions or the maximum diameter of the pancreatic duct) and qualitatively assess concerning features (such as mural nodules, the connection of cystic lesions to the pancreatic duct, and changes in lesions over time). These assessments are then used in a binary classification to stratify the risk of the lesions.

[0008] Because current clinical assessments are performed manually and rely heavily on subjective characteristics, there are considerable differences between different readers and even among the same reader at different time points.

[0009] Furthermore, these subjective assessments struggle to differentiate between benign lesions, precancerous lesions, and malignant lesions. The variability in assessments and the difficulty in identifying high-risk cases mean that many patients are either diagnosed at an advanced stage or overtreated—most patients with pancreatic cystic lesions who undergo surgery do not show any significant developmental abnormalities or malignancies on the histology after resection.

[0010] Academic societies such as the COMP Cyst Society have made some progress in risk stratification of lesions, and the COMP Cyst Society has developed methods based on a combination of genetic markers obtained through invasive assessment of cystic lesions and standard clinical evaluation. However, these methods still only include manual qualitative assessments from imaging data.

[0011] This invention utilizes a novel measurement of quantitative metrics from medical scan imaging data of visceral organs. This method can characterize the biophysical features of cystic lesions and their interactions with the pancreatic duct, common bile duct, and pancreatic parenchyma or other visceral ducts to enhance the stratification of a patient's current and future malignancy risk. Using these methods, we aim to improve the accuracy of cystic lesion assessment, reduce the time required to perform the assessment, and decrease operator variability compared to conventional methods. Summary of the Invention

[0012] A method for generating quantitative parameters of lesions and pancreatobiliary ducts in visceral organs from volumetric medical imaging scan data obtained from medical imaging scans of all or part of visceral organs. The method may include locating the position of at least one lesion and at least one pancreatobiliary duct within the visceral organ on the volumetric medical imaging scan data.

[0013] This method may include segmenting voxels within a medical imaging scan using volumetric medical imaging scan data to identify at least one lesion. The method may include segmenting at least one pancreatic or bile duct using volumetric medical imaging scan data. The voxel may contain viscera scanned by the medical imaging scan. Viscera within a voxel may include all or part of an internal organ.

[0014] The method may include determining at least one structural parameter of at least one segmented lesion. The method may include determining at least one structural parameter of at least one segmented pancreaticobiliary duct.

[0015] The pancreatobiliary ducts are typically tubular, and are therefore called tubular pancreatobiliary ducts. The pancreatobiliary ducts, particularly the bile ducts, pancreatic ducts, and their associated ductules and canialiculi, are involved in the transport of bile and pancreatic juice. Therefore, the process of segmenting and identifying the pancreatobiliary ducts involves segmenting and identifying the tubular ducts, especially the bile ducts, pancreatic ducts, and their associated ductules and canialiculi, within the volume of a medical imaging scan of the visceral organs.

[0016] The structural parameters of at least one segmented pancreatic duct may include quantitative parameters.

[0017] In a preferred embodiment of the invention, at least one group of structural parameters or quantitative structural parameters of the segmented pancreaticobiliary or tubular duct includes at least one parameter, which represents at least one of the following:

[0018] At least one location is the centerline of at least one divided pancreatic duct; at at least one location the centerline of at least one divided pancreatic duct faces;

[0019] The radius of at least one divided pancreatic duct at at least one location;

[0020] The diameter of at least one divided pancreatic duct at at least one location;

[0021] At least one location, the cross-section of at least one segmented pancreatic duct is oriented;

[0022] A cross-sectional profile of at least one segmented pancreaticobiliary duct at at least one location; an indication of the branching point of at least one segmented pancreaticobiliary duct at at least one location; and

[0023] Orientation of at least one branch point of the divided pancreatic biliary duct at at least one location.

[0024] Furthermore, preferably, the quantitative structural parameter set of at least one segmented visceral organ lesion includes at least one parameter, which represents at least one of the following:

[0025] The maximum diameter of the segmented lesion; the volume of the segmented lesion;

[0026] The presence of septa within the segmented lesions was confirmed;

[0027] Determining the shape of the segmented lesion; determining the contents of the segmented lesion.

[0028] The structural parameters of the at least one segmented lesion may include quantitative parameters, qualitative parameters, or both. In a preferred embodiment of the invention, the method further includes the step of determining the distance between the segmented duct and the segmented lesion using one or more of the structural parameters or quantitative structural parameters of the at least one segmented lesion and one or more of the structural parameters or quantitative structural parameters of the segmented pancreaticobiliary duct.

[0029] Preferably, the method further includes: dividing the identified segmented pancreaticobiliary duct into an upstream region of the lesion, a downstream region of the lesion, and a region interacting with the lesion, and determining the diameter and diameter variation of the pancreaticobiliary duct or tubular duct in each of these different regions.

[0030] In embodiments of the invention, the width profile of at least one of the upstream region, downstream region, and interaction region of the tubular pancreaticobiliary or tubular duct is used to determine additional measurements of the duct.

[0031] Furthermore, preferably, the method further includes detecting patterns of change within at least one segmented pancreatobiliary duct based on a median diameter estimate along the length of at least one segmented pancreatobiliary duct. Preferably, the method includes detecting patterns of change within at least one segmented pancreatobiliary duct by applying at least one pattern detection window to the median diameter estimate data.

[0032] In a preferred embodiment of the invention, the method includes detecting at least one of the following: narrowing; dilation; and beading.

[0033] Furthermore, preferably, at least one lesion is identified based on the maximum strength protection of the voxels constituting the volumetric medical imaging scan data.

[0034] Preferably, at least one lesion is identified by applying a threshold to the entire medical imaging scan data and examining the volume rendering of each voxel that exceeds the threshold.

[0035] Preferably, the internal organ is the pancreas.

[0036] In a preferred embodiment of the invention, the method further includes the step of performing tubular enhancement on volumetric medical imaging scan data to derive at least one tubularity measurement for each voxel within the volumetric medical imaging scan data; wherein tubular enhancement includes, for each voxel within the volume of the medical imaging scan data, calculating at least one metric that distinguishes tubular structures from other structures and calculating a tubularity measurement for the corresponding voxel based at least in part on the at least one metric.

[0037] Preferably, the method includes enhancement using tubular pancreatic and biliary structures based on multi-scale Hessian methods.

[0038] In a preferred embodiment of the invention, the volumetric medical imaging scan data includes imaging scan data obtained via magnetic resonance imaging modality.

[0039] Preferably, the method further includes determining the total number of pancreatic lesions shown in the volumetric imaging scan data.

[0040] This method can be systematically implemented. The method may include locating the position of at least one lesion in an internal organ on medical imaging scan data. The structural parameters of the segmented at least one pancreatic or bile duct may include quantitative parameters. The method may include segmenting at least one detected lesion and determining one or more quantitative structural parameters of the at least one segmented lesion.

[0041] This method may include performing segmentation on the volume of medical imaging scan data to identify tubular ducts involved in the transport of bile and pancreatic juice, particularly the bile duct, pancreatic duct, and their associated small ducts and microtubules, within the visceral organs of the medical imaging scan volume.

[0042] The method may include the process of: calculating at least one set of quantitative structural parameters at at least one location along the length of the segmented pancreaticobiliary duct within the volume of medical imaging scan data.

[0043] The method may include generating at least one set of quantitative structural parameters for at least one segmented tubular duct.

