US 11,941,811 B2
Method for assessing cardiothoracic ratio and cardiothoracic ratio assessment system
Chin-Chi Kuo, Taichung (TW)
Assigned to CHINA MEDICAL UNIVERSITY, Taichung (TW)
Filed by China Medical University, Taichung (TW)
Filed on Jul. 28, 2021, as Appl. No. 17/386,683.
Claims priority of application No. 109138524 (TW), filed on Nov. 5, 2020.
Prior Publication US 2022/0138947 A1, May 5, 2022
Int. Cl. G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06T 7/00 (2017.01); G06T 7/12 (2017.01)
CPC G06T 7/0014 (2013.01) [G06N 3/045 (2023.01); G06T 2207/10116 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30048 (2013.01); G06T 2207/30061 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for assessing cardiothoracic ratio (CTR), comprising:
providing a testing X-ray image database of a subject;
performing a first image data classifying step, wherein the testing X-ray image database is classified by a first deep learning neural network classifier so as to obtain a testing chest X-ray image data, and the testing chest X-ray image data comprises a PA (posterior-anterior view) chest X-ray image data or an AP (anterior-posterior view) chest X-ray image data;
performing a second image data classifying step, wherein the testing chest X-ray image data is classified by a second deep learning neural network classifier so as to obtain a target chest X-ray image data;
performing a feature extracting step, wherein a diameter of thoracic cavity and a diameter of cardiac silhouette of the target chest X-ray image data are captured automatically and then trained to achieve a convergence by a third deep learning neural network classifier so as to obtain a feature of CTR; and
performing an assessing step, wherein an assessing result of CTR is obtained according to the feature of CTR by the third deep learning neural network classifier.