Ever Fortune.ai Co., Ltd.

China Medical University Hospital

Ken Ying-Kai Liao

Tzung-Chi Huang

Fuu-Jen Tsai

Jiaxin Yu

Christian Pascal Tchou

Chi-Kun Wang

Yang Hsien Lin

Po-Hsin Hsieh

A method for training a chromosome recognition model includes: identifying objects on a karyotype image, obtaining a mask and a minimal bounding box of each of the chromosome objects, and obtaining an organized image that includes a set of organized chromosome objects; generating a simulated metaphase image in which the chromosome objects are randomly reorganized; detecting the plurality of chromosome objects on the simulated metaphase image; obtaining a recalibrated image in which the chromosome objects are separated from one another, so as to train the chromosome recognition model for identifying feature of chromosome objects included in an image.

Method and system for training a separation of overlapping chromosome recognition model based on simulation

A system for real-time determination of the hand bone age using a personal device essentially include: a cloud computing platform storing a first marked database, an artificial neural network-based bone age model, and a comparison logic, wherein the first marked database at least has a hand bone image and the corresponding feature marking data; and a to-be-compared image providing device for downloading a to-be-compared hand bone image from a cloud-based to-be-compared image database. A personal device can be used to obtain a to-be-compared hand bone image from the to-be-compared image providing device and upload this image to the cloud computing platform in order for the cloud computing platform to find, through comparison, the hand bone image in the bone age model that is the most similar to the uploaded image and then transmit to the personal device the interpretation data corresponding to the hand bone image found.

System and method for real-time determination of hand bone age using personal device

An assisted detection system of breast tumor includes an image capturing unit and a non-transitory machine readable medium. The non-transitory machine readable medium storing a program which, when executed by at least one processing unit, determines a breast tumor type of the subject and predicts a probability of a tumor location of the subject. The program includes a reference database obtaining module, a first image preprocessing module, an autoencoder module, a classifying module, a second image preprocessing module and a comparing module.

Assisted detection model of breast tumor, assisted detection system thereof, and method for assisted detecting breast tumor

Growing community of inventors

Taichung, Taiwan

Ken Ying-Kai Liao