[0044] An image processing system may be arranged to generate quantitative parameters of lesions and pancreatic ducts in visceral organs from volumetric medical imaging scan data, wherein the scan shows all or part of the visceral organs; the image processing system includes at least one processing device arranged to perform the following operations: locating the position of at least one lesion in the visceral organ on the medical imaging scan data; segmenting at least one detected lesion and determining one or more quantitative structural parameters of the at least one segmented lesion; performing segmentation of the volume of the medical imaging scan data to identify tubular pancreatic ducts in the visceral organs within the volume of the medical imaging scan; calculating at least one set of quantitative structural parameters at at least one location along the length of the at least one segmented tubular pancreatic duct within the volume of the medical imaging scan data; and generating at least one set of quantitative structural parameters of the at least one segmented tubular pancreatic duct.

[0045] In an exemplary embodiment of the present invention, the quantitative structural parameter set of at least one segmented pancreaticobiliary duct includes at least one parameter, which represents at least one of the following:

[0046] At least one location is the centerline of at least one divided pancreatic duct; at at least one location the centerline of at least one divided pancreatic duct faces;

[0047] The radius of at least one divided pancreatic duct at at least one location;

[0048] The diameter of at least one divided pancreatic duct at at least one location;

[0049] At least one location, the cross-section of at least one segmented pancreatic duct is oriented;

[0050] A cross-sectional profile of at least one segmented pancreaticobiliary duct at at least one location; an indication of the branching point of at least one segmented pancreaticobiliary duct at at least one location; and

[0051] Orientation of at least one branch point of the divided pancreatic biliary duct at at least one location.

[0052] Furthermore, preferably, the quantitative structural parameter set of at least one segmented visceral organ lesion includes at least one parameter, which represents at least one of the following:

[0053] The maximum diameter of the segmented lesion; the volume of the segmented lesion;

[0054] The determination of the presence of septa within the segmented lesion; the determination of the shape of the segmented lesion; the determination of the contents of the segmented lesion.

[0055] In a preferred embodiment of the invention, the processing device is further configured to perform the following steps: determining the distance between the segmented pancreaticobiliary duct and the segmented lesion using one or more of the quantitative structural parameters of at least one segmented lesion and one or more of the quantitative structural parameters of the segmented pancreaticobiliary duct.

[0056] Preferably, the processing device is further configured to perform the following steps: dividing the identified segmented pancreaticobiliary duct into an upstream region of the lesion, a downstream region of the lesion, and a region interacting with the lesion, and determining the diameter and diameter variation of the pancreaticobiliary duct in each of these different regions.

[0057] Furthermore, preferably, the width profile of different regions of the tubular pancreatic duct is used to determine additional measurements of the duct.

[0058] Preferably, the processing device is further configured to perform the following steps: detecting patterns of change within at least one segmented pancreaticobiliary duct based on a median diameter estimate along the length of at least one segmented duct.

[0059] In a preferred embodiment of the invention, the processing device is further configured to perform the following steps: detecting patterns of change within at least one segmented pancreaticobiliary duct by applying at least one pattern detection window to median diameter estimation data.

[0060] Furthermore, preferably, the processing device is also configured to perform a step of detecting at least one of the following: narrowing; expansion; and beading.

[0061] Preferably, the processing device is further configured to identify at least one lesion by applying a threshold to the entirety of the medical imaging scan data and examining the volume rendering of each voxel exceeding the threshold.

[0062] Furthermore, preferably, the processing device is also configured to perform the following steps: performing tubular enhancement on volumetric medical imaging scan data to derive at least one tubularity measurement for each voxel within the volumetric medical imaging scan data; wherein tubular enhancement includes, for each voxel within the volume of the medical imaging scan data, calculating at least one metric that distinguishes tubular structures from other structures and calculating the tubularity measurement of the corresponding voxel based at least in part on the at least one metric.

[0063] In a preferred embodiment of the invention, any reference to the terms "duct" or "pancreatobiliary duct" refers to a duct involved in the transport of bile and pancreatic juice, particularly including all bile ducts, pancreatic ducts and their associated small ducts and microtubules. Attached Figure Description

[0064] Further details, aspects, and embodiments of the invention will be described by way of example only with reference to the accompanying drawings. In the drawings, the same reference numerals are used to identify similar or functionally similar elements. Elements in the drawings are for simplicity and clarity and are not necessarily drawn to scale.

[0065] Figure 1 is a schematic diagram showing various human organs (prior art).

[0066] Figure 2 The illustration shows a sample MRCP image (prior art) containing the bile duct, pancreas, and gallbladder.

[0067] Figure 3 The processing of quantitative imaging of the bile tree using MRCP+ is shown (prior art); Figure 4(a) is an example of a report showing the results of MRCP analysis of a healthy subject.

[0068] Figure 4(b) is an example of a report showing the MRCP analysis results of a subject with chronic pancreatitis.

[0069] Figures 5(a)-5(c) are examples of medical scan images used in embodiments of the present invention.

[0070] Figures 6(a)-6(d) show medical scan images and result data obtained at a troublesome stage in an embodiment of the method of the present invention.

[0071] Figure 7 The illustration shows a schematic diagram of measurements between a catheter and a cystic lesion according to an embodiment of the present invention.

[0072] Figure 8 This is a flowchart illustrating some steps in the method of the present invention;

[0073] Figure 9 This is a flowchart illustrating the steps involved in loading data for processing;

[0074] Figure 10 This is a flowchart illustrating the steps involved in segmenting cystic lesions.

[0075] Figure 11 This is a flowchart illustrating the steps for segmenting a catheter according to an embodiment of the present invention.

[0076] Figure 12 This is a flowchart illustrating steps for calculating one or more metrics according to an embodiment of the present invention.

[0077] Figure 13 This is a simplified flowchart illustrating an example of a method for detecting and quantifying stenosis and dilation within a ductal structure.

[0078] Figure 14A simplified block diagram illustrating an example of an image processing system. Detailed Implementation

[0079] The invention will now be described with reference to the accompanying drawings, which illustrate examples of methods and apparatus for generating quantitative data on the bile duct tree and pancreatic duct structures and / or information about cystic or malignant lesions from volumetric medical imaging scan data. However, it will be understood that the invention is not limited to the specific examples described herein and shown in the drawings.

[0080] Furthermore, since most of the embodiments shown in this invention can be implemented using electronic components and circuits known to those skilled in the art, the details will not be explained in more detail than those described below, in order to understand and recognize the fundamental concepts of this invention and to avoid obscuring or diverting the teachings of this invention.

[0081] Preferably, embodiments of the invention allow for the quantitative measurement of cystic or malignant lesions present in visceral organs, and their interactions with ducts within those organs, from medical scan images. In a preferred embodiment of the invention, the medical scan images are MRCP images. Preferably, the visceral organ is the pancreas, but the method can be used for other organs. Embodiments of the invention also allow for the combination of a range of automated quantitative measurements to create a risk score for visceral organ malignancies, which can aid in clinical decision-making. In embodiments of the invention, the method enhances the characterization of ducts within visceral organs, such as the pancreatic duct.

[0082] This invention can be used to predict the current and future malignancy risk of lesions in visceral organs based on one or more quantitative measurements of lesion-to-duct proximity, lesion size, and the impact of the lesion on one or more ducts in visceral organs. The invention includes measurements of the morphology of visceral organ ducts downstream and upstream of the lesion, as well as measurements of the morphology of ducts in the region closest to the lesion. Because cystic lesions in the head of visceral organs may also interact with the common bile duct, measurements of the morphology of the common bile duct are also performed in some embodiments of the invention.

