Search

Your search keyword '"Min, Zhe"' showing total 605 results
Start Over Author "Min, Zhe"
605 results on '"Min, Zhe"'

1. Biomechanics-informed Non-rigid Medical Image Registration and its Inverse Material Property Estimation with Linear and Nonlinear Elasticity

Author

Min, Zhe, Baum, Zachary M. C., Saeed, Shaheer U., Emberton, Mark, Barratt, Dean C., Taylor, Zeike A., and Hu, Yipeng

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

This paper investigates both biomechanical-constrained non-rigid medical image registrations and accurate identifications of material properties for soft tissues, using physics-informed neural networks (PINNs). The complex nonlinear elasticity theory is leveraged to formally establish the partial differential equations (PDEs) representing physics laws of biomechanical constraints that need to be satisfied, with which registration and identification tasks are treated as forward (i.e., data-driven solutions of PDEs) and inverse (i.e., parameter estimation) problems under PINNs respectively. Two net configurations (i.e., Cfg1 and Cfg2) have also been compared for both linear and nonlinear physics model. Two sets of experiments have been conducted, using pairs of undeformed and deformed MR images from clinical cases of prostate cancer biopsy. Our contributions are summarised as follows. 1) We developed a learning-based biomechanical-constrained non-rigid registration algorithm using PINNs, where linear elasticity is generalised to the nonlinear version. 2) We demonstrated extensively that nonlinear elasticity shows no statistical significance against linear models in computing point-wise displacement vectors but their respective benefits may depend on specific patients, with finite-element (FE) computed ground-truth. 3) We formulated and solved the inverse parameter estimation problem, under the joint optimisation scheme of registration and parameter identification using PINNs, whose solutions can be accurately found by locating saddle points., Comment: Accepted at MICCAI 2024

Published
2024

3. Semi-weakly-supervised neural network training for medical image registration

Author

Li, Yiwen, Fu, Yunguan, Gayo, Iani J. M. B., Yang, Qianye, Min, Zhe, Saeed, Shaheer U., Yan, Wen, Wang, Yipei, Noble, J. Alison, Emberton, Mark, Clarkson, Matthew J., Barratt, Dean C., Prisacariu, Victor A., and Hu, Yipeng

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

For training registration networks, weak supervision from segmented corresponding regions-of-interest (ROIs) have been proven effective for (a) supplementing unsupervised methods, and (b) being used independently in registration tasks in which unsupervised losses are unavailable or ineffective. This correspondence-informing supervision entails cost in annotation that requires significant specialised effort. This paper describes a semi-weakly-supervised registration pipeline that improves the model performance, when only a small corresponding-ROI-labelled dataset is available, by exploiting unlabelled image pairs. We examine two types of augmentation methods by perturbation on network weights and image resampling, such that consistency-based unsupervised losses can be applied on unlabelled data. The novel WarpDDF and RegCut approaches are proposed to allow commutative perturbation between an image pair and the predicted spatial transformation (i.e. respective input and output of registration networks), distinct from existing perturbation methods for classification or segmentation. Experiments using 589 male pelvic MR images, labelled with eight anatomical ROIs, show the improvement in registration performance and the ablated contributions from the individual strategies. Furthermore, this study attempts to construct one of the first computational atlases for pelvic structures, enabled by registering inter-subject MRs, and quantifies the significant differences due to the proposed semi-weak supervision with a discussion on the potential clinical use of example atlas-derived statistics.

Published
2024

12. Association between fibrinogen-to-albumin ratio and bone metabolism markers (β-CTX and P1NP) in Chinese individuals with osteoporotic fracture: a cross-sectional investigation

Author

Li-long Feng, Ke Lu, Chong Li, Min-zhe Xu, Yao-wei Ye, Yi Yin, and Hui-qiang Shan

Subjects
Procollagen type 1 N-terminal propeptide (P1NP), Osteoporotic fracture, Fibrinogen-to-albumin ratio (FAR), Inflammatory markers, Bone metabolism markers, β-C-terminal telopeptide of type 1 collagen (β-CTX), Diseases of the musculoskeletal system, RC925-935
Abstract

