Processing

Please wait...

Settings

Settings

Goto Application

1. WO1996027846 - METHOD AND SYSTEM FOR THE DETECTION OF LESIONS IN MEDICAL IMAGES

Publication Number WO/1996/027846
Publication Date 12.09.1996
International Application No. PCT/US1996/002439
International Filing Date 04.03.1996
Chapter 2 Demand Filed 13.09.1996
IPC
G06T 5/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
5Image enhancement or restoration
G06T 5/30 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
5Image enhancement or restoration
20by the use of local operators
30Erosion or dilatation, e.g. thinning
G06T 7/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
CPC
G06K 9/482
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
48by coding the contour of the pattern ; contour related features or features from contour like patterns, e.g. hand-drawn point-sequence
482analysing the spectrum of the contour, e.g. Fourier expansion
G06T 2207/20056
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20048Transform domain processing
20056Discrete and fast Fourier transform, [DFT, FFT]
G06T 2207/20156
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20112Image segmentation details
20156Automatic seed setting
G06T 2207/30068
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
30068Mammography; Breast
G06T 2207/30096
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
30096Tumor; Lesion
G06T 7/0012
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
0002Inspection of images, e.g. flaw detection
0012Biomedical image inspection
Applicants
  • ARCH DEVELOPMENT CORPORATION [US]/[US]
Inventors
  • BICK, Ulrich
  • GIGER, Maryellen, L.
Agents
  • KUESTERS, Eckhard, H.
Priority Data
08/398,30703.03.1995US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) METHOD AND SYSTEM FOR THE DETECTION OF LESIONS IN MEDICAL IMAGES
(FR) TECHNIQUE DE DETECTION DE LESIONS SUR DES IMAGES MEDICALES ET DISPOSITIF CORRESPONDANT
Abstract
(EN)
A method and system for the automated detection of lesions in the medical images. Medical images, such as mammograms are segmented and optionally processing with peripheral enhancement and/or modified median filtering. A modified morphological open operation (104-106) and filtering with a modified mass filter (107-109) are performed for the initial detection of circumscribed lesions. Then, the lesions are matched using a deformable shape template with Fourier descriptors (110-112). Characterization of the match is done using simulated annealing, and measuring the circularity and density characteristics of the suspected lesion. The procedure is performed iteratively at different spatial resolution in which at each resolution step a specific lesion size is detected. The detection of the lesion leads to a localization of a suspicious region and thus the likelyhood of cancer.
(FR)
L'invention porte sur une technique permettant la détection automatique de lésions sur des images médicales ainsi que sur le dispositif correspondant. On segmente des images médicales, des mammogrammes par exemple, que l'on traite éventuellement par un renforcement périphérique et/ou un filtrage médian modifié. On procède à une chirurgie morphologique ouverte (104, 106) ainsi qu'à un filtrage à l'aide d'un filtre de masse modifié (107, 109) aux fins de la détection initiale de lésions circonscrites. On fait correspondre des lésions à des descripteurs de Fourier (110, 112) à l'aide d'un gabarit déformable de forme et l'on procède à la caractérisation de la concordance par un recuit simulé ainsi que par la mesure des caractéristiques de circularité et de densité de la lésion suspectée. On procède de manière itérative selon une résolution spatiale différente dans laquelle chaque pas de résolution permet de détecter une taille spécifique de lésion. Cette détection de la lésion conduit à la localisation de la région suspecte et, partant, de la présence vraisemblable d'un cancer.
Latest bibliographic data on file with the International Bureau