[0083] Furthermore, embodiments of the present invention can also incorporate information from additional MRI sequences to characterize both the contents of the cyst and the solidity of internal organs. These may include T1 mapping (field normalization), proton density fat fraction (PDFF), and diffusion-weighted imaging (DWI).

[0084] Figures 5(a)-5(c) show the maximum intensity projections of MRCP coronal images, in which pancreatic cystic lesions are highlighted at positions 502, 504 and 506 on the images.

[0085] Figure 6 illustrates some steps for evaluating medical scan images of a patient's internal organs. Preferably, the organ is the pancreas, and medical scan images related to the pancreatic system are being evaluated. In a preferred embodiment of the invention, the medical scan images are MRI scans, and MRI data of a patient showing the pancreas are loaded into the software. At a minimum, this data must include MRCP scans. Scan data from additional 2D or 3D MRI sequences (e.g., T1, PDFF, or DWI data) may also be loaded.

[0086] First, in a preferred embodiment of the invention, the MRCP scan includes a scan of the pancreas, pancreatic lesions, common bile duct, and pancreatic duct. These are identified in the MRCP data, as shown in Figures 6(a) and 6(b). In Figure 6(a), the lesion can be identified on the maximum intensity projection (MIP) of the 3D MRI array from the MRCP data, and in Figure 6(b), the 3D coordinates are located. In a preferred embodiment of the invention, these selected regions of the scan are segmented. Segmentation of medical scan images, and indeed of digital images in general, is a known process of identifying objects and boundaries within an image and assigning labels to each pixel / voxel in the image so that pixels sharing certain characteristics are assigned the same label.

[0087] The simplest image segmentation method is called "thresholding," where grayscale digital image data is converted into binary image data based on a comparison of the grayscale data of each pixel / voxel with a threshold. Preferably, as shown in Figure 6(c), segmentation is performed using a local threshold automatically calculated at the location of the lesion and pancreaticobiliary tree.

[0088] In a preferred embodiment of the invention, a tubular enhancement algorithm that labels pixels based on the probability that they contain tubular structures is also incorporated into the segmentation of the pancreatic duct and common bile duct. In a preferred embodiment of the invention, the method further includes the step of performing tubular enhancement on volumetric medical imaging scan data to derive at least one tubeness measurement for each voxel within the volumetric medical imaging scan data; wherein tubular enhancement includes, for each voxel within the volume of the medical imaging scan data, calculating at least one metric that distinguishes tubular structures from other structures, and calculating the tubeness measurement of the corresponding voxel based at least in part on the at least one metric. More preferably, the method may include using multi-scale Hessian-based tubular bile duct structure enhancement.

[0089] As shown in Figure 6(d), one or more metrics of lesion morphology (e.g., maximum diameter, volume, sphericity, interaction with the pancreatic duct) are measured directly from the lesion segmentation mask. Catheter morphology is assessed by first measuring the centerlines of the duct segmentation mask and then calculating the duct diameter at each point along these centerlines. An interpolation-based approach is used to provide subpixel-scale diameter estimates. Based on these point-by-point diameter estimates, duct morphological metrics (e.g., median diameter, localized areas of diameter variation) are calculated.

[0090] If additional MRI parametric maps (e.g., T1, PDFF) are loaded into the software, the values ​​of these parametric maps are calculated within the parenchyma of the visceral organ, and, if requested by the user, the values ​​of these parametric maps are calculated within the lesion. These values ​​can be calculated in a user-defined region of interest or in an automatic segmentation mask of the visceral organ within the parametric map (e.g., via a convolutional neural network).

[0091] Finally, according to the present invention, one or more of the calculated metrics of the medical image and segmentation results, as well as any visualization, are output in a digital, machine-readable file format (e.g., JSON file, PDF, PNG, or other standard formats for images).

[0092] Figure 7 Different measurements that can be performed according to the method of the invention are shown. An increase in the diameter of the duct upstream of the lesion (upstream) may be an indicator of malignancy due to interaction with the lesion. In embodiments of the invention, the interaction between pancreatic cystic lesions and the main pancreatic duct (MPD) can indicate malignancy. The output of this function will enable the automated detection and quantification of phenomena that radiologists qualitatively assess, such as cystic lesions causing upstream dilation of the pancreatic duct or common bile duct—a known high-risk feature that may require surgical resection.

[0093] Various measurements that can be obtained by the methods of the present invention include, but are not limited to: measurements of lesion morphology in visceral organs (e.g., maximum diameter of the lesion); detection of one or more interactions between the lesion and the MPD / common bile duct (CBD); measurements of MPD / CBD morphology (median diameter, stenosis, dilation); shape of the lesion; detection of septa within the lesion; number of septa present within the lesion; number of lesions present (monocytic, oligocystic, multicystic); contents of the lesion; changes in MRI signal detected in the pancreatic parenchyma between the lesion and the duct; and changes in MRI signal detected in distant regions of the pancreatic parenchyma away from the lesion.

[0094] Figure 8A schematic view of the steps of an example embodiment of a method 900 for analyzing medical scan images is shown. In a preferred embodiment of the invention, the medical scan images are images obtained via magnetic resonance imaging modality. In step 902, data for analysis is loaded. Next is step 904, segmentation of lesions in internal organs shown in the scan data. (The following...) Figure 11 The steps for segmenting lesions are explained in more detail below. In step 906, ductal structures in the medical scan image are segmented. This is followed by step 908, which potentially maps the segmentation results of the lesions and / or ducts onto other imaging data. In step 910, quantitative measures of the lesions and / or ducts are calculated. In step 912, a risk score is calculated, and in step 914, all results are saved. In embodiments of the invention, a method for generating quantitative parameters of ducts and lesions in visceral organs from volumetric medical imaging scan data, wherein the scan shows all or part of the visceral organ, is described. Preferably, the method includes: locating the position of at least one lesion in a visceral organ on the medical imaging scan data; segmenting at least one detected lesion and determining one or more quantitative structural parameters of the at least one segmented lesion; performing segmentation on the volume of the medical imaging scan data to identify tubular ducts inside and near both the visceral organ within the volume of the medical imaging scan; for at least one segmented tubular duct within the volume of the medical imaging scan data, calculating at least one set of quantitative structural parameters at at least one location along the length of the tubular duct; and generating at least one set of quantitative structural parameters for the at least one segmented tubular duct.

[0095] Examples of expected types of quantitative structural parameters that can be generated using the above methods include:

[0096] The location of one or more centerlines of the segmented tubular pancreatic and biliary duct structures;

[0097] The centerline of the segmented tubular pancreatic biliary structure at one or more locations along the length of the segmented tubular pancreatic biliary structure points towards the centerline.

[0098] The radius value of the segmented tubular pancreaticobiliary structure at one or more locations along the length of the pancreaticobiliary structure;

[0099] The diameter value of the segmented tubular pancreaticobiliary structure at one or more locations along the length of the pancreaticobiliary structure;

[0100] The orientation of the cross-section of the pancreatic and biliary duct structure at one or more locations along the length of the pancreatic and biliary duct structure;

[0101] The cross-sectional profile (shape) of the segmented tubular pancreatic biliary structure at one or more locations along the length of the pancreatic biliary structure.

