Fujifilm has been granted a patent for a method, system, and computer program that transparently determines the accuracy of image analysis and processing software. The program code automatically launches a graphical user interface (window) alongside the viewer, annotates a region of the image, calculates values based on the annotation, compares them to values calculated by the software, and identifies discrepancies caused by calculation errors, displaying the reasons for each discrepancy. GlobalData’s report on Fujifilm 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 Fujifilm, AI-assisted medical imaging was a key innovation area identified from patents. Fujifilm's grant share as of September 2023 was 31%. Grant share is based on the ratio of number of grants to total number of patents.
Patent granted for method to determine accuracy of image analysis software
A recently granted patent (Publication Number: US11775153B2) describes a computer-implemented method for identifying and addressing calculation errors in software. The method involves determining when an image is selected and displayed in a software viewer, launching a graphical user interface window that displays the selected image, and automatically annotating a region of the image based on a specification document. The method then obtains instructions for calculating a set of values based on the annotation and compares these calculated values to values obtained from the software. If discrepancies outside of a predefined tolerance are identified, the method determines the reason for each discrepancy, which is displayed in the window.
The method also includes the ability to initiate actions to address the discrepancies, such as clearing the annotation and re-annotating the region of the image to visually confirm the reason for each discrepancy. The reasons for discrepancies can include higher precision calculations in the method compared to the software, as well as issues like edge pixel cases and rounding errors.
The patent also describes a system that includes one or more processors, memory, and program instructions for executing the method. The system can initiate actions to address discrepancies and position the graphical user interface window on the screen to avoid overlapping with the viewer.
Additionally, the patent mentions the use of Digital Imaging and Communications in Medicine (DICOM) images and provides a list of values that can be calculated, such as diameter, volume, peak standard uptake value (SUV), area, and standard deviation.
Furthermore, the patent includes a computer program product that stores instructions for executing the method. This program product can be used in conjunction with an ultrasound machine to obtain ultrasound data, provide inferences and confidence levels for each image, display images and inferences concurrently, and transmit inputs to the ultrasound machine for effecting changes.
Overall, this patent presents a computer-implemented method and system for identifying and addressing calculation errors in software, particularly in the context of image analysis. The method allows for automatic annotation, calculation, and comparison of values, as well as the determination and display of reasons for discrepancies. The system and computer program product provide additional functionalities and applications in the field of ultrasound imaging.
To know more about GlobalData’s detailed insights on Fujifilm, 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.
