Yuhuan Lu

Yuhuan Lu

Auto-generated profile, based on publicly available information

Yuhuan Lu

College of Computer Science and Electronic Engineering, Hunan University, Changsha, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
27 February 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
BPBin Pu
Bin Pu
KLKenli Li
Kenli Li
JCJianguo Chen
Jianguo Chen
YLYuhuan Lu
Yuhuan Lu
QZQing Zeng
Qing Zeng
SLShengli Li
Shengli Li
In the fetal cardiac ultrasound examination, standard cardiac cycle (SCC) recognition is the essential foundation for diagnosing congenital heart disease. Previous studies have mostly focused on the detection of adult CCs, which may not be applicable to the fetus. In clinical practice, localization of SCCs needs to recognize end-systole (ES) and end-diastole (ED) frames accurately, ensuring that every frame in the cycle is a standard view. Most existing methods are not based on the detection of key anatomical structures, which may not recognize irrelevant views and background frames, results containing non-standard frames, or even it does not work in clinical practice. We propose an end-to-end hybrid neural network based on an object detector to detect SCCs from fetal ultrasound videos efficiently, which consists of 3 modules, namely Anatomical Structure Detection (ASD), Cardiac Cycle Localization (CCL), and Standard Plane Recognition (SPR). Specifically, ASD uses an object detector to identify 9 key anatomical structures, 3 cardiac motion phases, and the corresponding confidence scores from fetal ultrasound videos. On this basis, we propose a joint probability method in the CCL to learn the cardiac motion cycle based on the 3 cardiac motion phases. In SPR, to reduce the impact of structure detection errors on the accuracy of the standard plane recognition, we use XGBoost algorithm to learn the relation knowledge of the detected anatomical structures. We evaluate our method on the test fetal ultrasound video datasets and clinical examination cases and achieve remarkable results. This study may pave the way for clinical practices.

15 November 2022 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
YLYuhuan Lu
Yuhuan Lu
KLKenli Li
Kenli Li
BPBin Pu
Bin Pu
YTYing Tan
Ying Tan
NZNingbo Zhu
Ningbo Zhu
Echocardiography is an essential procedure for the prenatal examination of the fetus for congenital heart disease (CHD). Accurate segmentation of key anatomical structures in a four-chamber view is an essential step in measuring fetal growth parameters and diagnosing CHD. Currently, most obstetricians perform segmentation tasks manually, but the pixel-level operation is labor-intensive and requires extensive anatomical knowledge and clinical experience. As such, efficiently and accurately detecting structures from real-world fetal ultrasound images is a key challenge. In this paper, we propose a YOLOX-based deep instance segmentation neural network (i.e., IS-YOLOX) for cardiac anatomical structure location and segmentation in fetal ultrasound images. Specifically, we reconstruct a new instance segmentation branch based on a multi-task deep learning framework. We then design a new multi-level non-maximum suppression (NMS) mechanism to further improve the segmentation performance that consists of three levels of selection. Moreover, unlike two-stage instance segmentation approaches, our method does not rely on object detection results. To the best of our knowledge, this is the first study regarding instance segmentation on 13 types of anatomical structures in the fetal four-chamber view. Extensive experiments were carried out on clinical datasets, and the experimental results show that our method outperforms nine competitive baselines.

28 November 2023 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
YKYan Kang
Yan Kang
LPLuhan Peng
Luhan Peng
JGJing Guo
Jing Guo
YLYuhuan Lu
Yuhuan Lu
YYYun Yang
Yun Yang
BPBin Pu
Bin Pu
The ubiquity and commoditization of wearable sensors have generated a deluge of user-generated health care data and played a key role in clinical utility, particularly when incorporated into personalized prediction models. The “curse of dimensionality” and enormous computational costs are still the main challenges faced by the existing algorithms as the number of wearable datasets exponentially increases. We propose a novel method by hybridizing a clustering method and a wrapper method to reduce the dimensionality of raw wearable datasets while preserving health care information. In the clustering stage, a dynamic correlation-guided feature clustering method reduces the search space by designing a dynamic threshold to filter unrelated high-dimensional features. In the wrapper stage, we obtain the optimal feature subset by improving the powerful search capability of the particle swarm optimization algorithm. A crossover operator based on normalized mutual information similarity is proposed to match particles, which effectively improves the diversity of the offspring swarm to prevent premature convergence. In addition, we propose a dynamic swarm strategy to mutate the duplicate particles in the swarm to enhance the efficiency of the particle search process. Our method is evaluated on ten real public datasets, and the experimental results demonstrate its superior performance.

