TY - JOUR
T1 - Automated comprehensive evaluation of coronary artery plaque in IVOCT using deep learning
AU - Liu, Pengfei
AU - Lu, Zang
AU - Hou, Wenqing
AU - Kadier, Kaisaierjiang
AU - Cui, Chunying
AU - Mu, Zhengyang
AU - Ainiwaer, Aikeliyaer
AU - Peng, Xinliang
AU - Wufu, Gulinuer
AU - Ma, Yitong
AU - Dai, Jianguo
AU - Ma, Xiang
N1 - Funding Information:
This work was supported by the Key Research and Development Task Special in Xinjiang Uygur Autonomous Region (No. 2022B03022-3), National Natural Science Foundation of China (No. 82360090), and president's fund project of Xinjiang University of political science and law (No. XZZK2023003). The authors acknowledge the clinicians and assistants who participated in this study for data collection, preparation, and quality control. Sincere gratitude to Prof. Lu Xiaolei from Xigu hospital of Lanzhou university second hospital for providing the IVOCT imaging data.
Funding Information:
This work was supported by the key research projects in Xinjiang Uygur Autonomous Region (grant no. 2022B03022-3 ), National Natural Science Foundation of China (grant no. 82360090 ), and president\u2019s fund project of Xinjiang University of political science and law (no. XZZK2023003 ). The authors acknowledge the clinicians and assistants who participated in this study for data collection, preparation, and quality control. Sincere gratitude to Prof. Lu Xiaolei from Xigu hospital of Lanzhou university second hospital for providing the IVOCT imaging data.
Publisher Copyright:
© 2025 The Authors
PY - 2025/4/18
Y1 - 2025/4/18
N2 - The process of manually characterizing and quantifying coronary artery plaque tissue in intravascular optical coherence tomography (IVOCT) images is both time-consuming and subjective. We have developed a deep learning-based semantic segmentation model (EDA-UNet) designed specifically for characterizing and quantifying coronary artery plaque tissue in IVOCT images. IVOCT images from two centers were utilized as the internal dataset for model training and internal testing. Images from another independent center employing IVOCT were used for external testing. The Dice coefficients for fibrous plaque, calcified plaque, and lipid plaque in external tests were 0.8282, 0.7408, and 0.7052 respectively. The model demonstrated strong correlation and consistency with the ground truth in the quantitative analysis of calcification scores and the identification of thin-cap fibroatheroma (TCFA). The median duration for each callback analysis was 18 s. EDA-UNet model serves as an efficient and accurate technological tool for plaque characterization and quantification.
AB - The process of manually characterizing and quantifying coronary artery plaque tissue in intravascular optical coherence tomography (IVOCT) images is both time-consuming and subjective. We have developed a deep learning-based semantic segmentation model (EDA-UNet) designed specifically for characterizing and quantifying coronary artery plaque tissue in IVOCT images. IVOCT images from two centers were utilized as the internal dataset for model training and internal testing. Images from another independent center employing IVOCT were used for external testing. The Dice coefficients for fibrous plaque, calcified plaque, and lipid plaque in external tests were 0.8282, 0.7408, and 0.7052 respectively. The model demonstrated strong correlation and consistency with the ground truth in the quantitative analysis of calcification scores and the identification of thin-cap fibroatheroma (TCFA). The median duration for each callback analysis was 18 s. EDA-UNet model serves as an efficient and accurate technological tool for plaque characterization and quantification.
KW - Artificial intelligence
KW - Cardiovascular medicine
U2 - 10.1016/j.isci.2025.112169
DO - 10.1016/j.isci.2025.112169
M3 - Article
SN - 2589-0042
VL - 28
JO - iScience
JF - iScience
IS - 4
M1 - 112169
ER -