Optical coherence tomography-based system for diagnosis of high-risk lesion and diagnosis method therefor

Patent metadata

Field	Value
Publication number	US-2022335601-A1
Application number	US-202017633113-A
Country	US
Kind code	A1
Filing date	Aug 5, 2020
Priority date	Aug 5, 2019
Publication date	Oct 20, 2022
Grant date	—

Abstract

The disclosure purposes to provide an optical coherence tomography (OCT)-based system for diagnosing a high risk lesion such as a vulnerable atheromatous plaque by using an artificial intelligence model through deep learning. A deep learning-based diagnostic method of diagnosing a high risk lesion of a coronary artery includes: acquiring an OCT image of a coronary artery lesion of a patient; extracting a first feature of a thin cap from the OCT image; setting a region of interest included in the OCT image on a basis of the first feature; and determining whether the region of interest includes a high risk lesion.

First claim

1 . A deep learning-based diagnostic method of diagnosing a high risk lesion of a coronary artery, the deep learning-based diagnostic method comprising:
an image acquiring step of acquiring an optical coherence tomography (OCT) image of a coronary artery lesion of a patient; a feature extraction step of extracting a first feature of a thin cap from the OCT image; a region-of-interest setting step of setting a region of interest included in the OCT image on a basis of the first feature; and a high risk determination step of determining whether the region of interest includes a high risk lesion.

2 . The deep learning-based diagnostic method of claim 1 , wherein
the first feature includes information about a fibrous cap thickness (FCT), the feature extraction step further comprises a step of extracting a second feature about a necrotic core from the OCT image, and the high risk determination step comprises determining whether the region of interest includes a thin cap fibroatheroma (TCFA), on a basis of the first feature and the second feature.

3 . The deep learning-based diagnostic method of claim 1 , wherein the region-of-interest setting step comprises indicating a marker corresponding to the region of interest.

4 . The deep learning-based diagnostic method of claim 1 , further comprising, when the OCT image is determined to include a high risk lesion, a lesion display step of displaying a lesion indicating a region corresponding to the high risk lesion, wherein the region corresponding to the high risk lesion comprises a region including a thin cap fibroatheroma (TCFA).

5 . The deep learning-based diagnostic method of claim 4 , wherein the lesion display step is performed by using at least one of a Grad-CAM and a guided Grad-CAM.

6 . A deep learning-based diagnostic apparatus of diagnosing a high risk lesion of a coronary artery, the deep learning-based diagnostic apparatus comprising:
an image acquiring unit configured to acquire an optical coherence tomography (OCT) image of a coronary artery lesion of a patient; a feature extraction unit configured to extract a first feature of a thin cap from the OCT image; a region-of-interest setting unit configured to set a region of interest included in the OCT image on a basis of the first feature; and a high risk determination unit configured to determine whether the region of interest includes a high risk lesion.

Assignees

• Asan Found
• Univ Ulsan Found Ind Coop

Inventors

• Kang Soo Jin
• Min Hyun Seok

Classifications

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• A61B5/02021

  Determining capillary fragility · CPC title

• A61B5/7275

  Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor · CPC title

• A61B5/02007

  Evaluating blood vessel condition, e.g. elasticity, compliance · CPC title