Abstract Objective Research on the link between inflammatory indicators and markers of bone metabolism is currently lacking, especially the interaction between Procollagen type 1 N-terminal propeptide (P1NP), the β-C-terminal telopeptide of type 1 collagen (β-CTX), and the fibrinogen-to-albumin ratio (FAR). This study intends to fill that knowledge gap by investigating the possible link between inflammatory indicators and bone metabolism. Methods This observational study included 718 individuals diagnosed with osteoporotic fractures from Kunshan Hospital Affiliated to Jiangsu University between January 2017 and July 2022. After accounting for several confounders, the independent connection between FAR levels and β-CTX and P1NP was investigated via Generalized Estimating Equations (GEE). On top of that, we used a generalized additive model (GAM) to find any non-linear correlations, and a two-piecewise linear regression model to find the threshold effects in the smoothing curves that came out of it. To ensure the aforementioned result was stable, a subgroup analysis was carried out. Results The results showed a positive linear correlation between FAR and β-CTX [β = 1.077, 95% confidence interval (CI): 0.24 to 1.92, P = 0.012]. The study’s findings demonstrated that FAR and P1NP fit curves in an inverted U-shaped pattern, and an inflection point K = 0.0685 for FAR was detected. P1NP showed a positive correlation with FAR below the inflection point (β = 306.10, 95% CI: 47.37 to 564.83, P = 0.021), and a negative correlation with FAR beyond the inflection point (β = -117.57, 95% CI: -231.34 to -3.80, P = 0.043). The subgroup analysis revealed that women had a more significant association between FAR and β-CTX in women than in men. Conclusions The results provide useful insights into the potential association between FAR and markers of bone metabolism. The study may provide a novel clinical implication by introducing FAR as a potential reference indicator for assessing bone health, offering a cost-effective and conveniently obtainable biomarker to monitor inflammation to improve bone metabolism in the treatment of osteoporosis.

Published
2025
Full Text
View/download PDF

13. Combiner and HyperCombiner Networks: Rules to Combine Multimodality MR Images for Prostate Cancer Localisation

Author

Yan, Wen, Chiu, Bernard, Shen, Ziyi, Yang, Qianye, Syer, Tom, Min, Zhe, Punwani, Shonit, Emberton, Mark, Atkinson, David, Barratt, Dean C., and Hu, Yipeng

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, 68T07
Abstract

One of the distinct characteristics in radiologists' reading of multiparametric prostate MR scans, using reporting systems such as PI-RADS v2.1, is to score individual types of MR modalities, T2-weighted, diffusion-weighted, and dynamic contrast-enhanced, and then combine these image-modality-specific scores using standardised decision rules to predict the likelihood of clinically significant cancer. This work aims to demonstrate that it is feasible for low-dimensional parametric models to model such decision rules in the proposed Combiner networks, without compromising the accuracy of predicting radiologic labels: First, it is shown that either a linear mixture model or a nonlinear stacking model is sufficient to model PI-RADS decision rules for localising prostate cancer. Second, parameters of these (generalised) linear models are proposed as hyperparameters, to weigh multiple networks that independently represent individual image modalities in the Combiner network training, as opposed to end-to-end modality ensemble. A HyperCombiner network is developed to train a single image segmentation network that can be conditioned on these hyperparameters during inference, for much improved efficiency. Experimental results based on data from 850 patients, for the application of automating radiologist labelling multi-parametric MR, compare the proposed combiner networks with other commonly-adopted end-to-end networks. Using the added advantages of obtaining and interpreting the modality combining rules, in terms of the linear weights or odds-ratios on individual image modalities, three clinical applications are presented for prostate cancer segmentation, including modality availability assessment, importance quantification and rule discovery., Comment: 30 pages, 6 figures

Published
2023
Full Text
View/download PDF

14. Non-rigid Medical Image Registration using Physics-informed Neural Networks

Author

Min, Zhe, Baum, Zachary M. C., Saeed, Shaheer U., Emberton, Mark, Barratt, Dean C., Taylor, Zeike A., and Hu, Yipeng

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Physics - Medical Physics
Abstract

Biomechanical modelling of soft tissue provides a non-data-driven method for constraining medical image registration, such that the estimated spatial transformation is considered biophysically plausible. This has not only been adopted in real-world clinical applications, such as the MR-to-ultrasound registration for prostate intervention of interest in this work, but also provides an explainable means of understanding the organ motion and spatial correspondence establishment. This work instantiates the recently-proposed physics-informed neural networks (PINNs) to a 3D linear elastic model for modelling prostate motion commonly encountered during transrectal ultrasound guided procedures. To overcome a widely-recognised challenge in generalising PINNs to different subjects, we propose to use PointNet as the nodal-permutation-invariant feature extractor, together with a registration algorithm that aligns point sets and simultaneously takes into account the PINN-imposed biomechanics. The proposed method has been both developed and validated in both patient-specific and multi-patient manner., Comment: IPMI 2023

