Automatic localization of cross sections corresponding to standard transesophageal echocardiographic views on computed tomography volume.
Authors
Affiliations (5)
Affiliations (5)
- Research and Development Center, Canon Medical Systems Corporation, 1385 Shimoishigami, Otawara-Shi, Tochigi, 324-8550, Japan.
- Research and Development Center, Canon Medical Systems (CHINA) CO., Ltd; No. 3, Xinyuan South Road, Chaoyang District, Beijing, 100027, People's Republic of China.
- Canon Medical Informatics, Inc. 5850 Opus Parkway, Suite 300, Minnetonka, MN, 55343, United States of America.
- Division of Cardiology, Mitsui Memorial Hospital, Kanda-Izumicho 1, Chiyoda-ku, Tokyo, 101-8643, Japan.
- Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Hongo 3-1-3, Bunkyo-ku, Tokyo, 113-8431, Japan.
Abstract
<i>Aims</i>: Preoperative observation of computed tomography (CT) cross sections corresponding to standard transesophageal echocardiographic (TEE) views is useful for treatments using TEE. However, manually locating those CT cross sections from the CT volume is time consuming. This study aimed to develop a fully automatic method to locate those CT cross sections corresponding to standard TEE views.<i>Methods</i>: Developed method crops CT volume based on the heart segmentation model if input is a chest CT. CT cross sections corresponding to standard TEE views are coarsely located from cropped chest CT or cardiac CT based on the esophagus segmentation model and the plane localization model. The coarse cross sections are refined based on the anatomical landmark detection model. Accuracies of located CT cross sections were evaluated by five-fold cross validation with comparison to manually set cross sections, using 110 CT volumes. The results were also compared to the top and the middle axial section of the heart as baselines.<i>Results</i>: The mean of rotation error, probe position error, landmark error and structural similarity index between the predicted and manually set cross sections were 12.52 ± 8.27 degree, 13.90 ± 10.62 mm, 3.95 ± 3.48 mm and 0.64 ± 0.15, respectively, and these errors were significantly smaller than the baselines. The mean processing time was 41.34 ± 22.75 s.<i>Conclusions</i>: Our developed method can provide CT cross sections corresponding to standard TEE views without user operations, resulting in faster treatment planning with less effort and without inter user variability in treatments using TEE.