[0102] Indications of branching points in the segmented tubular pancreaticobiliary structures at one or more locations along the length of the pancreaticobiliary structures; and

[0103] The orientation of the branching points of the tubular pancreaticobiliary structures at one or more locations along the length of the pancreaticobiliary structures.

[0104] In particular, for some exemplary embodiments of the invention, and as described in more detail below, the method may include determining such quantitative structural parameters at multiple locations along the length of each identified tubular pancreaticobiliary structure.

[0105] Advantageously, by generating quantitative ductal and lesion data, including the generated quantitative structural parameters, from volumetric scan data obtained via, for example, magnetic resonance imaging modalities, clinicians are provided with enhanced information relating to the patient's visceral organs. This allows clinicians to more accurately assess the pathology of the patient's visceral organs, and in particular, to more accurately assess the topological and structural features of one or more ducts and / or lesions within the visceral organs, such as the presence of stenosis and dilation in the ducts. In this way, embodiments of the invention provide improved non-invasive techniques that enable clinicians to detect changes in visceral organs, and more generally, improved non-invasive diagnostic techniques for providing clinicians with an accurate assessment of the interaction between lesions and ducts in visceral organs.

[0106] Figure 9 The diagram illustrates step 1000, which requires loading medical scan data into the system to perform the method. This corresponds to... Figure 9 Step 902. In step 1002, cases are loaded into the catalog; in step 1004, the validity of each case in the catalog is checked; and in step 1006, valid cases are loaded into the application.

[0107] Figure 10 The steps required in a method for lesion segmentation workflow 1100 are described. In step 1102, the location of the lesion is identified on a medical scan image. The input to this step is preferably a 3D MRI image, which is stored as a three-dimensional array of voxels (voxels are 3D pixels), and the output is the coordinates (rows, columns, slices) of any voxels within the lesion in the 3D array. Of course, in an alternative embodiment of the invention, a 2D image may also be used.

[0108] In a preferred embodiment of the invention, the maximum intensity projection (MIP) of a 3D MRI array is utilized. The MIP is a 2D array of pixels calculated by taking the maximum intensity of a 3D image along one direction. When calculating the MIP, a lookup table recording the position of each pixel in the MIP within the 3D MRI image is also calculated. Preferably, at least one lesion is identified based on the maximum intensity protection of the voxels constituting the volumetric medical imaging scan data.

[0109] Identify pixels within the MIP containing the lesion of interest to be measured. Obtain the 3D location of the lesion voxel from the selected pixels using a lookup table.

[0110] In an alternative embodiment of the invention, lesions can be located solely using 3D MRI data or on medical scan images, and voxels within the lesion to be measured can be directly identified. Alternatively, a threshold can be applied to the entire image, and the volume rendering of each voxel above the threshold can be presented to the user—who can then directly click on the volume rendering portion they believe to be a lesion. In embodiments of the invention, at least one lesion is identified by applying a threshold to all medical imaging scan data and examining the volume rendering of each voxel exceeding the threshold.

[0111] The next step is to segment the lesion using a local threshold in step 1104. This step takes a 3D MRI image as input, the coordinates of any voxels within the lesion (from the output of step 1102), and the output is a 3D lesion mask: a voxel array of the same size as the input image, in which each voxel of the lesion is set to 1, and all other voxels are set to 0.

[0112] In a preferred embodiment of the invention, each pixel in a 3D MRI image within a defined distance of a selected point within the lesion is selected. Using these selected pixels, an intensity threshold is calculated to classify these pixels into a foreground class (MRI voxels above a threshold) and a background class (MRI voxels below a threshold). For example, this can be accomplished using a method (often referred to as the Otsu method) that calculates the inter-class variance at each threshold for a range of thresholds varying from the lowest to the highest image intensity values ​​and returns the threshold that maximizes that variance.

[0113] A 3D mask is computed where each voxel in the 3D MRI image above a threshold is set to 1, and all other voxels are set to 0. The connected components of this mask are then identified. A connected component is any set of foreground voxels that form a continuous object; that is, for each pair of voxels in a connected component, there must exist a continuous path between them that passes through an array of voxels containing only the other foreground voxels. The connected component containing selected voxels within the lesion is identified, and all other components are removed from the mask. This final mask is returned as a 3D lesion mask.

[0114] However, in an alternative embodiment of the invention, step 1104 can be omitted, and the method proceeds directly to step 1106 to find the threshold, or skips to step 1110 to manually outline the lesion using a brush tool. Another effective alternative would be to use a selected point as a seed point in the 3D image and iteratively grow a lesion mask from that seed point, wherein neighboring MRI voxels of the current mask are identified at each iteration, and any voxels whose intensity falls within a specific threshold of those voxels within the current mask are added to the mask. This method is repeated until the lesion mask stops growing, or a fixed number of iterations is reached.

[0115] Step 1106 is an optional manual fine-tuning of the threshold. The input to this step is preferably a 3D MRI image, the coordinates of any voxels within the lesion (from the output of step 1102), and (if step 1104 has been run) a 3D cyst mask from step 1104. In a preferred embodiment of the invention, a visualization of the 3D MRI image is presented to the user, overlaid with the current lesion mask. The user can manually input an alternative image threshold different from the image threshold calculated in step 1104, where the same method is applied to recalculate the lesion mask with the manually selected threshold.

[0116] Step 1110 is an optional step to separate the mask from the surrounding structures. In a preferred embodiment of the invention, in this step, a visualization of a 3D MRI image is presented to the user, wherein the current lesion mask (output from step 1104 or 1106) is overlaid on the 3D MRI image. If the lesion connects to another anatomical structure with high intensity in the MRI image, such as the pancreatic duct, the mask may include both the mask and the connected structure. If this is the case, the user can use a watershed segmentation algorithm to separate the lesion from the surrounding structures.

[0117] In this method, a distance transformation of the lesion mask is calculated. This returns a 3D voxel array of the same size as the 3D lesion mask, recording the appropriate distance of each voxel to the nearest background voxel in the 3D lesion mask. The locations of local maxima in the distance transformation image are then recorded. Using the local maxima as seed points, a series of masks are iteratively grown from these seed points until adjacent masks meet each other at a “ridge” in the distance map, and all voxels in the original foreground region have been labeled. The mask containing selected points within the lesion is used as the new lesion mask. If this segmentation results in the lesion also being sub-components, any sub-masks contained within the lesion can be recombinated in step 1112.

[0118] In an alternative embodiment of the invention, separation can also be performed by iteratively eroding a combined mask containing both the catheter and the lesion until the catheter is no longer visible, and then iteratively expanding the eroded mask, which now contains only the lesion, for the same number of iterations required to remove the catheter. This alternative method takes advantage of the fact that catheters are generally thinner than most lesions, and therefore will disappear with fewer erosion iterations than a lesion mask.

[0119] The final step 1114 of method 1100 is optionally to edit the lesion mask using a brush tool. In a preferred embodiment of the invention, in this step of the method, a visualization of a 3D MRI image is presented to the user, with the current lesion mask overlaid on the 3D MRI image. If the mask does not correctly cover the lesion even after applying the methods in steps 1106, 1110, and 1112, the user can manually edit the lesion mask using a brush tool. Here, the user can scroll through slices of the 3D MRI image and manually mark any voxels within the lesion, and can also manually remove any voxels outside the lesion.

