著者
Susumu Katsushika Satoshi Kodera Mitsuhiko Nakamoto Kota Ninomiya Nobutaka Kakuda Hiroki Shinohara Ryo Matsuoka Hirotaka Ieki Masae Uehara Yasutomi Higashikuni Koki Nakanishi Tomoko Nakao Norifumi Takeda Katsuhito Fujiu Masao Daimon Jiro Ando Hiroshi Akazawa Hiroyuki Morita Issei Komuro
出版者
The Japanese Circulation Society
雑誌
Circulation Journal (ISSN:13469843)
巻号頁・発行日
vol.86, no.1, pp.87-95, 2021-12-24 (Released:2021-12-24)
参考文献数
27
被引用文献数
2 16

Background:Because the early diagnosis of subclinical cardiac sarcoidosis (CS) remains difficult, we developed a deep learning algorithm to distinguish CS patients from healthy subjects using echocardiographic movies.Methods and Results:Among the patients who underwent echocardiography from January 2015 to December 2019, we chose 151 echocardiographic movies from 50 CS patients and 151 from 149 healthy subjects. We trained two 3D convolutional neural networks (3D-CNN) to identify CS patients using a dataset of 212 echocardiographic movies with and without a transfer learning method (Pretrained algorithm and Non-pretrained algorithm). On an independent set of 41 echocardiographic movies, the area under the receiver-operating characteristic curve (AUC) of the Pretrained algorithm was greater than that of Non-pretrained algorithm (0.842, 95% confidence interval (CI): 0.722–0.962 vs. 0.724, 95% CI: 0.566–0.882, P=0.253). The AUC from the interpretation of the same set of 41 echocardiographic movies by 5 cardiologists was not significantly different from that of the Pretrained algorithm (0.855, 95% CI: 0.735–0.975 vs. 0.842, 95% CI: 0.722–0.962, P=0.885). A sensitivity map demonstrated that the Pretrained algorithm focused on the area of the mitral valve.Conclusions:A 3D-CNN with a transfer learning method may be a promising tool for detecting CS using an echocardiographic movie.
著者
Susumu Katsushika Satoshi Kodera Mitsuhiko Nakamoto Kota Ninomiya Nobutaka Kakuda Hiroki Shinohara Ryo Matsuoka Hirotaka Ieki Masae Uehara Yasutomi Higashikuni Koki Nakanishi Tomoko Nakao Norifumi Takeda Katsuhito Fujiu Masao Daimon Jiro Ando Hiroshi Akazawa Hiroyuki Morita Issei Komuro
出版者
The Japanese Circulation Society
雑誌
Circulation Journal (ISSN:13469843)
巻号頁・発行日
pp.CJ-21-0265, (Released:2021-06-26)
参考文献数
27
被引用文献数
16

Background:Because the early diagnosis of subclinical cardiac sarcoidosis (CS) remains difficult, we developed a deep learning algorithm to distinguish CS patients from healthy subjects using echocardiographic movies.Methods and Results:Among the patients who underwent echocardiography from January 2015 to December 2019, we chose 151 echocardiographic movies from 50 CS patients and 151 from 149 healthy subjects. We trained two 3D convolutional neural networks (3D-CNN) to identify CS patients using a dataset of 212 echocardiographic movies with and without a transfer learning method (Pretrained algorithm and Non-pretrained algorithm). On an independent set of 41 echocardiographic movies, the area under the receiver-operating characteristic curve (AUC) of the Pretrained algorithm was greater than that of Non-pretrained algorithm (0.842, 95% confidence interval (CI): 0.722–0.962 vs. 0.724, 95% CI: 0.566–0.882, P=0.253). The AUC from the interpretation of the same set of 41 echocardiographic movies by 5 cardiologists was not significantly different from that of the Pretrained algorithm (0.855, 95% CI: 0.735–0.975 vs. 0.842, 95% CI: 0.722–0.962, P=0.885). A sensitivity map demonstrated that the Pretrained algorithm focused on the area of the mitral valve.Conclusions:A 3D-CNN with a transfer learning method may be a promising tool for detecting CS using an echocardiographic movie.
著者
Naoko Sawada Koki Nakanishi Tomoko Nakao Tatsuya Miyoshi Masaaki Takeuchi Federico M. Asch Roberto M. Lang Masao Daimon
出版者
The Japanese Circulation Society
雑誌
Circulation Reports (ISSN:24340790)
巻号頁・発行日
pp.CR-23-0076, (Released:2023-10-18)
参考文献数
16

Background: Although accurate assessment of right ventricular (RV) morphology and function is clinically important, data regarding reference values for echocardiographic measurements of the right ventricle in the Japanese population are limited.Methods and Results: The World Alliance Society of Echocardiography (WASE) Normal Values Study was conducted to examine normal echocardiographic values in 15 countries. Using the WASE study database, we analyzed 2-dimensional echocardiographic parameters of RV size and systolic function in 192 healthy Japanese individuals and compared them with those obtained from 153 healthy American individuals. In the Japanese population, the absolute values of RV dimensions were smaller for women than men, although the difference disappeared after the data were adjusted for body surface area. RV dimensions, RV length and RV area were smaller in the elderly, but age did not affect RV systolic function. The absolute value, but not the adjusted value, of RV size tended to be smaller in Japanese than American individuals for both sexes. For men, RV systolic function parameters were lower in the Japanese population. This trend was not seen in women.Conclusions: The present study identified normal reference values for RV size and systolic function in a healthy Japanese population. Sex, age, and race had a significant impact on RV size; however, this trend was weak for RV systolic function.
著者
Hidetaka Itoh Hidehiro Kaneko Hiroyuki Kiriyama Yuriko Yoshida Koki Nakanishi Yoshiko Mizuno Masao Daimon Hiroyuki Morita Yutaka Yatomi Nobutake Yamamichi Issei Komuro
出版者
Japan Atherosclerosis Society
雑誌
Journal of Atherosclerosis and Thrombosis (ISSN:13403478)
巻号頁・発行日
pp.48728, (Released:2019-06-22)
参考文献数
40
被引用文献数
23

Aim: Obesity and metabolic syndrome (MetS) frequently coexist and are both important risk factors for cardiovascular disease. However, the pathophysiological role of obesity without MetS, also referred to as metabolically healthy obesity (MHO), remains unclear. In this study, we aim to clarify the effect of MHO on the development of carotid plaque using a community-based cohort.Methods: We examined 1,241 subjects who underwent health checkups at our institute. Obesity was defined by a body mass index of ≥ 25.0 kg/m2. Subjects were divided into three groups: non-obese, MHO, and metabolically unhealthy obesity (MUO).Results: The prevalence of carotid plaque, defined as intima-media thickness (IMT) ≥ 1.1 mm, was higher in subjects with MUO and MHO than in non-obese subjects. Multivariable analysis demonstrated that MHO (odds ratio 1.6, p=0.012) and MUO (odds ratio 1.9, p=0.003) as well as age of ≥ 65 years, male sex, hypertension, and diabetes mellitus were independently associated with carotid plaque formation. A similar trend was observed in each subgroup according to age and sex.Conclusions: MHO increased the prevalence of carotid plaque when compared with non-obese subjects, suggesting the potential significance of MHO in the development of subsequent cardiovascular diseases.