18113753. MODULE FOR IDENTIFICATION AND CLASSIFICATION TO SORT CELLS BASED ON THE NUCLEAR TRANSLOCATION OF FLUORESCENCE SIGNALS simplified abstract (Sony Group Corporation)

MODULE FOR IDENTIFICATION AND CLASSIFICATION TO SORT CELLS BASED ON THE NUCLEAR TRANSLOCATION OF FLUORESCENCE SIGNALS

Organization Name

Sony Group Corporation

Inventor(s)

Ming-Chang Liu of San Jose CA (US)

Su-Hui Chiang of San Jose CA (US)

Haipeng Tang of Sunnyvale CA (US)

Michael Zordan of Boulder Creek CA (US)

Ko-Kai Albert Huang of Cupertino CA (US)

MODULE FOR IDENTIFICATION AND CLASSIFICATION TO SORT CELLS BASED ON THE NUCLEAR TRANSLOCATION OF FLUORESCENCE SIGNALS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18113753 titled 'MODULE FOR IDENTIFICATION AND CLASSIFICATION TO SORT CELLS BASED ON THE NUCLEAR TRANSLOCATION OF FLUORESCENCE SIGNALS

Simplified Explanation

The abstract describes an Image Activated Cell Sorting (IACS) classification workflow that involves using a neural network-based feature encoder to extract features from cell images, clustering cells based on these features, selecting clusters to sort based on the images, fine-tuning a classification network based on the selected clusters, and using the refined network for real-time cell sorting.

• Neural network-based feature encoder extracts features from cell images
• Cells are automatically clustered based on extracted features
• Clusters are identified for sorting based on cell images
• Classification network is fine-tuned based on selected clusters
• Refined network is used for real-time cell sorting

Potential Applications

This technology can be applied in various fields such as medical research, drug discovery, and biological studies where sorting and classifying cells based on images is required.

Problems Solved

This technology solves the problem of efficiently sorting and classifying cells based on their images, which can be time-consuming and error-prone when done manually.

Benefits

The benefits of this technology include increased accuracy in cell sorting, faster processing times, and the ability to handle large volumes of cell images efficiently.

Potential Commercial Applications

Potential commercial applications of this technology include automated cell sorting systems for research laboratories, pharmaceutical companies, and biotechnology firms.

Possible Prior Art

One possible prior art in this field is the use of traditional image processing techniques for cell sorting and classification, which may not be as efficient or accurate as the neural network-based approach described in this patent application.

Unanswered Questions

How does the neural network-based feature encoder handle variations in cell images?

The article does not provide specific details on how the feature encoder adapts to different types of cell images and variations in image quality.

What is the scalability of this technology for processing large datasets of cell images?

The scalability of the classification network and clustering algorithm for handling large volumes of cell images is not discussed in the article.

Original Abstract Submitted

An Image Activated Cell Sorting (IACS) classification workflow includes: employing a neural network-based feature encoder (or extractor) to extract features of cell images; automatically clustering cells based on extracted cell features; identifying a cluster to pick which cluster(s) to sort based on the cell images; fine-tuning a classification network based on the cluster(s) selected; and once refined, the classification network is used to sort cells for real-time live sorting.