[0120] Figure 11 It is shown as follows Figure 9 The flowchart of step 1200, required for segmenting the duct, is shown in step 906. This is a more detailed explanation of the processing performed in step 906. In step 1202, the duct is selected automatically or by the user, and thresholding is performed using local contrast. This is followed by step 1204, where the start and end points of the pancreatic duct and / or the start and end points of the common bile duct are selected. Next is step 1206, where tubular structures are detected using measurements of tubularity. In step 1208, a path search is performed to move from the start point to the end point of the duct to generate a centerline model. Finally, in step 1210, the diameter of the duct and changes in diameter(s) are quantified. In a preferred embodiment of the invention, the quantitative structural parameter set for at least one segmented duct includes at least one parameter representing at least one of the following:

[0121] At least one location at the centerline position of a segmented catheter;

[0122] At at least one location, the centerline of at least one segmented catheter faces;

[0123] The radius of at least one segmented conduit at at least one location;

[0124] The diameter of at least one segmented conduit at at least one location;

[0125] At least one location, the cross-section of at least one segmented conduit is oriented;

[0126] The cross-sectional profile of at least one segmented conduit at at least one location;

[0127] An indication that at least one segmented catheter has a branch point at at least one location; and

[0128] Orientation of at least one branch point of a split catheter at at least one location.

[0129] Figure 13 A workflow 1300 is described for measuring quantitative measures involving lesions and their interactions with the pancreatic duct and common bile duct. The steps of this method are as described above. Figure 9 This is an extension of step 910, which determines the quantitative measurement. In a preferred embodiment of the invention, the quantitative structural parameter set for at least one segmented visceral organ lesion includes at least one parameter, which represents at least one of the following:

[0130] The maximum diameter of the segmented lesion; the volume of the segmented lesion;

[0131] The determination of the presence of septa within the segmented lesion; the determination of the shape of the segmented lesion; the determination of the contents of the segmented lesion.

[0132] The initial step 1302 is to calculate the lesion size. The input for this step is as follows: Figure 11 The output of this step is the 3D lesion segmentation mask generated as shown and by the method described above, along with 3D MRI image metadata (including information about voxel dimensions in mm). The output of this step is the maximum diameter of the lesion in the three viewing planes, and the 3D volume of the lesion.

[0133] In a preferred embodiment of the invention, in this step, the lesion mask is stored as a 3D voxel array of size Nx × Ny × Nz, where each voxel containing the lesion is set to 1, and all other voxels are set to 0. To calculate the maximum lesion diameter along the first observation plane, we loop along the first dimension (i.e., from slice 1 to slice Nx) on each slice, and for each slice containing at least one voxel set to 1, we identify the edge voxels of the lesion (i.e., those voxels set to 1, but with at least one adjacent voxel set to zero) and measure the maximum distance between any pair of edge voxels. We repeat this method on the other two observation planes, looping along the second and third dimensions, to obtain the maximum diameter in the second and third observation planes, respectively. The volume of the lesion is also recorded.

[0134] In step 1304, we measure the distance between the lesion and the pancreatic duct and common bile duct. The input to this step is a 3D lesion segmentation mask containing the pancreatic duct and common bile duct, or a 3D segmentation mask, or both (obtained using the same method outlined in the MRCP+ patent). The output from this step is the nearest distance between the lesion and the pancreatic duct and common bile duct, and the (row, column, slice) coordinates of the points on these two ducts closest to the lesion. In a preferred embodiment of the invention, the distance between the segmented duct and the segmented lesion is determined using one or more of the qualitative structural parameters of at least one segmented lesion and one or more of the quantitative structural parameters of the segmented duct.

[0135] In a preferred embodiment of the invention, a distance transformation of the lesion mask is calculated. This returns a 3D voxel array of the same size as the 3D lesion mask, which records the distance of each background voxel to the nearest foreground pixel in the lesion mask. For each foreground voxel within the pancreas and common bile duct segmentation mask, the corresponding value in the distance transformation image is found, and the foreground voxel with the minimum distance transformation value is recorded. The position of this voxel and its corresponding distance transformation value are the nearest point on the duct to the lesion and the minimum distance between the duct and the lesion, respectively.

[0136] In cases where several catheter voxels are located at the same minimum distance from the lesion, the average location is calculated (by taking the average row, column, and slice coordinates of each voxel).

[0137] In cases of significant interaction between the lesion and the catheter, the catheter may not be modeled near the lesion, resulting in gaps in the catheter mask near the lesion. In such cases, the proximity from the lesion to the catheter is calculated using the catheter centerline representation generated by MRCP+. This is an ordered list of coordinates (x, y, z, d) of points along the catheter centerline, starting from the most downstream point. The first three counts record the coordinates of the point in the image, and the fourth count records the diameter at that point. First, interpolation (e.g., splines) is used to estimate the (x, y, z, d) coordinates of any gaps in the centerline model. Then, the distance transformation value of the lesion mask is calculated at each point on the interpolated centerline. The centerline point with the minimum distance transformation value is the centerline point closest to the lesion. The closest distance from the catheter to the lesion is the distance transformation value to the lesion at the nearest centerline point minus the radius of the catheter at that point. In cases where several centerline points are found to have the minimum distance equidistant from the lesion, the median point of the centerline points (ordered from the beginning to the end of the catheter) is used as the nearest point.

[0138] Alternatively, for each foreground voxel in the catheter mask, the distance to each foreground voxel in the lesion mask can be calculated. The closest distance between the lesion and the catheter will be the minimum of all these distances, and the voxel in the catheter mask with this minimum distance will be the closest point on the catheter to the lesion.

[0139] In step 1306, we determine the connectivity between the lesion and the pancreatic duct and common bile duct. In a preferred embodiment of the invention, if the minimum distance (from step 1304) is below a certain threshold, the two are recorded as connected. Otherwise, they are recorded as not connected.

[0140] If the above also fails, but the user visually sees that the lesion and the catheter appear to be connected, the user can also choose to manually mark them as connected, and the distance from step 1304 is also set to zero.

[0141] In an alternative embodiment of the invention, we detect the interaction between the lesion and the catheter by first creating a mask using the lower of the image thresholds for either the lesion or the catheter (where any voxels in the original MRI image greater than the threshold are set to 1, and all other voxels are set to 0). If any connected component in the mask overlaps with both the lesion and catheter masks, the lesion and catheter are marked as connected, and the distance calculated in step 1304 is overwritten to zero.

[0142] Another approach iteratively applies the expansion to the lesion mask or catheter segmentation mask and records how many iterations are required to connect one mask to another. If the number of iterations is below a certain threshold, the two are considered connected.

[0143] We can further supplement the implementations and alternative methods outlined herein by measuring the difference in pancreatic duct diameter upstream and downstream of the lesion—if the diameter increases from downstream to upstream, or if the change in diameter deviates from a pre-characterized normal range, this suggests a possible interaction (in the absence of any interaction, we expect the pancreatic duct diameter to decrease as we move from downstream to upstream). If the pancreatic duct diameter increases from downstream to upstream, or if the output from any other method outlined herein indicates that the pancreatic duct is connected to the lesion, we can label the lesion as interacting with the pancreatic duct. In a preferred embodiment of the invention, the method further includes dividing the identified segmented duct into an upstream region of the lesion, a downstream region of the lesion, and a region interacting with the lesion, and determining the duct diameter and diameter change in each of these different regions. More preferably, the width profile of the different regions of the tubular duct is used to determine additional ductal measurements.

