Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 25.01.2022 at 9:00 AM CET
Settings

Settings

Goto Application

1. WO2021219727 - OCT EN FACE PATHOLOGY SEGMENTATION USING CHANNEL-CODED SLABS

Publication Number WO/2021/219727
Publication Date 04.11.2021
International Application No. PCT/EP2021/061147
International Filing Date 28.04.2021
IPC
G06T 7/00 2017.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
A61B 3/12 2006.1
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
3Apparatus for testing the eyes; Instruments for examining the eyes
10Objective types, i.e. instruments for examining the eyes independent of the patients perceptions or reactions
12for looking at the eye fundus, e.g. ophthalmoscopes
CPC
A61B 3/102
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
3Apparatus for testing the eyes; Instruments for examining the eyes
10Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
102for optical coherence tomography [OCT]
A61B 3/12
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
3Apparatus for testing the eyes; Instruments for examining the eyes
10Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
12for looking at the eye fundus, e.g. ophthalmoscopes
A61B 3/1241
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
3Apparatus for testing the eyes; Instruments for examining the eyes
10Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
12for looking at the eye fundus, e.g. ophthalmoscopes
1241specially adapted for observation of ocular blood flow, e.g. by fluorescein angiography
G06T 2207/10101
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
10Image acquisition modality
10072Tomographic images
10101Optical tomography; Optical coherence tomography [OCT]
G06T 2207/20084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20084Artificial neural networks [ANN]
G06T 2207/30041
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
30Subject of image; Context of image processing
30004Biomedical image processing
30041Eye; Retina; Ophthalmic
Applicants
  • CARL ZEISS MEDITEC, INC. [US]/[US]
  • CARL ZEISS MEDITEC AG [DE]/[DE]
Inventors
  • SISTERNES, Luis De
  • MANIVANNAN, Niranchana
Agents
  • BECK, Bernard
Priority Data
63/017,57429.04.2020US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) OCT EN FACE PATHOLOGY SEGMENTATION USING CHANNEL-CODED SLABS
(FR) SEGMENTATION DE FACE DE PATHOLOGIE PAR TCO UTILISANT DES PLAQUES À CODAGE DE CANAL
Abstract
(EN) A system and method for use with optical coherence tomography (OCT) data to identify a target pathology extracts multiple pathology-characteristic images from the OCT data. The extracted pathology-characteristic images may include a mixture of OCT structural images (including retinal layer thickness information) and OCT angiography images. Optionally, other pathology-characteristic images and data maps (mapped to corresponding positions in the OCT data), such as fundus images and visual field test maps may be accessed as additional pathology-characteristic images. Each pathology-characteristic image defines a different image channel (e.g., "color channel") per pixel in a composite, channel-coded image, which is then used to train a neural network to search for the target pathology in OCT data. The trained neural network may then receive new composite, channel-coded image and identify/segment the target pathology within the new channel-coded image.
(FR) Un système et un procédé destinés à être utilisés avec des données de tomographie par cohérence optique (TCO) pour identifier une pathologie cible, extraient de multiples images caractéristiques de pathologie à partir des données de TCO. Les images caractéristiques de pathologie extraites peuvent comprendre un mélange d'images structurales de TCO (y compris des informations d'épaisseur de couche rétinienne) et des images d'angiographie par TCO. Facultativement, d'autres images caractéristiques de pathologie et des cartes de données (mappées à des positions correspondantes dans les données de TCO), telles que des images de fond d’œil et des cartes de test de champ visuel peuvent être atteintes en tant qu'images caractéristiques de pathologie supplémentaires. Chaque image caractéristique de pathologie définit un canal d'image différent (par exemple, " canal de couleur ") par pixel dans une image composite à codage de canal qui est ensuite utilisée pour entraîner un réseau neuronal pour rechercher la pathologie cible dans des données de TCO. Le réseau neuronal entraîné peut ensuite recevoir une nouvelle image composite à codage de canal et identifier/segmenter la pathologie cible à l'intérieur de la nouvelle image à codage de canal.
Latest bibliographic data on file with the International Bureau