Haoyan Li

Dr. Haoyan Li

orcid

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
8 July 2021 in BMC Medical Imaging
Verified
Journal Article
Open access
PDF file
JSJihang Sun
Jihang Sun
HLHaoyan Li
Haoyan Li
BWBei Wang
Bei Wang
JLJianying Li
Jianying Li
MLMichelle Li
Michelle Li
YPYun Peng
Yun Peng
Background: To evaluate the performance of a Deep Learning Image Reconstruction (DLIR) algorithm in pediatric head CT for improving image quality and lesion detection with 0.625 mm thin-slice images. Methods: Low-dose axial head CT scans of 50 children with 120 kV, 0.8 s rotation and age-dependent 150–220 mA tube current were selected. Images were reconstructed at 5 mm and 0.625 mm slice thickness using Filtered back projection (FBP), Adaptive statistical iterative reconstruction-v at 50% strength (50%ASIR-V) (as reference standard), 100%ASIR-V and DLIR-high (DL-H). The CT attenuation and standard deviation values of the gray and white matters in the basal ganglia were measured. The clarity of sulci/cisterns, boundary between white and gray matters, and overall image quality was subjectively evaluated. The number of lesions in each reconstruction group was counted. Results: The 5 mm FBP, 50%ASIR-V, 100%ASIR-V and DL-H images had a subjective score of 2.25 ± 0.44, 3.05 ± 0.23, 2.87 ± 0.39 and 3.64 ± 0.49 in a 5-point scale, respectively with DL-H having the lowest image noise of white matter at 2.00 ± 0.34 HU; For the 0.625 mm images, only DL-H images met the diagnostic requirement. The 0.625 mm DL-H images had similar image noise (3.11 ± 0.58 HU) of the white matter and overall image quality score (3.04 ± 0.33) as the 5 mm 50% ASIR-V images (3.16 ± 0.60 HU and 3.05 ± 0.23). Sixty-five lesions were recognized in 5 mm 50%ASIR-V images and 69 were detected in 0.625 mm DL-H images. Conclusion: DL-H improves the head CT image quality for children compared with ASIR-V images. The 0.625 mm DL-H images improve lesion detection and produce similar image noise as the 5 mm 50%ASIR-V images, indicating a potential 85% dose reduction if current image quality and slice thickness are desired.



27 April 2025 in Tomography
Verified
Journal Article
Open access
PDF file
HLHaoyan Li
Haoyan Li
CZchen zhenpeng
chen zhenpeng
SGShuaiyi Gao
Shuaiyi Gao
JHJiaqi Hu
Jiaqi Hu
ZYZhihao Yang
Zhihao Yang
JSJihang Sun
Jihang Sun
Objectives: To evaluate the medical image segmentation performance of monochromatic images in various energy levels. Methods: The low-density module (25 mm in diameter, 6 Hounsfield Unit (HU) in density difference from background) from the ACR464 phantom was scanned at both 10 mGy and 5 mGy dose levels. Virtual monoenergetic images (VMIs) at different energy levels of 40, 50, 60, 68, 74, and 100 keV were generated. The images at 10 mGy reconstructed with 50% adaptive statistical iterative reconstruction veo (ASIR-V50%) were used to train an image segmentation model based on U-Net. The evaluation set used 5 mGy VMIs reconstructed with various reconstruction algorithms: FBP, ASIR-V50%, ASIR-V100%, deep learning image reconstruction (DLIR) with low (DLIR-L), medium (DLIR-M), and high (DLIR-H) strength levels. U-Net was employed as a tool to compare algorithm performance. Image noise and segmentation metrics, such as the DICE coefficient, intersection over union (IOU), sensitivity, and Hausdorff distance, were calculated to assess both image quality and segmentation performance. Results: DLIR-M and DLIR-H consistently achieved lower image noise and better segmentation performance, with the highest results observed at 60 keV, and DLIR-H had the lowest image noise across all energy levels. The performance metrics, including IOU, DICE, and sensitivity, were ranked in descending order with energy levels of 60 keV, 68 keV, 50 keV, 74 keV, 40 keV, and 100 keV. Specifically, at 60 keV, the average IOU values for each reconstruction method were 0.60 for FBP, 0.67 for ASIR-V50%, 0.68 for ASIR-V100%, 0.72 for DLIR-L, 0.75 for DLIR-M, and 0.75 for DLIR-H. The average DICE values were 0.75, 0.80, 0.82, 0.83, 0.85, and 0.86. The sensitivity values were 0.93, 0.91, 0.96, 0.95, 0.98, and 0.98. Conclusions: For low-density, non-enhancing objects under a low dose, the 60 keV VMIs performed better in automatic segmentation. DLIR-M and DLIR-H algorithms delivered the best results, whereas DLIR-H provided the lowest image noise and highest sensitivity.

13 July 2025 in International Journal of Imaging Systems and Technology
Verified
Journal Article
Closed access
JSJihang Sun
Jihang Sun
HLHaoyan Li
Haoyan Li
SYShen Yang
Shen Yang
RSRuifang Sun
Ruifang Sun
FWFanning Wang
Fanning Wang
YPYun Peng
Yun Peng

29 January 2026 in European Journal of Radiology Open
Verified
Journal Article
Open access
RSRuifang Sun
Ruifang Sun
HLHaoyan Li
Haoyan Li
BWBei Wang
Bei Wang
HKHuiying Kang
Huiying Kang
RLRuntong Lu
Runtong Lu
JSJihang Sun
Jihang Sun
To investigate the feasibility of evaluating Imaging-Defined Risk Factors (IDRFs) in Neuroblastoma (NB) patients using venous-phase (VP)-only images in dual-energy CT for radiation dose reduction and examination workflow optimization, compared with conventional triple-phase CECT. Ninety-four pediatric NB patients (ages 4.92 ± 3.45 y, range 0–17 y), who underwent triple-phase DECT were included. The standard 68 keV images reconstructed using 50 % adaptive statistical iterative reconstruction-V (ASIR-V) served as the control group. The 40 keV images in VP with deep learning image reconstruction (DLIR) were used as the study group. Objective measurements included CT values and standard deviations of the aorta, back muscles, NB lesions; contrast-to-noise ratio (CNR) of the aorta, and edge-rise slope (ERS) of NB lesions and compared by using paired Wilcoxon tests. Two pediatric radiologists independently reviewed images for IDRFs and used a 5-point scale to assess images quality. Weighted Cohen's kappa was generated to analyze the inter-rater differences. The study group had higher arterial CT values (440.81 ± 79.93 HU vs. 340.35 ± 61.14 HU, p < 0.001), similar CNR (30.43 ± 10.91 vs. 28.17 ± 10.05, p = 0.110), and higher ERS (129.31 ± 41.32 vs. 114.06 ± 36.33, p = 0.002). Two radiologists showed no difference in IDRFs assessment with good intra-group consistency, and all images met diagnostic needs with image quality scores exceeded 3. The single-phase DECT reduced radiation dose to 108.84 ± 50.49 mGy-cm, over 60 % lower than the triple-phase CECT. Single venous-phase 40 keV-DECT images demonstrate feasibility for evaluating IDRFs in pediatric NB patients, saving about 60 % radiation dose and optimizing the examination workflow compared to the conventional triple-phase approach.