Chun-Yi Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chun-Yi Lin has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Yu-Te Wu
Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei, Taiwan
5 shared publications - Po-Shan Wang
Institute of Biophotonics, National Yang-Ming University, Taipei 11221, Taiwan
3 shared publications - Chi-Wen Jao
Institute of Biophotonics, National Yang-Ming University, Taipei 112, Taiwan
2 shared publications - Chia-Feng Lu
Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
2 shared publications - Guan-Yu Li
Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
2 shared publications - Hai-Neng Fu
Heart Center, Cheng Hsin General Hospital, Taipei 112, Taiwan
2 shared publications
Latest Publications
- Open Access
- 17 April 2026
- Published by MDPI AG in Bioengineering
- Vol. 13 (4) , 471
Automated Aortic Quantification Based on Artificial Intelligence: Validation Using Contrast-Enhanced and Non-Contrast CT Scans from the Same Session
Early detection of aortic dilatation is clinically important for preventing progression to serious aortic disease and enabling timely intervention. We aimed to develop an AI method for quantifying the aorta in both contrast-enhanced and non-contrast CT scans, assisting early detection of aortic dilation. A total of 190 patient cases were analyzed, each having paired contrast-enhanced and non-contrast CT scans acquired in the same session, resulting in 380 scans. Our approach, based on open-source tools, demonstrated strong agreement with manual annotations, particularly in the ascending aorta. For contrast-enhanced CT, the AI achieved a correlation coefficient of 0.987 and intraclass correlation coefficient (ICC) of 0.986; for non-contrast CT, both were 0.945. Compared with clinical records, the sensitivity of AI detection was 97% for contrast-enhanced CT and 94% for non-contrast CT. This AI-based workflow enables highly sensitive automated aortic quantification in both contrast-enhanced and non-contrast CT scans, supporting broader clinical applicability across different imaging conditions.
- 17 April 2026
- Published by MDPI AG in Bioengineering
- Vol. 13 (4) , 471
Open AccessAutomated Aortic Quantification Based on Artificial Intelligence: Validation Using Contrast-Enhanced and Non-Contrast CT Scans from the Same Session
Early detection of aortic dilatation is clinically important for preventing progression to serious aortic disease and enabling timely intervention. We aimed to develop an AI method for quantifying the aorta in both contrast-enhanced and non-contrast CT scans, assisting early detection of aortic dilation. A total of 190 patient cases were analyzed, each having paired contrast-enhanced and non-contrast CT scans acquired in the same session, resulting in 380 scans. Our approach, based on open-source tools, demonstrated strong agreement with manual annotations, particularly in the ascending aorta. For contrast-enhanced CT, the AI achieved a correlation coefficient of 0.987 and intraclass correlation coefficient (ICC) of 0.986; for non-contrast CT, both were 0.945. Compared with clinical records, the sensitivity of AI detection was 97% for contrast-enhanced CT and 94% for non-contrast CT. This AI-based workflow enables highly sensitive automated aortic quantification in both contrast-enhanced and non-contrast CT scans, supporting broader clinical applicability across different imaging conditions.
- Open Access
- 26 February 2026
- Published by MDPI AG in Preprints.org
Automated Aortic Quantification Based on Artificial Intelligence: Validation Using Contrast-Enhanced and Non-Contrast CT Scans from the Same Session
Artificial intelligence (AI) advancements have enabled automated aortic quantification in computed tomography (CT) imaging. We aimed to develop an AI method for quantifying the aorta in both contrast-enhanced and non-contrast CT scans, assisting early detection of aortic dilation. A total of 190 patient cases were analyzed, each having paired con-trast-enhanced and non-contrast CT scans acquired in the same session, resulting in 380 scans. Our approach, based on open-source tools, demonstrated strong agreement with manual annotations, particularly in the ascending aorta. For contrast-enhanced CT, the AI achieved a correlation coefficient of 0.987 and intraclass correlation coefficient (ICC) of 0.986; for non-contrast CT, both were 0.945. Compared with clinical records, the sensi-tivity of AI detection was 97% for contrast-enhanced CT and 94% for non-contrast CT. This AI-based approach offers highly sensitive, automated aortic quantification across contrast conditions, supporting physicians in early identification of aortic abnormalities.
