V5med Inc.

Chien Ting Yang

Tzu-Kuei Shen

Guang-hao Suen

Linda Siana

Kuo-Tung Hung

Liang-wei Sheu

Yu Hsun Kao

A high-speed automatic scanning system for interpreting images with AI assistance and method using the same are provided. The system includes a control computer and an image capture platform. Scanning parameters of the image capture platform, including a helically-clockwise or helically-counterclockwise scanning path, is set by the control computer. After the scanning path is selected, the image capture platform aligns a camera to focus on a central block and respectively captures images of the central block's sub-blocks. Until all the blocks have been scanned, the image capture platform repeats the following procedure: moving the focusing position to a next neighboring block according to the scanning path, focusing on the next neighboring block, and capturing images of the sub-blocks of the next neighboring block. The present invention can fast perform scanning, exempted from performing focusing for every image, reducing the cycles and time of focusing.

High-speed automatic scanning system for interpreting images with AI assistance and method using the same

An AI-assisted automatic labeling system and a method thereof are disclosed. The method comprises steps: selecting images from microscopic images as candidate images, using a pre-labeling module to automatically label cells in the candidate images, and dividing the labeled images into training data and verification data; using a training module and the training data to train a basic model; using a verification module to verify and modify the basic model, wherein the verification module respectively verifies at least one cell area and at least one background area of the verification data to converge the basic model and form an automatic labeling model; using the automatic labeling model to automatically label cells in redundant images of the microscopic images. The basic model trained by the present invention can use few labeled images to perform regressive training and verification and then automatically labels the redundant images accurately and efficiently.

AI-assisted automatic labeling system and method

Growing community of inventors

HSINCHU, Taiwan

Chien Ting Yang