Automated method and system for the detection and classification of abnormal lesions and parenchymal distortions in digital medical images
US5133020A · kind A · utility
Assignee
Inventors
Key dates
| Filing date | Jul 21, 1989 |
| Grant date | Jul 21, 1992 |
| Priority date | — |
| Expiry date | Jul 21, 2009 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30068
- WIPO fieldMedical technology
- WIPO sectorInstruments
Abstract
A method for automated analysis of abnormalities in the form of lesions and parenchymal distortions using digital images, including generating image data from respective of digital images derived from at least one selected portion of an object, for example, from mammographical digital images of the left and right breasts. The image data from each of the digital images are then correlated to produce correlated data in which normal anatomical structured background is removed. The correlated data is then searched using one or more predetermined criteria to identify in at least one of the digital images an abnormal region represented by a portion of the correlated data which meets the predetermined criteria. The location of the abnormal region is then indicated, and the indicated location is then subjected to classification processing to determine whether or not the abnormal region is benign or malignant. Classification is performed based on the degree of spiculations of the identified abnormal region. In order to enhance the process of searching for abnormal regions, in one embodiment the gray-level frequency-distributions of two or more images are matched by matching the cumulative g…
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.