- 26 February 2026
- Published by MDPI AG in Preprints.org
Open AccessAutomated Aortic Quantification Based on Artificial Intelligence: Validation Using Contrast-Enhanced and Non-Contrast CT Scans from the Same Session
Artificial intelligence (AI) advancements have enabled automated aortic quantification in computed tomography (CT) imaging. We aimed to develop an AI method for quantifying the aorta in both contrast-enhanced and non-contrast CT scans, assisting early detection of aortic dilation. A total of 190 patient cases were analyzed, each having paired con-trast-enhanced and non-contrast CT scans acquired in the same session, resulting in 380 scans. Our approach, based on open-source tools, demonstrated strong agreement with manual annotations, particularly in the ascending aorta. For contrast-enhanced CT, the AI achieved a correlation coefficient of 0.987 and intraclass correlation coefficient (ICC) of 0.986; for non-contrast CT, both were 0.945. Compared with clinical records, the sensi-tivity of AI detection was 97% for contrast-enhanced CT and 94% for non-contrast CT. This AI-based approach offers highly sensitive, automated aortic quantification across contrast conditions, supporting physicians in early identification of aortic abnormalities.
- Open Access
Application of Convolutional Neural Network for Fingerprint-Based Prediction of Gender, Finger Position, and Height
Fingerprints are the most common personal identification feature and key evidence for crime scene investigators. The prediction of fingerprints features include gender, height range (tall or short), left or right hand, and finger position can effectively narrow down the list of suspects, increase the speed of comparison, and greatly improve the effectiveness of criminal investigations. In this study, we used three commonly used CNNs (VGG16, Inception-v3, and Resnet50) to perform biometric prediction on 1000 samples, and the results showed that VGG16 achieved the highest accuracy in identifying gender (79.2%), left- and right-hand fingerprints (94.4%), finger position (84.8%), and height range (69.8%, using the ring finger of male participants). In addition, we visualized the CNN classification basis by the Grad-CAM technique and compared the results with those predicted by experts and found that the CNN model outperformed experts in terms of classification accuracy and speed, and provided good reference for fingerprints that were difficult to determine manually.
Open AccessApplication of Convolutional Neural Network for Fingerprint-Based Prediction of Gender, Finger Position, and Height
Fingerprints are the most common personal identification feature and key evidence for crime scene investigators. The prediction of fingerprints features include gender, height range (tall or short), left or right hand, and finger position can effectively narrow down the list of suspects, increase the speed of comparison, and greatly improve the effectiveness of criminal investigations. In this study, we used three commonly used CNNs (VGG16, Inception-v3, and Resnet50) to perform biometric prediction on 1000 samples, and the results showed that VGG16 achieved the highest accuracy in identifying gender (79.2%), left- and right-hand fingerprints (94.4%), finger position (84.8%), and height range (69.8%, using the ring finger of male participants). In addition, we visualized the CNN classification basis by the Grad-CAM technique and compared the results with those predicted by experts and found that the CNN model outperformed experts in terms of classification accuracy and speed, and provided good reference for fingerprints that were difficult to determine manually.
- 12 July 2021
- Published by Springer Nature in International Journal of Fuzzy Systems
- Vol. 23 (8) , 2417-2431
Using Fuzzy Classifier in Ensemble Method for Motor Imagery Electroencephalography Classification
- 12 July 2021
- Published by Springer Nature in International Journal of Fuzzy Systems
- Vol. 23 (8) , 2417-2431
Using Fuzzy Classifier in Ensemble Method for Motor Imagery Electroencephalography Classification