[0144] In step 1308, we measure the duct size. In a preferred embodiment of the invention, a point (x, y, z, d) is used, starting from the head of the pancreas and ending at the tail, along the centerline of the duct. The first three coordinates record the position of this point in the image, and the fourth coordinate is the measured diameter of the duct at that point.

[0145] The coordinates of the nearest point on the pancreatic duct to the lesion will most likely lie on the surface of the pancreatic duct. First, find the point on the centerline of the pancreatic duct closest to that point. This is recorded as the centerline point closest to the cyst. If there is a gap in the ductal mask and a centerline-based method is used to find the nearest point, the nearest centerline point from that method is used instead. Each point on the centerline within r mm of the nearest centerline point to the lesion is marked as being in the “interaction zone”, where r is half the maximum diameter of the lesion calculated in step 1302. Because the lesion centerline points are sorted from head to tail (i.e., from downstream to upstream), all centerline points before the interaction zone are marked as downstream, and all those centerline points after the interaction zone are marked as upstream. Return the median ductal diameter in the upstream, downstream, and interaction zones, as well as the median diameter of the entire duct.

[0146] Figure 13 A simplified flowchart 1400 illustrates an example of a method for detecting and quantifying patterns of change indicating at least one of narrowing, dilation, and beading within the bile duct tree or pancreatic duct structures. Figure 13 The method begins at 1410 and moves to 1420, where quantitative bile duct tree and pancreatic duct data are loaded. In step 1430, the centerline point and duct are measured, as shown... Figure 11 As described in steps 1208 and 1210. Each catheter is represented as an ordered list containing the centerline coordinates of its spatial location and catheter width at each centerline point. In the illustrated example, at step 1440, the extracted catheter width estimate may optionally be smoothed to remove noise that could cause false detections—for example, a Gaussian kernel or local averaging may be applied.

[0147] In step 1450, local minima of the width profile along the ordered centerline points are detected. The salience or “severity” of each local minima is characterized by both the absolute difference and the percentage difference in tube width between the minimum point and the adjacent local maximum point. If one or both of these differences exceed a given threshold for a given local minima, the local minima is marked as narrow.

[0148] In step 1460, local maxima of the width profile along the ordered centerline points are detected. The salience or “severity” of each local maxima is characterized by measuring both the absolute difference and the percentage difference in tube width between the maxima point and the adjacent local minima. If one or both of these differences exceed a given threshold for a given local maxima, the local maxima is marked as dilatation.

[0149] Beading can also be detected, for example, based on the sequence of detected stenosis and dilatation. In step 1470, a quantitative measurement of each detected stenosis and dilatation is calculated, such as the severity defined in steps 1450 and 1460. Finally, in 1480, stenosis and dilatation data including location and each quantitative measurement, as well as summary measures, such as the total number of stenosis and dilatation and the percentage of the length of each catheter including stenosis and dilatation, are recorded.

[0150] Figure 14 A simplified block diagram of an example image processing system 1500 that can be adapted according to an example of the present invention is illustrated. System 1500 includes one or more processing devices 1510 arranged to perform various processing functions. In some example embodiments, one or more of the processing devices 1510 may include one or more processor cores arranged to execute computer program code. Additionally / alternatively, at least one of the processing devices may include hardware processing devices, such as application-specific integrated circuit (ASIC) devices or hardware accelerator modules, which include hardware circuitry arranged to perform predefined processing on data provided thereto.

[0151] System 1500 also includes one or more memory elements 1520. The memory elements 1520 may include one or more non-transitory computer program products, such as, for example, hard disks, optical storage devices such as CD-ROM devices, magnetic storage devices, read-only memory, ROM, programmable read-only memory, PROM, erasable programmable read-only memory, EPROM, electrically erasable programmable read-only memory (EEPROM), and flash memory. Memory elements 1520 may additionally / alternatively include one or more volatile memory elements, such as random access memory (RAM), cache memory, etc.

[0152] For simplicity and ease of understanding, the following text will refer to a single processing device 1510 and a single memory element 1520. However, it should be understood that such references to a single processing device 1510 or a single memory element 1520 are intended to cover multiple processing devices 1510 and multiple memory elements 1520, respectively.

[0153] Memory element 1520 may store executable computer program code to be executed by processing device 1510. Memory element 1520 may also store data to be accessed and / or processed by processing device 1510 when executing the computer program code.

[0154] Figure 14 The system 1500 illustrated in the figure also includes one or more output devices, as generally indicated at 1530. For example, such output devices may include display devices, printer devices, network interface devices, etc. Figure 14 The system 1500 illustrated in the figure also includes one or more user input devices, as generally indicated at 1540. For example, such input devices may include a keyboard, keypad, mouse, touchscreen, etc.

[0155] According to some examples of the invention, the processing device 1510 is arranged to generate quantitative data on the bile duct tree and pancreatic duct structure from volumetric medical imaging scan data, for example, according to the various methods described above with reference to the accompanying drawings. Therefore, the processing device 1510 is arranged as follows:

[0156] Perform volume segmentation of medical imaging scan data to identify tubular ductal structures within the volume of medical imaging scan data;

[0157] Calculate a set of quantitative structural parameters at each location along the length of the identified tubular bile ducts and pancreatic structures; and

[0158] The output includes quantitative bile duct tree and pancreatic data, which consist of quantitative structural parameter sets of the identified tubular bile ducts and pancreatic structures.

[0159] For example, processing device 1510 may be arranged to execute computer program code stored in memory element 1520 for performing at least some steps of the various methods described above with reference to the accompanying drawings.

[0160] like Figure 14 As shown, the image processing system 1500 can be operatively coupled to at least one data storage device 1550, the processing device 1510 can retrieve imaging scan data from the data storage device 1550, and the processing device 1510 can output quantitative bile duct and pancreas data to the data storage device 1550, including a quantitative set of structural parameters for segmented tubular bile duct and pancreas structures.

[0161] It is also conceivable that various values, measures, measurements, and other data generated by the image processing system 1500 during the generation of quantitative bile duct tree and pancreatic data can be output together or separately to and stored in the data storage device 1550. For example, such data includes:

[0162] Heissen volume;

[0163] eigenvectors;

[0164] Ra ratio;

[0165] Rb ratio;

[0166] Strength metric S;

[0167] Tubular measurement (To / To(σ));

[0168] Scale (σ);

[0169] The segmented (binarized) volume;

[0170] Centerline point;

[0171] Pipe width estimation;

[0172] Branch nodes;

[0173] Median value; and

[0174] Narrow and / or expanded data.

[0175] As discussed with reference to preferred embodiments of the invention, the invention allows for the following features:

[0176] Lesion segmentation, and detection of the interaction between the lesion and the main pancreatic duct and common bile duct;

[0177] Morphological measurements of pancreatic lesions (e.g., maximum diameter, volume, sphericity); morphological measurements of pancreatic ducts and common bile ducts (e.g., median diameter, localized areas of diameter variation).

[0178] Quantification of the interaction between pancreatic cystic lesions and ducts; interaction between lesions and pancreatic duct / CBD;

[0179] Detect the closest point between the lesion and the catheter;

[0180] Measurement of the distance between the lesion and the pancreatic duct / CBD;

[0181] The pancreatic duct / CBD was divided into upstream, downstream, and interacting segments; morphological changes in the pancreatic duct were detected.

