Method for assisting corneal severity identification using unsupervised machine learning

Patent metadata

Field	Value
Publication number	US-10945598-B2
Application number	US-201916269221-A
Country	US
Kind code	B2
Filing date	Feb 6, 2019
Priority date	Feb 6, 2019
Publication date	Mar 16, 2021
Grant date	Mar 16, 2021

Abstract

A method for assisting corneal severity identification, the method comprising obtaining a corneal configuration data set of a cornea to be examined by a tomography such as an optical coherence tomography; visualizing the corneal configuration data set of the cornea to be examined along with a number of pre-existing corneal configuration data sets of disorder corneas, disorder-suspect corneas and normal corneas obtained by the tomography using t-distributed Stochastic Neighbor Embedding in a two or three dimensional map, and judging corneal severity from the map.

First claim

The invention claimed is:

1. A method for assisting corneal severity identification, the method comprising:
obtaining a corneal configuration data set of a cornea to be examined by a tomography;
visualizing the corneal configuration data set of the cornea to be examined along with a number of pre-existing corneal configuration data sets of disorder corneas, disorder-suspect corneas and normal corneas obtained by the tomography using t-distributed Stochastic Neighbor Embedding in a two or three dimensional map, and
locating a visualized part of the corneal configuration data set of the cornea to be examined on the map to judge corneal severity from a cluster which the located visualized part belongs to, wherein the cluster comprises visualized parts of the pre-existing corneal configuration data sets of disorder corneas, disorder-suspect corneas or normal corneas.

2. The method according to claim 1 , wherein the tomography is an optical coherence tomography.

3. A method for assisting corneal severity identification, the method comprising:
obtaining a corneal configuration data set of a cornea to be examined by a tomography;
visualizing the corneal configuration data set of the cornea to be examined along with a number of pre-existing corneal configuration data sets of disorder corneas, disorder-suspect corneas and normal corneas obtained by the tomography using t-distributed Stochastic Neighbor Embedding in a two or three dimensional map, and
judging corneal severity from the map;
wherein the corneal severity is at least one selected from the group consisting of keratoconus severity, bullous keratopathy severity, walleye severity, keratoleukoma severity, keratohelcosis severity, herpes corneae severity, corneal chemical burn severity, corneal thermal burn severity, and degeneratio corneae severity.

4. A method for assisting corneal severity identification, the method comprising:
obtaining a corneal configuration data set of a cornea to be examined by a tomography;
visualizing the corneal configuration data set of the cornea to be examined along with a number of pre-existing corneal configuration data sets of disorder corneas, disorder-suspect corneas and normal corneas obtained by the tomography using t-distributed Stochastic Neighbor Embedding in a two or three dimensional map, and
judging corneal severity from the map;
wherein the corneal configuration data set comprises at least one of a 2D analysis of ACA viewing surface, a 2D analysis of CCT/ACD viewing surface, STAR360°, analysis of lens morphology on 2D Result, analysis of lens morphology on 3D Result, analysis of corneal morphology and reference point.

5. The method according to claim 4 , wherein the 2D analysis of ACA viewing surface comprises at least one of AOD500, A0D750, ARA500, ARA750, TISA500, TISA750, TIA500, and TIA750.

6. The method according to claim 4 , wherein the 2D analysis of CCT/ACD viewing surface comprises at least one of CCT, ACD Endo., LV, ACW, CCT, ACD[Epi.], ACD[Endo.], Vault, CLR and ATA.

7. The method according to claim 4 , wherein the STAR360° comprises at least one of AOD250, AOD500, AOD750, ARA250, ARA500, ARA750, TISA250, TIA500, TIA750, CCT, ACD Endo., LV, ACW, AC.Area, IT750, IT2000, I-Curv. and ITC.

8. The method according to claim 4 , wherein the analysis of lens morphology on 2D Result comprises at least one of Front R, Thickness, Diameter, Decentration and Tilt.

9. The method according to claim 4 , wherein the analysis of lens morphology on 3D Result comprises at least one of Front R, Front Rs, Front Rf, Back R, Back Rs, Back Rf, Thickness, Diameter, Decentration, and Tilt.

10. The method according to claim 4 , wherein the analysis of corneal morphology comprises at least one of Ks, Kf, CYL, ACCP, ECC, AA, Apex, Thinnest, and ESI.

11. The method according to claim 4 , wherein the reference point comprises at least one of SS, AR, IR, IRT, and EP.

12. A method for assisting corneal severity identification, the method comprising:
obtaining a corneal configuration data set of a cornea to be examined by a tomography;
visualizing the corneal configuration data set of the cornea to be examined along with a number of pre-existing corneal configuration data sets of disorder corneas, disorder-suspect corneas and normal corneas obtained by the tomography using t-distributed Stochastic Neighbor Embedding in a two or three dimensional map, and
judging corneal severity from the map;
wherein the corneal configuration data set comprises at least one of DSI, OSI, CSI, SD_P(4 mm), CV_P(4 mm), ACP(3 mm), RMS_E(4 mm), SR_E(4 mm), SR_H(4 mm), CSI_T, SD_T(4 mm), and CV_T(4 mm).

13. A method for assisting corneal severity identification, the method comprising:
obtaining a corneal configuration data set of a cornea to be examined by a tomography;
visualizing the corneal configuration data set of the cornea to be examined along with a number of pre-existing corneal configuration data sets of disorder corneas, disorder-suspect corneas and normal corneas obtained by the tomography using t-distributed Stochastic Neighbor Embedding in a two or three dimensional map, and
judging corneal severity from the map;
wherein the tomography is an anterior eye part optical coherence tomography.

14. A method for assisting corneal severity identification, the method comprising:
obtaining a corneal configuration data set of a cornea to be examined by a tomography;
visualizing the corneal configuration data set of the cornea to be examined along with a number of pre-existing corneal configuration data sets of disorder corneas, disorder-suspect corneas and normal corneas obtained by the tomography using t-distributed Stochastic Neighbor Embedding in a two or three dimensional map, and
judging corneal severity from the map;
wherein the tomography is a swept-source optical coherence tomography.

Assignees

• Univ Jichi Medical
• Hayashi Takahiko

Inventors

• Yousefi Siamak
• Takahashi Hidenori
• Hayashi Takahiko

Classifications

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• A61B3/1005

  for measuring distances inside the eye, e.g. thickness of the cornea (A61B3/11 takes precedence) · CPC title

• A61B3/102

  for optical coherence tomography [OCT] · CPC title

• A61B3/0025

  characterised by electronic signal processing, e.g. eye models · CPC title

• A61B3/107 Primary

  for determining the shape or measuring the curvature of the cornea · CPC title