Database element retrieval by example

• US 6,230,154 B1
• Filed: 07/15/1998
• Issued: 05/08/2001
• Est. Priority Date: 07/15/1997
• Status: Expired due to Fees

• Current Assignee: Morphometrix Technologies Incorporated
• Original Assignee: Morphometrix Technologies Incorporated
• Inventors: Lappa, Iouri, Raz, Ryan S.
• Primary Examiner(s): Black, Thomas
• Assistant Examiner(s): DO, THUY T
• Application Number:
  US09/115,608
• Time in Patent Office: 1,028 Days
• Field of Search: 707/1, 707/3, 707/4, 707/5, 707/7, 707/100, 395/605, 395/602, 395/600, 395/414, 364/419
• US Class Current: 707/740
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/60 relating to pathologies
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A system and method for database element retrieval. A query comprises identifying which elements in the database are close or similar to an example which is specified in the query. The query is performed by defining a hyper-box that surrounds the example in the database space. Once the hyper-box is defined, the elements contained within the hyper-box will be close or similar to the example in the query. The elements contained in the hyper-box may be subsequently ranked in the database space using a Euclidean concept of distance.

Claims

1. A database element retrieval system comprising:

(a) means for storing a plurality of elements, said elements having parameters defining characteristics of said elements, and said elements being stored and classified based on one or more of said parameters;

(b) means for processing an external query, said means for processing including,

(i) means for generating search parameters associated with said query,

(ii) means for determining a classification measure for said query, said classification measure being based on the search parameters for said query, and said classification measure providing a measure of similarity between the search parameters for said query and the parameters associated with elements store din the database,

(iii) means for setting a search range in the database for said query,

(iv) means for establishing a search space in the database, said search space being based on said search range and said classification measure,

(v) means for retrieving a plurality of elements from said search space in response to said query.

2. A method for retrieving one or more elements from a database in response to a query, said method comprising the steps of:

(a) generating search parameters associated with said query;

(b) determining a classification measure for said query, said classification measure being based on the search parameters for said query, and said classification measure providing a measure of similarity between the search parameters for said query and the parameters associated with elements stored in the database;

(c) setting a search range in the database for said query;

(d) establishing a search space in the database, said search space being based on said search range and said classification measure;

(e) retrieving a plurality of elements from said search space in response to said query.

3. A method for creating a collection of elements for a database, said elements comprising digital representations of cytological specimens, said method comprising the steps of:

(a) measuring parameters associated with each of the digital representations, said parameters including size, colour, shape or texture of objects appearing in said digital representations;

(b) classifying said elements on the basis of similarities between said measured parameters.

4. A database system for retrieving one or more digital representations of cytological specimens in response to a query, said database system comprising:

(a) means for storing a plurality of digital representations of cytological specimens;

(b) means for determining digital representations in the database which are similar to the query, said similarity being based on measured parameters associated with said digital representations; and

(c) means for retrieving said similar digital representations.

5. A method for retrieving one or more digital representations of cytological specimens from a database in response to a query, said method comprising the steps of:

(a) determining one or more digital representations similar to the query, said similarity being based on parameters associated with the digital representations;

(b) retrieving said similar digital representations from the database in response to said query.

6. A database retrieval system for digital representations of cytological specimens, said database retrieval system comprising:

(a) means for storing a plurality said digital representations, said digital representations having parameters defining characteristics of said digital representations, and said digital representations being stored and classified based on one or more or said parameters;

(b) means for processing an external query, said means for processing including,

(i) means for generating search parameters associated with said query,

(ii) means for determining a classification measure for said query, said classification measure being based on the search parameters for said query, and said classification measure providing a measure of similarity between the search parameters for said query and the parameters with digital representations stored in the database,

(iii) means for setting a search range in the database for said query,

(iv) means for establishing a search space in the database, said search space being based on said search range and said classification measure,

(v) means for retrieving a plurality of digital representations from said search space in response to said query.