Google Inc.

Shravya R Shetty

Srinivasan Venkatachary

Trystan G Upstill

Jack Wright Menzel

Bin Liu

Abhishek Das

Krishnan Eswaran

Daniel Shing Shun Tse

Shahar Jamshy

Zvika Ben-Haim

A computer-implemented system is described for identifying and retrieving similar radiology images to a query image. The system includes one or more fetchers receiving the query image and retrieving a set of candidate similar radiology images from a data store. One or more scorers receive the query image and the set of candidate similar radiology images and generate a similarity score between the query image and each candidate image. A pooler receives the similarity scores from the one or more scorers, ranks the candidate images, and returns a list of the candidate images reflecting the ranking. The scorers implement a modelling technique to generate the similarity score capturing a plurality of similarity attributes of the query image and the set of candidate similar radiology images and annotations associated therewith. For example, the similarity attributes could be patient, diagnostic and/or visual similarity, and the modelling techniques could be triplet loss, classification loss, regression loss and object detection loss.

Similar image search for radiology

A method includes receiving a query that is unstructured for a plurality databases; determining a service requirement fulfilled by the databases from the terms of the query; determining, for each of the databases, a service requirement score for the database; selecting one of the databases based on the service requirement scores; determining, from the query, parameter values for the service requirement; providing the parameter values for a search operation for the selected database and receiving database search results responsive to the parameter values and the search operation; determining, from the database search results, a search constraint for the search query; revising the search query to include the constraint and providing the revised search query to a search engine; and providing search results identifying resources that the search engine determined to be responsive to the revised query.

Resource identification from organic and structured content

A method includes receiving a query that that is unstructured for a plurality databases; receiving data identifying resources that are determined to be responsive to the query, each resource associated with a search score that defines a respective position of the resource in an order of responsiveness to the query; determining, a service requirement from the terms of the query; determining, for each of the databases, a service requirement score for the database; for each resource that is associated with one of the databases, adjusting the search score based on the service requirement score for the database; generating search results, each search result identify a corresponding resource that was determined to be responsive to the query, and the search results being ordered according to the respective search scores and adjusted search scores of the resources.

Growing community of inventors

Mountain View, CA, United States of America

Shravya R Shetty