10 July 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
YLYuhuan Lu
Yuhuan Lu
GTGuanghua Tan
Guanghua Tan
BPBin Pu
Bin Pu
HWHang Wang
Hang Wang
BLBocheng Liang
Bocheng Liang
JRJagath C Rajapakse
Jagath C Rajapakse
Congenital heart disease (CHD) is the most common congenital disability affecting healthy development and growth, even resulting in pregnancy termination or fetal death. Recently, deep learning techniques have made remarkable progress to assist in diagnosing CHD. One very popular method is directly classifying fetal ultrasound images, recognized as abnormal and normal, which tends to focus more on global features and neglects semantic knowledge of anatomical structures. The other approach is segmentation-based diagnosis, which requires a large number of pixel-level annotation masks for training. However, the detailed pixel-level segmentation annotation is costly or even unavailable. Based on the above analysis, we propose SKGC, a universal framework to identify normal or abnormal four-chamber heart (4CH) images, guided by a few annotation masks, while improving accuracy remarkably. SKGC consists of a semantic-level knowledge extraction module (SKEM), a multi-knowledge fusion module (MFM), and a classification module (CM). SKEM is responsible for obtaining high-level semantic knowledge, serving as an abstract representation of the anatomical structures that obstetricians focus on. MFM is a lightweight but efficient module that fuses semantic-level knowledge with the original specific knowledge in ultrasound images. CM classifies the fused knowledge and can be replaced by any advanced classifier. Moreover, we design a new loss function that enhances the constraint between the foreground and background predictions, improving the quality of the semantic-level knowledge. Experimental results on the collected real-world NA-4CH and the publicly FEST datasets show that SKGC achieves impressive performance with the best accuracy of 99.68% and 95.40%, respectively. Notably, the accuracy improves from 74.68% to 88.14% using only 10 labeled masks.

31 July 2024
Verified
Book Chapter
Closed access
PDF file
JHJie He
Jie He
LYLei Yang
Lei Yang
YZYunping Zhu
Yunping Zhu
DLDonglian Li
Donglian Li
ZDZhixing Ding
Zhixing Ding
SLShengli Li
Shengli Li

12 March 2025 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
YLYuhuan Lu
Yuhuan Lu
GTGuanghua Tan
Guanghua Tan
BPBin Pu
Bin Pu
PYPak-Hei Yeung
Pak-Hei Yeung
HWHang Wang
Hang Wang
KLKenli Li
Kenli Li
The detection of cardiac phase in ultrasound videos, identifying end-systolic (ES) and end-diastolic (ED) frames, is a critical step in assessing cardiac function, monitoring structural changes, and diagnosing congenital heart disease. Current popular methods use recurrent neu ral networks to track dependencies over long sequences for cardiac phase detection, but often overlook the short-term motion of cardiac valves that sonographers rely on. In this paper, we propose a novel optical flow-enhanced Mamba U-net framework, designed to utilize both short-term motion and long-term dependencies to detect the cardiac phase in ultrasound videos. We utilize optical flow to capture the short-term motion of cardiac muscles and valves between adjacent frames, enhancing the input video. The Mamba layer is employed to track long-term dependencies across cardiac cycles. We then develop regression branches using the U-Net architecture, which integrates short-term and long-term information while extracting multi-scale features. Using this method, we can generate regression scores for each frame and identify keyframes (i.e., ES and ED frames). Additionally, we design a keyframe weighted loss function to guide the network to focus more on keyframes rather than intermediate period frames. Ourmethod demonstrates superior performance compared to advanced baseline methods, achieving frame mismatches of 1.465 frames for ES and 0.842 frames for ED in the Fetal Echocardiogram dataset, where heart rates are higher and phase changes occur rapidly, and 2.444 frames and 2.072 frames in the publicly available adult Echonet-Dynamic dataset. Its accuracy and robustness in both fetal and adult datasets highlight its potential for clinical application.