[0182] Detecting the branch catheter connected to the lesion; and

[0183] Quantify the mural nodules / solid components of the lesion.

[0184] Characterization of the pancreatic parenchyma is also possible using the method of this invention. This will provide the following measurements or organ analyses, including:

[0185] Characterization of the region between the lesion and the pancreatic duct via multiparametric MRI;

[0186] Assessment of pancreatic fat and inflammation in the parenchyma using PDFF and T1; and

[0187] Regional changes in pancreatic volume and regional changes in T1 and PDFF.

[0188] The method of this invention can also be used to characterize lesions. This allows:

[0189] Representation of shape;

[0190] Maximum diameter;

[0191] Volume;

[0192] The detection of septa within the lesion, and the determination of the number of septa present within the lesion; and

[0193] The number of lesions present (including those classified as monocystic, oligocystic, or polycystic based on the presence of cystic lesions).

[0194] The determination of cyst contents by changes in MRI contrast (including T1 and proton density fat fraction [PDFF]) can also be achieved by the method of the present invention. These include one or more of the following: changes in MRI signals (T1, PDFF, diffusion-weighted imaging [DWI] signals) detected in the pancreatic parenchyma between the lesion and the duct.

[0195] The method of this invention can also be used to predict longitudinal changes in malignant tumors. These may include one or more of the following:

[0196] A change in any of the above indicators indicates an increased risk;

[0197] Images from the same patient were registered at multiple time points to match lesions that changed over time.

[0198] As described above, the present invention provides novel automated measurements for quantitatively characterizing cystic lesions and their interactions with the pancreatic duct, CBD, and pancreatic parenchyma. These provide more robust measurements, reduce variability among clinicians, improve risk prediction for pancreatic cancer, and save time due to automation.

[0199] Changes in MRI signals detected in distant regions of the pancreatic parenchyma away from cystic lesions can be assessed, including T1, PDFF, and DWI signals.

[0200] This method has the potential to be applied to a wider range of assessments, including other modalities (e.g., computed tomography) or other organs (e.g., characterization of renal cysts).

[0201] As described above, the present invention can be implemented in a computer program running on an image processing system, the computer program including at least a code portion for performing the steps of the method according to the present invention or enabling the programmable device to perform the functions of the device or system according to the present invention when running on a programmable device such as an image processing system.

[0202] A computer program is a list of instructions such as a particular application and / or operating system. A computer program may include, for example, one or more of the following: subroutines, functions, procedures, object methods, object implementations, executable applications, applets, servlets, source code, object code, shared libraries / dynamically loaded libraries, and / or other sequences of instructions designed to be executed on a computer system.

[0203] Computer programs can be internally stored on tangible, non-transitory computer-readable storage media, or transferred to a computer system via computer-readable transmission media. All or some of the computer programs can be provided on computer-readable media that are permanently, removably, or remotely coupled to the information processing system. Tangible, non-transitory computer-readable media can include, for example, but not limited to, any number of the following media: magnetic storage media, including magnetic disk and magnetic tape storage media; optical storage media, such as optical disc media (e.g., CD-ROM, CD-R, etc.) and digital video disc storage media; non-volatile memory storage media, including semiconductor-based memory cells such as flash memory, EEPROM, EPROM, ROM; ferromagnetic digital memory; MRAM; and volatile storage media, including registers, buffers or caches, main memory, RAM, etc.

[0204] Computer processing typically involves the executing (running) program or part of a program, current program values ​​and status information, and the resources used by the operating system to manage the execution of the processing. The operating system (OS) is software that manages the computer's resource sharing and provides programmers with interfaces for accessing those resources. The operating system processes system data and responds to user input by allocating and managing tasks and internal system resources as services to the system's users and programs.

[0205] In the foregoing description, the invention has been described with reference to specific examples of embodiments thereof. However, it is clear that various modifications and alterations can be made to the invention without departing from the scope of the invention as set forth in the appended claims, and the claims are not limited to the specific examples described above.

[0206] Those skilled in the art will recognize that the boundaries between logic blocks are merely illustrative, and alternative embodiments may combine logic blocks or circuit elements, or implement alternative functional decompositions for various logic blocks or circuit elements. Therefore, it should be understood that the architecture described herein is merely exemplary, and many other architectures that actually achieve the same functionality can be implemented.

[0207] Any arrangement of components that perform the same function is effectively “associated” to achieve the desired functionality. Therefore, any two components combined in this paper to achieve a specific function can be considered “associated” with each other to achieve the desired functionality, regardless of the architecture or intermediate components. Similarly, any two such associated components can also be considered “operably connected” or “operably coupled” with each other to achieve the desired functionality.

[0208] Furthermore, those skilled in the art will recognize that the boundaries between the above operations are merely illustrative. Multiple operations may be combined into a single operation, a single operation may be distributed among additional operations, and operations may be performed with at least partial overlap in time. Additionally, alternative embodiments may include multiple instances of a particular operation, and the order of operations may be varied in various other embodiments.

[0209] However, other modifications, variations, and substitutions are also possible. Therefore, the specification and drawings are considered illustrative rather than restrictive.

[0210] In the claims, any reference numerals placed between parentheses should not be construed as limiting the claims. The word “comprising” does not exclude the presence of other elements or steps besides those listed in the claims. Furthermore, the term “a” as used herein is defined as one or more. Moreover, the use of introductory phrases such as “at least one” and “one or more” in the claims should not be construed as implying that any particular claim containing such an introduced element is limited to an invention containing only one such element, even when the same claim includes the introductory phrases “one or more” or “at least one” along with indefinite articles such as “a.” The same applies to the use of definite articles. Unless otherwise stated, terms such as “first” and “second” are used to make arbitrary distinctions between the elements described by these terms. Therefore, these terms are not necessarily intended to indicate the time or other priority of these elements. The fact that certain manners are referenced in mutually different claims does not mean that combinations of these manners cannot be used advantageously.

[0211] The invention has been described by way of example only. Therefore, the foregoing is to be considered merely an illustration of the principles of the invention. Furthermore, since many modifications and alterations will readily occur to those skilled in the art, it is not intended to limit the invention to the exact constructions and operations shown and described, and thus, all suitable modifications and equivalents may be considered to fall within the scope of the claims.

Claims

1. A method for generating quantitative parameters of lesions and pancreatic and bile ducts in said visceral organs from volumetric medical imaging scan data obtained from medical imaging scans of all or part of said visceral organs; said method comprising: Locate at least one lesion and at least one pancreatic duct in the visceral organ on the volumetric medical imaging scan data; The volumetric medical imaging scan data is used to perform volume segmentation within the medical imaging scan to identify and segment the at least one lesion and the pancreaticobiliary duct; Determine at least one structural parameter of the segmented at least one lesion; Determine at least one structural parameter of the segmented at least one pancreatic duct.

2. The method of claim 1, wherein the structural parameters of the at least one pancreatic duct that has been segmented include quantitative parameters.

3. The method of claim 1, wherein at least one of the structural parameters of the at least one segmented pancreatic duct is determined at at least one location along the length of the at least one pancreatic duct.

