18620434. Medical Condition Visual Search simplified abstract (Google LLC)

From WikiPatents
Jump to navigation Jump to search

Medical Condition Visual Search

Organization Name

Google LLC

Inventor(s)

Peggy Yen Phuong Bui of San Francisco CA (US)

Bianca Madalina Buisman of Ruschlikon (CH)

Quang Anh Duong of San Francisco CA (US)

Anastasia Martynova of Alameda CA (US)

Ayush Jain of Los Altos CA (US)

Yuan Liu of Santa Clara CA (US)

Jonathan David Krause of Mountain View CA (US)

Amit Sanjay Talreja of Santa Clara CA (US)

Rajeev Vijay Rikhye of Fremont CA (US)

Mahvish A. Nagda of Palo Alto CA (US)

Pinal Bavishi of Sunnyvale CA (US)

Christopher James Eicher of Cupertino CA (US)

Abigail Ward of San Mateo CA (US)

Jieming Yu of Jersey City NJ (US)

Louis Wang of San Francisco CA (US)

Dounia Berrada of Saratoga CA (US)

Dale Richard Webster of Redwood City CA (US)

Harshit Kharbanda of Pleasanton CA (US)

Igor Bonaci of Wollerau (CH)

Kai Yu of San Francisco CA (US)

Ke Lan of San Jose CA (US)

[[:Category:Kaan Y�cer of San Francisco CA (US)|Kaan Y�cer of San Francisco CA (US)]][[Category:Kaan Y�cer of San Francisco CA (US)]]

Willa Angel Chen Miller of Sunnyvale CA (US)

Lars Thomas Hansen of Adliswil (CH)

Medical Condition Visual Search - A simplified explanation of the abstract

This abstract first appeared for US patent application 18620434 titled 'Medical Condition Visual Search

Simplified Explanation: The patent application describes systems and methods for diagnostic visual search using classification models to determine search query intent and predict potential diagnoses based on images.

  • Uses classification models to determine search query intent and predict potential diagnoses
  • Processes images to identify body parts and descriptive diagnostic search queries
  • Utilizes conditions classification model to predict condition classifications based on intent determination
  • Provides condition information based on predicted condition classifications

Key Features and Innovation:

  • Utilizes multiple classification models for diagnostic visual search
  • Processes images to determine search query intent and predict potential diagnoses
  • Provides condition information based on predicted condition classifications

Potential Applications:

  • Medical diagnosis and healthcare applications
  • Image recognition and classification systems
  • Diagnostic search engines and tools

Problems Solved:

  • Improves accuracy and efficiency of diagnostic visual search
  • Enhances the process of predicting potential diagnoses based on search queries
  • Facilitates access to condition information for users

Benefits:

  • Faster and more accurate diagnosis predictions
  • Improved search query intent determination
  • Enhanced user experience in accessing condition information

Commercial Applications: Diagnostic Visual Search Systems for Healthcare and Medical Industries

Prior Art: Further research can be conducted in medical imaging technologies and diagnostic search algorithms.

Frequently Updated Research: Stay updated on advancements in medical imaging technologies and machine learning algorithms for diagnostic visual search.

Questions about Diagnostic Visual Search: 1. How does the use of classification models improve the accuracy of diagnostic visual search? 2. What are the potential limitations of using image processing for determining search query intent in diagnostic visual search?


Original Abstract Submitted

Systems and methods for diagnostic visual search can include processing a search query with a plurality of classification models to determine a search query intent and predict potential diagnosis. The search query can include an image that is processed to determine the presence of a body part and may be processed to determine if the search query is descriptive of a diagnostic search query. Based on the intent determination, the image may then be processed by a conditions classification model to determine one or more predicted condition classifications. Condition information can then be obtained and provided based on the one or more predicted condition classifications.