Yukai Cheng

Dr. Yukai Cheng


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 October 2021 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
YCYukai Cheng
Yukai Cheng
CLChih-Lung Lin
Chih-Lung Lin
YHYi-Chi Huang
Yi-Chi Huang
JCJui-Chi Chen
Jui-Chi Chen
TLTzu-Peng Lan
Tzu-Peng Lan
CCCheng-Hung Chuang
Cheng-Hung Chuang
The automatic segmentation of intervertebral discs from medical images is an important task for an intelligent clinical system. In this study, a deep learning model based on the MultiResUNet model for the automatic segmentation of specific intervertebral discs is presented. MultiResUNet can easily segment all intervertebral discs in MRI images; however, when only certain specific intervertebral discs need to be segmented, problems with segmentation errors, misalignment, and noise occur. In order to solve these problems, a two-stage MultiResUNet model is proposed. Connected-component labeling, automatic cropping, and distance transform are used in the proposed method. The experimental results show that the segmentation errors and misalignments of specific intervertebral discs are greatly reduced, and the segmentation accuracy is increased to about 94%. The performance of the proposed method proves its usefulness for the automatic segmentation of specific intervertebral discs over other deep learning models, such as the U-Net, CNN-based, Attention U-Net, and MultiResUNet models.

16 January 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
YCYukai Cheng
Yukai Cheng
CLChih-Lung Lin
Chih-Lung Lin
YHYi-Chi Huang
Yi-Chi Huang
Guo-Shiang LinGuo-Shiang Lin
Guo-Shiang Lin
ZLZhen-You Lian
Zhen-You Lian
CCCheng-Hung Chuang
Cheng-Hung Chuang
Automatically segmenting specific tissues or structures from medical images is a straightforward task for deep learning models. However, identifying a few specific objects from a group of similar targets can be a challenging task. This study focuses on the segmentation of certain specific intervertebral discs from lateral spine images acquired from an MRI scanner. In this research, an approach is proposed that utilizes MultiResUNet models and employs saliency maps for target intervertebral disc segmentation. First, a sub-image cropping method is used to separate the target discs. This method uses MultiResUNet to predict the saliency maps of target discs and crop sub-images for easier segmentation. Then, MultiResUNet is used to segment the target discs in these sub-images. The distance maps of the segmented discs are then calculated and combined with their original image for data augmentation to predict the remaining target discs. The training set and test set use 2674 and 308 MRI images, respectively. Experimental results demonstrate that the proposed method significantly enhances segmentation accuracy to about 98%. The performance of this approach highlights its effectiveness in segmenting specific intervertebral discs from closely similar discs.

4 May 2026 in Child's Nervous System
Verified
Journal Article
Open access
CCChao-Yuan Chang
Chao-Yuan Chang
YCYukai Cheng
Yukai Cheng
This study evaluated a modified anchoring technique using a straight connector in non-burr hole valve shunt systems to reduce catheter migration in children under 3 years of age. We retrospectively reviewed records of 48 children (< 3 years) who received frontal ventriculoperitoneal (VP) shunt placement using a non-burr hole valve system between January 2017 and July 2022. Catheter migration occurred in 18 of 48 patients. Migration was significantly higher with the right-angle adaptor (61.5%) than with the straight connector (9.1%; p = 0.0002). Younger age at surgery was associated with migration (4.5 vs. 10.1 months, p = 0.0048). Univariate analysis showed younger age and use of the straight connector were associated with reduced migration risk. In this small retrospective study, anchoring the straight connector was associated with fewer catheter migration events, but the difference was not statistically significant after adjustment for age. These findings should be interpreted as exploratory, highlighting a potential technical consideration rather than a proven benefit. Further prospective studies with larger and age-stratified cohorts are needed to determine whether this modification contributes meaningfully to reducing shunt migration.