Methods, systems, and computer readable media for automated detection of abnormalities in medical images

Patent metadata

Field	Value
Publication number	US-2016239969-A1
Application number	US-201615044928-A
Country	US
Kind code	A1
Filing date	Feb 16, 2016
Priority date	Feb 14, 2015
Publication date	Aug 18, 2016
Grant date	—

Abstract

Methods, systems, and computer readable media for automated detection of abnormalities in medical images are disclosed. According to a method for automated abnormality detection, the method includes receiving a target image. The method also includes deformably registering to the target image or to a common template a subset of normative images from a plurality of normative images, wherein the subset of normative images is associated with a normal variation of an anatomical feature. The method further includes defining a dictionary using the subset of normative images. The method also includes decomposing, using sparse decomposition and the dictionary, the target image. The method further includes classifying one or more voxels of the target image as normal or abnormal based on results of the sparse decomposition.

First claim

What is claimed is:

1 . A method for automated abnormality detection, the method comprising:
receiving a target image; deformably registering to the target image or to a common template a subset of normative images from a plurality of normative images, wherein the subset of normative images is associated with a normal variation of an anatomical feature; defining a dictionary using the subset of normative images; decomposing, using sparse decomposition and the dictionary, the target image; and classifying one or more voxels of the target image.

2 . The method of claim 1 comprising:
re-aligning the subset of normative images;
re-defining the dictionary using the subset of normative images;
re-decomposing the target image using the dictionary; and
re-classifying the one or more voxels in the target image as normal or abnormal.

3 . The method of claim 1 wherein using the sparse decomposition includes performing l1-norm minimization to identify a normal component and a residual component in the target image.

4 . The method of claim 1 wherein defining the dictionary includes identifying a subset of images associated with a same or similar spatial location as the target image.

5 . The method of claim 1 comprising:
generating at least one abnormality score associated with at least one voxel of the target image based on a sliding windowing scheme with overlapping patches.

6 . The method of claim 1 comprising:
generating a shape-based abnormality score for the target image based on a Jacobian determinant, a divergence, a curl, or a feature of one or more deformation fields.

7 . The method of claim 1 comprising:
generating an image-based abnormality map after each of a plurality of successively higher resolution levels.

8 . The method of claim 1 wherein the plurality of images includes a two dimensional (2D) image, a projectional radiograph (x-ray), a tomogram, an ultrasound image, a thermal image, an echocardiogram, a magnetic resonance image (MRI), a three dimensional (3D) image, a computed tomography (CT) image, a photoacoustic image, an elastography image, a tactile image, a positron emission tomography (PET) image, or a single-photon emission computed tomography (SPECT) image.

9 . The method of claim 1 wherein the plurality of images include normal anatomical or functional variations for one or more portions of a biological system.

10 . The method of claim 9 wherein the biological system includes the anatomical feature, a skeletal system, a muscular system, an integumentary system, a nervous system, a cardiovascular system, an endocrine system, a respiratory system, a urinary system, an excretory system, a reproductive system, a digestive system, a lymphatic system, a brain, a stomach, a heart, a lung, a bladder, a liver, a kidney, skin, an eye, a bone, an organ, or a body part.

11 . A system for automated abnormality detection, the system comprising:
a computing platform including at least one processor and memory, the computing platform comprising: an abnormality detection module utilizing the at least one processor and memory, the abnormality detection module is configured to receive a target image, to deformably register to the target image or to a common template a subset of normative images from a plurality of normative images, wherein the subset of normative images is associated with a normal variation of an anatomical feature, to define a dictionary using the subset of normative images, to decompose, using sparse decomposition and the dictionary, the target image, and to classify one or more voxels of the target image as normal or abnormal based on results of the sparse decomposition.

12 . The system of claim 11 wherein the abnormality detection module is configured to re-align the subset of normative images, to re-define the dictionary using the subset of normative images, to re-decompose the target image using the dictionary, and to re-classify the one or more voxels in the target image as normal or abnormal.

13 . The system of claim 11 wherein the abnormality detection module is configured to perform l1-norm minimization to identify a normal component and a residual component in the target image.

14 . The system of claim 11 wherein the abnormality detection module is configured to identify a subset of images associated with a same or similar spatial location as the target image.

15 . The system of claim 11 wherein the abnormality detection module is configured to generate at least one abnormality score associated with at least one voxel of the target image based on a sliding windowing scheme with overlapping patches.

16 . The system of claim 11 wherein the abnormality detection module is configured to generate a shape-based abnormality score for the target image based on a Jacobian determinant, a divergence, a curl, or a feature of one or more deformation fields.

17 . The system of claim 11 wherein the abnormality detection module is configured to generate an image-based abnormality map after each of a plurality of successively higher resolution levels.

18 . The system of claim 11 wherein the plurality of images includes a two dimensional (2D) image, a projectional radiograph (x-ray), a tomogram, an ultrasound image, a thermal image, an echocardiogram, a magnetic resonance image (MRI), a three dimensional (3D) image, a computed tomography (CT) image, a photoacoustic image, an elastography image, a tactile image, a positron emission tomography (PET) image, or a single-photon emission computed tomography (SPECT) image.

19 . The system of claim 11 wherein the plurality of images include normal anatomical or functional variations for one or more portions of a biological system.

20 . The system of claim 19 wherein the biological system includes a skeletal system, a muscular system, an integumentary system, a nervous system, a cardiovascular system, an endocrine system, a respiratory system, a urinary system, an excretory system, a reproductive system, a digestive system, a lymphatic system, a brain, a stomach, a heart, a lung, a bladder, a liver, a kidney, skin, an eye, a bone, an organ, or a body part.

21 . A non-transitory computer readable medium having stored thereon executable instructions that when executed by at least one processor of at least one computer cause the at least one computer to perform steps comprising:
receiving a target image; deformably registering to the target image or to a common template a subset of normative images from a plurality of normative images, wherein the subset of normative images is associated with a normal variation of an anatomical feature; defining a dictionary using the subset of normative images; decomposing, using sparse decomposition and the dictionary, the target image; and classifying one or more voxels of the target image as normal or abnormal based on results of the sparse decomposition.

22 . The non-transitory computer readable medium of claim 21 comprising additional executable instructions that when executed by the at least one processor of the at least one computer cause the at least one computer to perform steps comprising:
re-aligning the subset of normative images;
re-defining the dictionary using the subset of normative images;
re-decomposing the target image using the dictionary; and
re-classifying the one or more voxels in the target image as normal or abnormal.

Assignees

• Univ Pennsylvania

Inventors

• Davatzikos Christos
• Zeng Ke
• Erus Ali Guray

Classifications

• G06T7/0014 Primary

  using an image reference approach · CPC title

• G06V10/7715

  Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title

• G06F18/2433

  Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection · CPC title