IP Library › Granted Patent US 12,295,774
Granted Patent B2
US 12,295,774 · App. 17/807,772 · Granted May 13, 2025

Large vessel occlusion detection and classification in medical imaging

Inventors: Bogdan Georgescu (Princeton, NJ); Eli Gibson (Plainsboro, NJ); Thomas Re (New York, NY); Dorin Comaniciu (Princeton, NJ)
Assignee: Siemens Healthineers AG
A61B6/5217G06T7/337G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30016
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,295,774
App. No.
17/807,772
Granted
May 13, 2025
Kind
B2
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.

Claims (54)

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 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.

16. The non-transitory computer readable medium of claim 15 , 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.

17. The non-transitory computer readable medium of claim 16 , wherein the PDF model is learned using a Gaussian Process model.

18. The non-transitory computer readable medium of claim 15 , 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.

19. The non-transitory computer readable medium of claim 15 , the operations 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.

20. The non-transitory computer readable medium of claim 15 , 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.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 20, 2023
From: SIEMENS HEALTHCARE GMBH
To: SIEMENS HEALTHINEERS AG
Reel/Frame 066267/0346 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 5, 2022
From: SIEMENS MEDICAL SOLUTIONS USA, INC.
To: SIEMENS HEALTHCARE GMBH
Reel/Frame 060395/0236 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 29, 2022
From: GEORGESCU, BOGDAN; GIBSON, ELI; RE, THOMAS; COMANICIU, DORIN
To: SIEMENS MEDICAL SOLUTIONS USA, INC.
Reel/Frame 060352/0748 →
Continuity (1)
Related Publication 20230404512A1 · Dec 21, 2023
References Cited (34)
US 9792531B2 · Georgescu et al. · 2017 [cited by applicant]
US 10373313B2 · Ghesu et al. · 2019 [cited by applicant]
US 20140107479A1 · Klaiman · 2014 [cited by examiner]
US 20180366225A1 · Mansi · 2018 [cited by examiner]
US 20200394793A1 · Namias · 2020 [cited by examiner]
US 20210059623A1 · Straka · 2021 [cited by examiner]
US 20210209757A1 · Min · 2021 [cited by examiner]
US 20210236080A1 · Herrmann · 2021 [cited by examiner]
US 20210374950A1 · Gao · 2021 [cited by examiner]
US 20220125323A1 · Smith · 2022 [cited by examiner]
H. Hong et al, “Automatic vessel extraction by patient motion correction and bone removal in brain CT angiography”, International Congress Series, vol. 1281, pp. 369-374, 2005 (Year: 2005). [cited by examiner]
X. Wang et al, “Skeleton-based cerebrovascular quantitative analysis”, BMC Medical Imaging, vol. 16, No. 68, pp. 1-15, 2016 (Year: 2016). [cited by examiner]
M. Zreik et al, “A Recurrent CNN for Automatic Detection and Classification of Coronary Artery Plaque and Stenosis in Coronary CT Angiography”, IEEE Transactions on Medical Imaging, vol. 38, No. 7, Jul. 2019 (Year: 2019… [cited by examiner]
G. Chen et al, “Automated computer assisted detection system for cerebral aneurysms in time of fight magnetic resonance angiography using fully convolutional network”, BioMedical Engineering OnLine, vol. 19, No. 38, pp.… [cited by examiner]
J. Soun et al, “Artificial Intelligence and Acute Stroke Imaging”, American Journal of Neuroradiology, vol. 42, No. 1, pp. 2-11, Jan. 2021 (Year: 2021). [cited by examiner]
R. Rava et al, “Validation of an artificial intelligence-driven large vessel occlusion detection algorithm for acute ischemic stroke patients”, The Neuroradiology Journal, vol. 34, No. 5, pp. 408-417, 2021 (Year: 2021). [cited by examiner]
A. Yahav-Dovrat et al, “Evaluation of Artificial Intelligence-Powered Identification of Large-Vessel Occlusions in a Comprehensive Stroke Center”, American Journal of Neuroradiology, vol. 42, pp. 247-254, Feb. 2021 (Yea… [cited by examiner]
P. Cimflova et al, “Validation of a machine learning software tool for automated large vessel occlusion detection in patients with suspected acute stroke”, Neuroradiology, vol. 64, pp. 2245-2255, May 2022 (Year: 2022). [cited by examiner]
Y. Wang et al, “A deep symmetry convnet for stroke lesion segmentation”, 2016 IEEE International Conference on Image Processing (ICIP), pp. 111-115, 2016 (Year: 2016). [cited by examiner]
G. Praveen et al, “Ischemic stroke lesion segmentation using stacked sparse autoencoder”, Computers in Biology and Medicine, vol. 99, pp. 38-52, May 2018 (Year: 2018). [cited by examiner]
Y. Wang et al, “A 3D Cross-Hemisphere Neighborhood Difference Convnet for Chronic Stroke Lesion Segmentation”, 2019 IEEE International Conference on Image Processing (ICIP), pp. 1545-1549, 2019 (Year: 2019). [cited by examiner]
A. Barman et al, “Determining Ischemic Stroke From CT-Angiography Imaging Using Symmetry-Sensitive Convolutional Networks”, 2019 IEEE International Symposium on Biomedical Imaging, pp. 1873-1877, Apr. 2019 (Year: 2019). [cited by examiner]
You et al, “3D dissimilar-siamese-u-net for hyperdense Middle cerebral artery sign segmentation”, Computerized Medical Imaging and Graphics, vol. 90, pp. 1-13, 2021 (Year: 2021). [cited by examiner]
Malhotra et al, “Ischemic strokes due to large-vessel occlusions contribute disproportionately to stroke-related dependence and death: a review”, Frontiers Neurology, 2017, pp. 1-6. [cited by applicant]
Amukotuwa et al, “Automated Detection of Intracranial Large Vessel Occlusions on Computed Tomography Angiography: A Single Center Experience”, Stroke, 2019, vol. 50, pp. 2790-2798. [cited by applicant]
Murray et al, “Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: a systematic review”, J Neurointerv Surg, 2019, pp. 1-10. [cited by applicant]
Ghesu et al, “Multi-Scale Deep Reinforcement Learning for Real-Time 3D-Landmark Detection in CT Scans”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, pp. 1-14. [cited by applicant]
Yang et al, “Automatic liver segmentation using an adversarial image-to-image network”, International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 1-9. [cited by applicant]
U.S. Appl. No. 17/449,263, filed Sep. 29, 2021, 43 pgs. [cited by applicant]
U.S. Appl. No. 17/449,298, filed Sep. 29, 2021, 40 pgs. [cited by applicant]
Extended European Search Report (EESR) mailed Dec. 7, 2023 in corresponding European Patent Application No. 23180035.0. [cited by applicant]
Barman Arko et al: “Determining Ischemic Stroke From CT-Angiography Imaging Using Symmetry-Sensitive Convolutional Networks”, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), IEEE, Apr. 8, 2019 … [cited by applicant]
You Jia et al: “3D dissimilar-siamese-u-net for hyperdense Middle cerebral artery sign segmentation”, Computerized Medical Imaging and Graphics, Pergamon Press, New York, NY, US, vol. 90, Mar. 14, 2021 (Mar. 14, 2021). [cited by applicant]
Wang Yan-Ran et al: “A 3D Cross-Hemisphere Neighborhood Difference Convnet for Chronic Stroke Lesion Segmentation” 2019 IEEE International Conference On Image Processing (ICIP), IEEE, Sep. 22, 2019 (Sep. 22, 2019), pp. … [cited by applicant]