Nianan He

Prof. Nianan He

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
1 May 2021 in Endocrine Connections
Verified
Journal Article
Open access
PDF file
LHLei Hu
Lei Hu
XLXiao Liu
Xiao Liu
CPChong Pei
Chong Pei
LXLi Xie
Li Xie
NHNianan He
Nianan He
Objective We evaluated the diagnostic accuracy of perinodular stiffness, four risk stratification systems (RSSs) (KWAK-TIRADS, ACR-TIRADS, EU-TIRADS, and C-TIRADS), and the combination of perinodular stiffness and the four RSSs in differentiating malignant from benign thyroid nodules (TNs). Methods A total of 788 TNs in 726 patients were examined with conventional ultrasound (US) examination and sound touch elastography (STE). All TNs were classified by each of the four RSSs. The stiffness inside (E) the TNs was measured by STE. The stiffness of the 2.0-mm perinodular region (Eshell) was measured with the Shell measurement function of STE. The diagnostic performances of four RSSs, the E values, and the Eshell values were evaluated. All TNs were further divided into subgroups based on size (≤ 10 mm group and > 10 mm group). Results Ninety-six TNs were classified as benign and 692 as malignant. Among the single-method approaches, ACR-TIRADS showed the highest AUC (0.77) for differentiating malignant from benign TNs for all TNs included. Eshell showed the highest AUC (0.75) in differentiating malignant from benign TNs for TNs with sizes ≤ 10 mm, and there were no significant differences in AUC among all single methods for diagnosis of TNs with sizes > 10 mm (P > 0.05). The combination of C-TIRADS and Eshell/E yielded the highest AUC for all TNs (0.83) and for TNs with size ≤ 10 mm (0.85) compared with other combinations. Conclusions Eshell/E combined with conventional US improves the diagnostic accuracy in TNs and may reduce unnecessary fine-needle aspiration. Abstract Objective We evaluated the diagnostic accuracy of perinodular stiffness, four risk stratification systems (RSSs) (KWAK-TIRADS, ACR-TIRADS, EU-TIRADS, and C-TIRADS), and the combination of perinodular stiffness and the four RSSs in differentiating malignant from benign thyroid nodules (TNs). Methods A total of 788 TNs in 726 patients were examined with conventional ultrasound (US) examination and sound touch elastography (STE). All TNs were classified by each of the four RSSs. The stiffness inside (E) the TNs was measured by STE. The stiffness of the 2.0-mm perinodular region (Eshell) was measured with the Shell measurement function of STE. The diagnostic performances of four RSSs, the E values, and the Eshell values were evaluated. All TNs were further divided into subgroups based on size (≤ 10 mm group and > 10 mm group). Results Ninety-six TNs were classified as benign and 692 as malignant. Among the single-method approaches, ACR-TIRADS showed the highest AUC (0.77) for differentiating malignant from benign TNs for all TNs included. Eshell showed the highest AUC (0.75) in differentiating malignant from benign TNs for TNs with sizes ≤ 10 mm, and there were no significant differences in AUC among all single methods for diagnosis of TNs with sizes > 10 mm (P > 0.05). The combination of C-TIRADS and Eshell/E yielded the highest AUC for all TNs (0.83) and for TNs with size ≤ 10 mm (0.85) compared with other combinations. Conclusions Eshell/E combined with conventional US improves the diagnostic accuracy in TNs and may reduce unnecessary fine-needle aspiration.

16 August 2022 in Endocrinology
Verified
Journal Article
Closed access
PDF file
LHLei Hu
Lei Hu
CPChong Pei
Chong Pei
LXLi Xie
Li Xie
ZLZhen Liu
Zhen Liu
NHNianan He
Nianan He
WLWeifu Lv
Weifu Lv
We aimed to develop deep learning models based on perinodular regions’ shear-wave elastography (SWE) images and ultrasound (US) images of thyroid nodules (TNs) and determine their performances in predicting thyroid cancer. A total of 1747 American College of Radiology Thyroid Imaging Reporting & Data System 4 (TR4) thyroid nodules (TNs) in 1582 patients were included in this retrospective study. US images, SWE images, and 2 quantitative SWE parameters (maximum elasticity of TNs; 5-point average maximum elasticity of TNs) were obtained. Based on US and SWE images of TNs and perinodular tissue, respectively, 7 single-image convolutional neural networks (CNN) models [US, internal SWE, 0.5 mm SWE, 1.0 mm SWE, 1.5 mm SWE, 2.0 mm SWE of perinodular tissue, and whole SWE region of interest (ROI) image] and another 6 fusional-image CNN models (US + internal SWE, US + 0.5 mm SWE, US + 1.0 mm SWE, US + 1.5 mm SWE, US + 2.0 mm SWE, US + ROI SWE) were established using RestNet18. All of the CNN models and quantitative SWE parameters were built on a training cohort (1247 TNs) and evaluated on a validation cohort (500 TNs). In predicting thyroid cancer, US + 2.0 mm SWE image CNN model obtained the highest area under the curve in 10 mm < TNs ≤ 20 mm (0.95 for training; 0.92 for validation) and TNs > 20 mm (0.95 for training; 0.92 for validation), while US + 1.0 mm SWE image CNN model obtained the highest area under the curve in TNs ≤ 10 mm (0.95 for training; 0.92 for validation). The CNN models based on the fusion of SWE segmentation images and US images improve the radiological diagnostic accuracy of thyroid cancer.