4. The method of claim 3, wherein the structural parameters of the at least one pancreatobiliary duct that has been segmented include at least one parameter, said at least one parameter representing at least one of the following: The centerline position of the at least one pancreatic biliary duct at the at least one location; At the at least one location, the centerline of the at least one pancreatic biliary duct faces; The radius of the at least one pancreatic duct at the at least one location; The diameter of the at least one pancreatic duct at the at least one location; The cross-section of the at least one pancreatic duct at the at least one location is oriented as follows; The cross-sectional profile of the at least one pancreatic duct at the at least one location; An indication that at least one pancreatic bile duct has a branching point at the at least one location; as well as The orientation of the branch point of the at least one pancreatic duct at the at least one location.

5. The method of any of the preceding claims, wherein the structural parameters of the at least one lesion being segmented include quantitative parameters.

6. The method of any of the preceding claims, wherein the group of structural parameters of the segmented at least one lesion includes at least one parameter, said at least one parameter representing at least one of the following: The maximum diameter of the lesion; the volume of the lesion; The presence of a diaphragm within the lesion was confirmed; The shape of the lesion; the contents of the lesion.

7. The method of any of the preceding claims, wherein the structural parameters of the at least one lesion being segmented include qualitative parameters.

8. The method as claimed in any of the preceding claims, further comprising: The distance between the segmented lesion and the segmented pancreatic duct is determined using at least one of the structural parameters of the segmented at least one lesion and at least one of the structural parameters of the segmented pancreatic duct.

9. The method of any of the preceding claims, wherein the method further comprises: The at least one pancreatic biliary duct is divided and identified as an upstream region of the lesion, a downstream region of the lesion, and a region interacting with the lesion, and the diameter and diameter variation of the pancreatic biliary duct in each of these different regions are determined.

10. The method of claim 9, wherein the width profile of at least one of the upstream region, downstream region, and interaction region of the pancreatic biliary duct is used to determine additional measurements of the pancreatic biliary duct.

11. The method of claim 9 or claim 10, further comprising detecting patterns of change within the at least one pancreatic duct based on a median diameter estimate along the length of the at least one pancreatic duct.

12. The method of claim 11, further comprising detecting patterns of change within the at least one pancreatic duct by applying at least one pattern detection window to median diameter estimation data.

13. The method of claim 11 or claim 12, further comprising detecting at least one of the following: narrowing; dilation; and beading.

14. The method of any of the preceding claims, wherein the at least one lesion is identified based on the maximum intensity protection of the voxels constituting the volumetric medical imaging scan data.

15. The method of any of the preceding claims, wherein the segmented at least one lesion is identified by applying a threshold to the entirety of the medical imaging scan data and examining the volume rendering of each voxel exceeding the threshold.

16. The method of any of the preceding claims, wherein the visceral organ is the pancreas.

17. The method of any of the preceding claims, further comprising the step of performing tubular enhancement on the volumetric medical imaging scan data to derive at least one tubularity measurement for each voxel within the volumetric medical imaging scan data; wherein the tubular enhancement comprises, for each voxel within the volume of the medical imaging scan data, calculating at least one metric that distinguishes tubular structures from other structures and calculating a tubularity measurement for the corresponding voxel based at least in part on the at least one metric.

18. The method of any of the preceding claims further comprises enhancement using a tubular pancreatic-biliary structure based on multi-scale Hessian.

19. The method of any of the preceding claims, wherein the volumetric medical imaging scan data comprises imaging scan data obtained via magnetic resonance imaging modality.

20. The method of any of the preceding claims, further comprising determining the total number of pancreatic lesions shown in the volumetric imaging scan data.

21. An image processing system configured to generate quantitative parameters of lesions and pancreatic and bile ducts in said visceral organs from volumetric medical imaging scan data from scans showing all or part of visceral organs; said image processing system comprising at least one processing device configured to perform the following operations: Locate the position of at least one lesion in the internal organ on the medical imaging scan data; segment the located at least one lesion and determine one or more structural parameters of the segmented at least one lesion; Perform segmentation of the volume of the medical imaging scan data to identify the pancreas and bile ducts of the visceral organs within the volume of the medical imaging scan; Generate at least one set of quantitative structural parameters for at least one segmented pancreatic biliary duct.

22. The image processing system of claim 1, wherein the image processing system is arranged to identify at least one of the pancreatic ducts within the volume of the medical imaging scan data to calculate at least one set of quantitative structural parameters at at least one location along the length of the pancreatic duct.

23. The image processing system of claim 22, wherein the quantitative structural parameter set of the segmented at least one pancreaticobiliary duct includes at least one parameter, said at least one parameter representing at least one of the following: The centerline position of the at least one pancreatic biliary duct at the at least one location; At the at least one location, the centerline of the at least one pancreatic biliary duct faces; The radius of the at least one pancreatic duct at the at least one location; The diameter of the at least one pancreatic duct at the at least one location; The cross-section of the at least one pancreatic duct at the at least one location is oriented as follows; The cross-sectional profile of the at least one pancreatic duct at the at least one location; An indication that at least one pancreatic bile duct has a branching point at the at least one location; as well as The orientation of the branch point of the at least one pancreatic duct at the at least one location.

24. The image processing system of claim 21, 22 or 23, wherein the group of structural parameters of the segmented at least one lesion includes quantitative structural parameters.

25. The image processing system of claim 21, 22, 23 or 24, wherein the structural parameter set of the segmented at least one lesion includes at least one parameter, said at least one parameter representing at least one of the following: The maximum diameter of the lesion; the volume of the lesion; The determination of the presence of a septum within the lesion; the determination of the shape of the lesion; the determination of the contents of the lesion.

26. The image processing system according to any one of claims 21 to 25, wherein the structural parameters of the segmented at least one lesion include qualitative structural parameters.

27. The image processing system of any one of claims 21 to 26, wherein the processing device is further configured to perform the following steps: The distance between the pancreatic duct and the lesion is determined using one or more of the structural parameters of the at least one segmented lesion and one or more of the quantitative structural parameters of the segmented pancreatic duct.

28. The image processing system of claims 21 to 27, wherein the processing device is further configured to perform the following steps: The pancreatic biliary duct is divided into an upstream region of the segmented lesion, a downstream region, and a region that interacts with the segmented lesion, and the diameter and diameter variation of the pancreatic biliary duct in each of these different regions are determined.

29. The image processing system of claim 28, wherein the width profile of the different regions of the pancreatic biliary duct is used to determine additional measurements of the duct.

30. The image processing system of any one of claims 21 to 29, wherein the processing device is further configured to perform the step of detecting a pattern of change within the at least one pancreatic duct based on a median diameter estimate along the length of the at least one pancreatic duct.

31. The image processing system of any one of claims 21 to 30, wherein the processing device is further configured to perform the step of detecting a pattern of change within the at least one pancreatic duct by applying at least one pattern detection window to median diameter estimation data.

32. The image processing system of any one of claims 21 to 31, wherein the processing device is further configured to perform the step of detecting at least one of the following: narrowing; dilation; and beading.

33. The image processing system of any one of claims 21 to 32, wherein the processing device is further configured to identify at least one segmented lesion by applying a threshold to the entirety of the medical imaging scan data and examining the volume rendering of each voxel exceeding the threshold.

34. The image processing system according to any one of claims 21 to 33, wherein the processing device is further configured to perform the following steps: Perform tubular enhancement on the volumetric medical imaging scan data to derive at least one tubularity measurement for each voxel within the volumetric medical imaging scan data; wherein the tubular enhancement includes, for each voxel within the volume of the medical imaging scan data, calculating at least one metric that distinguishes tubular structures from other structures and calculating the tubularity measurement of the corresponding voxel based at least in part on the at least one metric.

Images