CellaVision has been granted a patent for a method that trains a neural network classifier to categorize digital images of biological samples. The method utilizes a training set of labeled images and associated global data to enhance classification accuracy by deriving input values and feature vectors for the neural network. GlobalData’s report on CellaVision 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 CellaVision, Cellular imaging techniques was a key innovation area identified from patents. CellaVision's grant share as of July 2024 was 47%. Grant share is based on the ratio of number of grants to total number of patents.
Method for training neural network to classify biological images
The granted patent US12051253B2 outlines a method for training a neural network classifier to categorize digital images of biological samples into specific classes. The process begins with the provision of a training set of labeled digital images, each associated with global data relevant to the respective biological sample. The method involves deriving two sets of input values: the first set pertains to specific features of the digital image, while the second set is based on the associated global data. These input values are combined into a feature vector, which the neural network classifier uses to determine the appropriate class for each image. The training process incorporates both the image data and the global data, with the specific class label serving as the correct output for the neural network.
Additionally, the patent describes various configurations of the neural network classifier, including the use of decision and feature extraction subnets, and specifies that the classifier may be a convolutional neural network. The global data can include information such as average color and calibration data from chemical reference patches on a microscope slide. The method also allows for the integration of global data into the pixel data of the digital images, enhancing the classifier's ability to accurately assign classes. Furthermore, the patent encompasses an analyzing device designed for optical analysis of biological samples, which incorporates a camera and processor to capture images and analyze global data. The invention also includes a computer-readable medium containing instructions to execute the described methods.
To know more about GlobalData’s detailed insights on CellaVision, 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.