Published
2023

15. Association between diabetes mellitus and trochanteric bone mineral density in individuals with osteoporotic fractures: a retrospective study

Author

Shao-han Guo, Jian Xu, Min-zhe Xu, Chong Li, Ya-qin Gong, and Ke Lu

Subjects
osteoporotic fractures, diabetes, bone mineral density, sex-specific effects, retrospective analysis, Medicine (General), R5-920
Abstract

BackgroundThe relationship between diabetes mellitus (DM) and bone mineral density (BMD) in patients with osteoporotic fractures (OPFs) remains complex and heterogeneous, specifically between the genders. This study aimed to explore the association between diabetes status and trochanteric BMD in a cohort of patients with OPFs and elucidate the differences between male and female patients.MethodsThis retrospective analysis was performed on 710 admitted patients aged 50 years or older with OPFs. In this study, the exposure variable was diabetes status. Trochanteric BMD comprised the dependent variable. While controlling for covariance influences, generalized estimating equations (GEE) were applied to examine the independent link between diabetes status and trochanteric BMD in OPFs patients. Moreover, a subgroup analysis was also conducted to validate the result’s stability.ResultsA substantial positive association was noted between diabetes status and trochanteric BMD in diabetic patients, as determined by the fully adjusted model (β = 0.017, 95% CI 0.001 to 0.033, p = 0.035). Furthermore, the sex-specific analysis showed a significant positive relationship between diabetes status and trochanteric BMD in male patients (β = 0.040, 95% CI 0.006 to 0.075, p = 0.022), whereas no significant relationship was observed in female patients (β = 0.010, 95% CI −0.008 to 0.028, p = 0.256).ConclusionThis study highlighted the significant sex differences in the impact of diabetes on trochanteric BMD among patients with OPFs. The male diabetic patients had higher trochanteric BMD than their non-diabetic counterparts; however, this association was not evident in female patients. Further research is necessary to understand the underlying mechanisms that contribute to these sex-specific differences and to evaluate the clinical implications of managing fracture risk in diabetic patients.

Published
2024
Full Text
View/download PDF

16. Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration

Author

Li, Yiwen, Fu, Yunguan, Gayo, Iani, Yang, Qianye, Min, Zhe, Saeed, Shaheer, Yan, Wen, Wang, Yipei, Noble, J. Alison, Emberton, Mark, Clarkson, Matthew J., Huisman, Henkjan, Barratt, Dean, Prisacariu, Victor Adrian, and Hu, Yipeng

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

The prowess that makes few-shot learning desirable in medical image analysis is the efficient use of the support image data, which are labelled to classify or segment new classes, a task that otherwise requires substantially more training images and expert annotations. This work describes a fully 3D prototypical few-shot segmentation algorithm, such that the trained networks can be effectively adapted to clinically interesting structures that are absent in training, using only a few labelled images from a different institute. First, to compensate for the widely recognised spatial variability between institutions in episodic adaptation of novel classes, a novel spatial registration mechanism is integrated into prototypical learning, consisting of a segmentation head and an spatial alignment module. Second, to assist the training with observed imperfect alignment, support mask conditioning module is proposed to further utilise the annotation available from the support images. Extensive experiments are presented in an application of segmenting eight anatomical structures important for interventional planning, using a data set of 589 pelvic T2-weighted MR images, acquired at seven institutes. The results demonstrate the efficacy in each of the 3D formulation, the spatial registration, and the support mask conditioning, all of which made positive contributions independently or collectively. Compared with the previously proposed 2D alternatives, the few-shot segmentation performance was improved with statistical significance, regardless whether the support data come from the same or different institutes., Comment: accepted by Medical Image Analysis

Published
2022

18. The association between the triglyceride-glucose index and bone turnover markers in osteoporotic fractures patients aged 50 and above who are hospitalized for surgical intervention: a retrospective cross-sectional study

Author

Jian Xu, Shao-han Guo, Min-zhe Xu, Chong Li, Ya-qin Gong, and Ke Lu

Subjects
P1NP, β-CTX, BTMs, osteoporotic fractures, TyG index, Diseases of the endocrine glands. Clinical endocrinology, RC648-665
Abstract

