Atrial fibrillation auxiliary analysis method based on cross-model mutual teaching semi-supervision

• Main Authors: SU WEIHUA, WANG YUANQUAN, GUO SHIJIE, XIANG SHUN, WANG JIANRU
• Format: Patent
• Language: Chinese; English
• Published: 03.01.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

According to the atrial fibrillation auxiliary analysis method based on cross-model mutual teaching semi-supervision, a deformable Transform is introduced, a left atrium segmentation model is constructed, the left atrium segmentation model can extract long dependence information between images, and the space information of heart nuclear magnetic resonance images is fully utilized to improve the segmentation precision of a left atrium area; secondly, a semi-supervised training framework based on cross-model mutual teaching is built to train a left atrium segmentation model, the trained left atrium segmentation model is utilized to segment the 3D heart nuclear magnetic resonance image, and a left atrium segmentation prediction map is generated; and finally, reconstructing the generated left atrium segmentation prediction map, calculating four clinical indexes, namely the diameter, the volume, the volume index and the sphericity degree of the left atrium, and referring to a normal reference value range and combi