Hoya‘s patent describes a program that processes endoscope images using multiple learning models to generate diagnosis support information for lesions. The system includes a specialized endoscope design and outputs diagnostic data alongside model information, enhancing diagnostic accuracy through advanced machine learning techniques. GlobalData’s report on Hoya gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Hoya, AI-assisted medical imaging was a key innovation area identified from patents. Hoya's grant share as of June 2024 was 56%. Grant share is based on the ratio of number of grants to total number of patents.
Endoscope image analysis using multiple learning models
The patent US12045985B2 describes a non-transitory computer-readable storage medium and an information processing method designed to enhance the diagnostic capabilities of endoscopic imaging. The system involves an endoscope equipped with an inserter that features a distal tip with an image sensor, a bending section, and a proximal section. The endoscope is complemented by a bend-preventer and an operator that facilitates the bending of the inserter. The core functionality revolves around a processor that acquires endoscopic images and inputs them into multiple learning models, specifically neural networks, to generate diagnosis support information regarding lesions identified in the images. Notably, the learning models share the same layer configuration but are trained on different datasets, allowing for diverse outputs that can be associated with the respective models.
Additionally, the patent outlines various functionalities, including the ability to select specific learning models and display cumulative usage statistics. The system can process multiple endoscopic images captured over time, providing a comprehensive analysis of lesions by outputting diagnosis support information such as the presence, type, stage, and location of lesions. This structured approach not only aids in accurate diagnosis but also facilitates a better understanding of the differences between the learning models employed. Overall, the invention aims to improve the efficiency and accuracy of endoscopic diagnostics through advanced image processing and machine learning techniques.
To know more about GlobalData’s detailed insights on Hoya, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