ObjectiveTo evaluate the correlation between the triglyceride-glucose (TyG) index and bone turnover markers (BTMs) in osteoporotic fractures (OPFs) patients hospitalized for surgical intervention.MethodsA retrospective cross-sectional study was conducted on 3558 OPFs patients hospitalized for surgical intervention between January 2017 and July 2022. The study obtained baseline values for various biomarkers and covariates, including fasting blood glucose, β-C-terminal telopeptide of type I collagen (β-CTX), procollagen type 1 N-terminal propeptide (P1NP), triglycerides, age, sex, body mass index, smoking, drinking, low-density lipoprotein, high-density lipoprotein, aspartate aminotransferase, uric acid, the score of American society of anesthesiologists, homocysteine, parathyroid hormone, apolipoprotein B, apolipoprotein A, magnesium, phosphorus and calcium. Multiple linear regression, curve fitting, threshold effects, and subgroup analyses were also applied.ResultsAfter adjusting for covariates in the regression analysis, the results revealed a negative correlation between β-CTX and P1NP levels and the baseline TyG index. Specifically, a one-unit increase in the TyG index was associated with a reduction in β-CTX levels of -0.06 (95% CI: -0.10, -0.01; P-value = 0.012) and a reduction in P1NP levels of -4.70 (95% CI: -9.30, -0.09; P-value = 0.046). Additionally, the inflection points for the nonlinear correlation between the TyG index and β-CTX and P1NP were found to be K = 6.31 and K = 6.63, respectively.ConclusionThe study demonstrated a negative, non-linear relationship among the TyG index, β-CTX and P1NP in OPFs patients hospitalized for surgical intervention. These findings suggest that elevated TyG index levels may adversely affect bone turnover, potentially contributing to the progression of OP.

Published
2024
Full Text
View/download PDF

20. The impact of using voxel-level segmentation metrics on evaluating multifocal prostate cancer localisation

Author

Yan, Wen, Yang, Qianye, Syer, Tom, Min, Zhe, Punwani, Shonit, Emberton, Mark, Barratt, Dean C., Chiu, Bernard, and Hu, Yipeng

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Dice similarity coefficient (DSC) and Hausdorff distance (HD) are widely used for evaluating medical image segmentation. They have also been criticised, when reported alone, for their unclear or even misleading clinical interpretation. DSCs may also differ substantially from HDs, due to boundary smoothness or multiple regions of interest (ROIs) within a subject. More importantly, either metric can also have a nonlinear, non-monotonic relationship with outcomes based on Type 1 and 2 errors, designed for specific clinical decisions that use the resulting segmentation. Whilst cases causing disagreement between these metrics are not difficult to postulate. This work first proposes a new asymmetric detection metric, adapting those used in object detection, for planning prostate cancer procedures. The lesion-level metrics is then compared with the voxel-level DSC and HD, whereas a 3D UNet is used for segmenting lesions from multiparametric MR (mpMR) images. Based on experimental results we report pairwise agreement and correlation 1) between DSC and HD, and 2) between voxel-level DSC and recall-controlled precision at lesion-level, with Cohen's [0.49, 0.61] and Pearson's [0.66, 0.76] (p-values}<0.001) at varying cut-offs. However, the differences in false-positives and false-negatives, between the actual errors and the perceived counterparts if DSC is used, can be as high as 152 and 154, respectively, out of the 357 test set lesions. We therefore carefully conclude that, despite of the significant correlations, voxel-level metrics such as DSC can misrepresent lesion-level detection accuracy for evaluating localisation of multifocal prostate cancer and should be interpreted with caution.

Published
2022

21. Few-shot image segmentation for cross-institution male pelvic organs using registration-assisted prototypical learning

Author

Li, Yiwen, Fu, Yunguan, Yang, Qianye, Min, Zhe, Yan, Wen, Huisman, Henkjan, Barratt, Dean, Prisacariu, Victor Adrian, and Hu, Yipeng

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

The ability to adapt medical image segmentation networks for a novel class such as an unseen anatomical or pathological structure, when only a few labelled examples of this class are available from local healthcare providers, is sought-after. This potentially addresses two widely recognised limitations in deploying modern deep learning models to clinical practice, expertise-and-labour-intensive labelling and cross-institution generalisation. This work presents the first 3D few-shot interclass segmentation network for medical images, using a labelled multi-institution dataset from prostate cancer patients with eight regions of interest. We propose an image alignment module registering the predicted segmentation of both query and support data, in a standard prototypical learning algorithm, to a reference atlas space. The built-in registration mechanism can effectively utilise the prior knowledge of consistent anatomy between subjects, regardless whether they are from the same institution or not. Experimental results demonstrated that the proposed registration-assisted prototypical learning significantly improved segmentation accuracy (p-values<0.01) on query data from a holdout institution, with varying availability of support data from multiple institutions. We also report the additional benefits of the proposed 3D networks with 75% fewer parameters and an arguably simpler implementation, compared with existing 2D few-shot approaches that segment 2D slices of volumetric medical images., Comment: To appear in the proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI) 2022