23 June 2023 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
HZHao Zhang
Hao Zhang
YZYunhao Zhu
Yunhao Zhu
BZBowen Zhou
Bowen Zhou
SLSongde Liu
Songde Liu
NHNianan He
Nianan He
CTChao Tian
Chao Tian
Objective . Delay-and-sum (DAS) and minimum variance (MV) are two of the most important beamformers researched in ultrasound imaging. Compared with DAS, MV beamformer is different in respect of the aperture weights calculation, and can enhance the image quality by minimizing interference signal power. Various MV beamformers in linear array are studied, but linear array only provides a limited field of view. Ring array can provide better resolution and a full viewing angle; however, few studies have been explored based on ring array transducers. Approach . In this study, we proposed the multibeam MV (MB-MV) beamformer based on the conventional MV to enhance the image quality in ring array ultrasound imaging. To assess the effectiveness of the proposed approach, we conducted simulations, phantom experiments, and in vivo human experiments to compare MB-MV with DAS and spatial smoothing (SS) MV beamformers. Main results . The results show that the MB-MV method achieves at least 50% enhancement in terms of full width at half maximum compared to the others. Additionally, the MB-MV method improves the contrast ratio by approximate 6 dB and 4 dB compared with DAS and SS MV, respectively. Significance . This work demonstrates the feasibility of MB-MV method for ring array ultrasound imaging, and proves that MB-MV can improve the imaging quality in medical ultrasound imaging. According to our results, MB-MV method provides great potential in distinguishing between lesion and non-lesion areas in clinics, and further promotes the practical application of ring arrays in ultrasound imaging.

16 February 2022 in Frontiers in Oncology
Verified
Journal Article
Open access
XLXiao Liu
Xiao Liu
LXLi Xie
Li Xie
XYXianjun Ye
Xianjun Ye
YCYayun Cui
Yayun Cui
NHNianan He
Nianan He
LHLei Hu
Lei Hu
Background: Conventional ultrasound diagnosis of thyroid nodules (TNs) had a high false-positive rate, resulting in many unnecessary fine-needle aspirations (FNAs).Objective: This study aimed to establish a simple algorithm to reduce unnecessary FNA on TIRADS 4 TNs using different quantitative parameters of ultrasonic elasticity and chi-square automatic interactive detector (CHAID) method.Methods: From January 2020 to May 2021, 432 TNs were included in the study, which were confirmed by FNA or surgical pathology. Each TN was examined using conventional ultrasound, sound touch elastography, and Shell measurement function. The quantitative parameters E and Eshell were recorded, and the Eshell/E values were calculated for each TN. The diagnostic performance of the quantitative parameters was evaluated using the receiver operating characteristic curves. The CHAID was used to classify and analyze the quantitative parameters, and the prediction model was established.Results: A total of 226 TNs were malignant and 206 were benign. Eshell and Eshell/E ratio were included in the classification algorithm, which showed a depth of two ramifications (Eshell/E ≤ 0.988 or 0.988–1.043 or >1.043; if Eshell/E ≤ 0.988, then Eshell ≤ 64.0 or 64.0–74.0 or >74.0; if Eshell/E = 0.988–1.043, then Eshell ≤ 66.0 or > 66.0; if Eshell/E >1.043, then Eshell ≤ 69.0 or >69.0). The unnecessary FNAs could have been avoided in 57.3% of the cases using this algorithm.Conclusion: The prediction model using quantitative parameters had high diagnostic performance; it could quickly distinguish benign lesions and avoid subjective influence to some extent.

13 September 2026 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
SWShouzhi Wang
Shouzhi Wang
YYYing Yu
Ying Yu
LClei cao
lei cao
JXJiawei Xiong
Jiawei Xiong
CYchuang yin
chuang yin
NHNianan He
Nianan He
Background: Anthracycline-induced cardiotoxicity remains a major clinical challenge in oncology. The association between statin use and pulmonary hemodynamic changes during anthracycline chemotherapy remains largely unexplored. Methods: The primary endpoint was change in left ventricular ejection fraction from baseline to 12 months. Secondary endpoints included changes in left ventricular end-systolic volume index and mean e’ velocity. Exploratory endpoints included changes in other diastolic parameters, all estimated systolic pulmonary artery pressure (SPAP)-derived variables, and the descriptive incidence of cancer therapeutics-related cardiac dysfunction (CTRCD). Analyses included multivariable linear regression, 1:1 propensity score matching with baseline echocardiographic parameters included in the matching model, and multiple imputation for missing SPAP data. Results: After confounder adjustment, statin use was independently associated with a milder decline in mean e’ velocity (β = 0.75 cm/s, 95% CI 0.41 to 1.09, p < 0.001) and a smaller reduction in E/A ratio (β = 0.06, 95% CI 0.01 to 0.11, p = 0.02). No significant between-group difference was observed for adjusted ejection fraction change (β = 0.28%, 95% CI −1.11 to 1.66, p = 0.694). Statin use was associated with lower relative change amplitude of estimated SPAP (β = −4.55%, 95% CI −7.34 to −1.76, p = 0.001), with no significant effect on signed mean change. A descriptive component analysis showed a smaller signed mean change in estimated right atrial pressure in the statin group, with no significant difference in tricuspid regurgitant pressure gradient change. This comparison cannot mathematically decompose the absolute-change SPAP endpoint. The incidence of study-defined CTRCD was numerically lower in the statin group (1.25% vs. 4.8%, OR 0.25, 95% CI 0.05 to 1.28, p = 0.15), but this difference was not statistically significant and the study was underpowered for this clinical endpoint. Conclusions: In this retrospective cohort, concomitant statin therapy was associated with smaller changes in diastolic parameters and lower relative change amplitude of estimated SPAP between baseline and 12 month follow-up. No significant independent association with left ventricular systolic function was observed after multivariable adjustment. These hypothesis-generating findings require confirmation in appropriately powered prospective multicenter studies before any clinical implications can be considered.