Large vessel occlusion detection and classification in medical imaging

Patent metadata

Field	Value
Publication number	US-12295774-B2
Application number	US-202217807772-A
Country	US
Kind code	B2
Filing date	Jun 20, 2022
Priority date	Jun 20, 2022
Publication date	May 13, 2025
Grant date	May 13, 2025

Abstract

Systems and methods for occlusion detection in medical images are provided. An input medical image of one or more vessels in an anatomical object of a patient is received. One or more anatomical landmarks are identified in the input medical image. A first patch and one or more additional patches are extracted from the input medical image based on the identified one or more anatomical landmarks. The first patch and the one or more additional patches depict different portions of the anatomical object. Features are extracted from the first patch and the one or more additional patches using a machine learning based feature extractor network. An occlusion in the one or more vessels is detected in the first patch based on the extracted features with or without modeling features on a probability distribution function. Results of the detecting are output.

First claim

The invention claimed is:

1. A computer-implemented method comprising:
receiving an input medical image of one or more vessels in an anatomical object of a patient;
identifying one or more anatomical landmarks in the input medical image;
extracting a first patch and one or more additional patches from the input medical image based on the identified one or more anatomical landmarks, the first patch and the one or more additional patches depicting different portions of the anatomical object;
extracting features from the first patch and the one or more additional patches using a machine learning based feature extractor network, the machine learning based feature extractor network receiving as input the first patch and the one or more additional patches and generating as output the extracted features, the extracted features comprising 1) differential features comparing the first patch with each of the one or more additional patches and 2) vessel density features specific to the first patch;
detecting an occlusion in the one or more vessels in the first patch based on the extracted features; and
outputting results of the detecting.

2. The computer-implemented method of claim 1 , further comprising removing bone from the input medical image and wherein extracting a first patch and one or more additional patches from the input medical image based on the identified one or more anatomical landmarks comprises:
extracting the first patch and the one or more additional patches from the bone-removed input medical image.

3. The computer-implemented method of claim 1 , wherein extracting features from the first patch and the one or more additional patches using a machine learning based feature extractor network comprises:
receiving the first patch via a first input channel of the machine learning based feature extractor network and the one or more additional patches via a respective one of one or more additional input channels of the machine learning based feature extractor network.

4. The computer-implemented method of claim 1 , wherein extracting a first patch and one or more additional patches from the input medical image based on the identified one or more anatomical landmarks comprises:
cropping the first patch and the one or more additional patches centered around the one or more anatomical landmarks.

5. The computer-implemented method of claim 1 , wherein detecting an occlusion in the one or more vessels in the first patch based on the extracted features comprises:
detecting the occlusion in the one or more vessels in the first patch using a probability distribution function (PDF) model fitted on a set of features extracted by a neural network.

6. The computer-implemented method of claim 5 , wherein the PDF model is learned using a Gaussian Process model.

7. The computer-implemented method of claim 1 , wherein:
identifying one or more anatomical landmarks in the input medical image comprises identifying a middle cerebral artery (MCA) bifurcation in the input medical image;
extracting a first patch and one or more additional patches from the input medical image based on the identified one or more anatomical landmarks comprises cropping the first patch centered around the MCA bifurcation; and
detecting an occlusion in the one or more vessels in the first patch based on the extracted features comprises detecting the occlusion as being in one of an internal carotid artery (ICA), an MCA M1 segment, or MCA M2 segment.

8. The computer-implemented method of claim 1 , further comprising generating at least one probability map of vessel presence for at least one of the first patch or the one or more additional patches and wherein extracting features from the first patch and the one or more additional patches using a machine learning based feature extractor network comprises:
extracting features from the at least one probability map using the machine learning based feature extractor network.

9. The computer-implemented method of claim 1 , wherein the anatomical object comprises a brain of the patient and the different portions comprise a left side of the brain a right side of the brain.

10. An apparatus comprising:
means for receiving an input medical image of one or more vessels in an anatomical object of a patient;
means for identifying one or more anatomical landmarks in the input medical image;
means for extracting a first patch and one or more additional patches from the input medical image based on the identified one or more anatomical landmarks, the first patch and the one or more additional patches depicting different portions of the anatomical object;
means for extracting features from the first patch and the one or more additional patches using a machine learning based feature extractor network, the machine learning based feature extractor network receiving as input the first patch and the one or more additional patches and generating as output the extracted features, the extracted features comprising 1) differential features comparing the first patch with each of the one or more additional patches and 2) vessel density features specific to the first patch;
means for detecting an occlusion in the one or more vessels in the first patch based on the extracted features; and
means for outputting results of the detecting.

11. The apparatus of claim 10 , further comprising means for removing bone from the input medical image and wherein extracting a first patch and one or more additional patches from the input medical image based on the identified one or more anatomical landmarks comprises:
means for extracting the first patch and the one or more additional patches from the bone-removed input medical image.

12. The apparatus of claim 10 , wherein the means for extracting features from the first patch and the one or more additional patches using a machine learning based feature extractor network comprises:
means for receiving the first patch via a first input channel of the machine learning based feature extractor network and the one or more additional patches via a respective one of one or more additional input channels of the machine learning based feature extractor network.

13. The apparatus of claim 10 , wherein the means for extracting a first patch and one or more additional patches from the input medical image based on the identified one or more anatomical landmarks comprises:
means for cropping the first patch and the one or more additional patches centered around the one or more anatomical landmarks.

14. The apparatus of claim 10 , wherein the anatomical object comprises a brain of the patient and the different portions comprise a left side of the brain a right side of the brain.

15. A non-transitory computer readable medium storing computer program instructions, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
receiving an input medical image of one or more vessels in an anatomical object of a patient;
identifying one or more anatomical landmarks in the input medical image;
extracting a first patch and one or more additional patches from the input medical image based on the identified one or more anatomical landmarks, the first patch and the one or more additional patches depicting different portions of the anatomical object;
extracting features from the first patch and the one or more additional patches using a machine learning based feature extractor network, the machine learning based feature extractor network receiving as input the first patch and the one or more additional patches and generating as output the extracted

Assignees

• Siemens Healthineers Ag

Inventors

• Georgescu Bogdan
• Gibson Eli
• Re Thomas
• Comaniciu Dorin

Classifications

• G06T2207/30016

  Brain · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T7/337

  involving reference images or patches · CPC title