Published
2022

23. Association between systemic inflammatory response index and bone turnover markers in Chinese patients with osteoporotic fractures: a retrospective cross-sectional study

Author

Peng Zhou, Ke Lu, Chong Li, Min-zhe Xu, Yao-wei Ye, Hui-qiang Shan, and Yi Yin

Subjects
systemic inflammatory response index, bone turnover markers, osteoporotic fractures, inflammation, osteoporosis, Medicine (General), R5-920
Abstract

BackgroundThe systemic inflammatory response index (SIRI) is a novel composite biomarker of inflammation. However, there is limited information on its use in the context of osteoporotic fractures. Hence, this study aimed to investigate the association between baseline SIRI values and bone turnover markers (BTMs) in Chinese patients diagnosed with osteoporotic fractures (OPFs), to offer a more precise method for assessing bone health and inflammation in clinical settings.MethodsA retrospective cross-sectional study was conducted on 3,558 hospitalized patients with OPFs who required surgery or hospitalization at the First People’s Hospital of Kunshan City from January 2017 to July 2022. Baseline measurements of SIRI, β-CTX (beta-C-terminal telopeptide of type I collagen), and P1NP (procollagen type I N-terminal propeptide) were obtained. The analyses were adjusted for variables, including age, sex, body mass index (BMI), and other initial laboratory and clinical findings. Furthermore, multivariable logistic regression, smooth curve fitting, and threshold analysis were also performed.ResultsThe results revealed a negative correlation between baseline SIRI values and both β-CTX and P1NP levels. After adjusting for covariates in the regression analysis, each unit increase in SIRI was found to be inked to a reduction of 0.04 (β = −0.04; 95% confidence interval [CI], −0.05 to −0.03; with p-value

Published
2024
Full Text
View/download PDF

24. Association of apolipoprotein A1 levels with lumbar bone mineral density and β-CTX in osteoporotic fracture individuals: a cross-sectional investigation

Author

Li-long Feng, Ke Lu, Chong Li, Min-zhe Xu, Yao-wei Ye, Yi Yin, and Hui-qiang Shan

Subjects
osteoporosis, fracture, apolipoprotein A1 (APOA1), bone mineral density (BMD), C-terminal telopeptide of type I collagen (β-CTX), high-density lipoprotein (HDL) osteoporosis, Medicine (General), R5-920
Abstract

BackgroundThe relationship between the levels of high-density lipoprotein (HDL) and bone mineral density (BMD) is controversial. Furthermore, the specific role of apolipoprotein A1 (APOA1), a primary HDL component, in regulating BMD remains unclear. This study aimed to elucidate the correlation between APOA1 levels and lumbar BMD in patients with osteoporotic fracture (OPF) for novel insights into potential therapeutic strategies against osteoporosis.MethodsThis study included 587 OPF patients enrolled at the Kunshan Hospital, Affiliated with Jiangsu University between January 2017 and July 2022. The patient’s serum APOA1 levels were determined, followed by the assessment of lumbar BMD and C-terminal telopeptide of type I collagen (β-CTX) as outcome variables. The association of APOA1 levels with lumbar BMD and β-CTX was assessed via Generalized Estimating Equations (GEE) and spline smoothing plot analyses. A generalized additive model (GAM) helped ascertain non-linear correlations. Moreover, a subgroup analysis was also conducted to validate the result’s stability.ResultsIt was observed that APOA1 levels were positively correlated with lumbar BMD (β = 0.07, 95% CI: 0.02 to 0.11, p = 0.0045), indicating that increased APOA1 levels were linked with enhanced lumbar BMD. Furthermore, APOA1 levels were negatively related to β-CTX (β = −0.19, 95% CI: −0.29 to −0.09, p = 0.0003), suggesting APOA1 might reduce osteolysis. In addition, these findings were robustly supported by subgroup and threshold effect analyses.ConclusionThis study indicated that increased APOA1 levels were correlated with enhanced lumbar BMD and decreased osteolysis in OPF patients. Therefore, APOA1 may inhibit osteoclast activity to prevent further deterioration in osteoporotic patients. However, further research I warranted to validate these conclusions and elucidate the underlying physiologies.

Published
2024
Full Text
View/download PDF

25. Advances in the epidemiology of the effects of maternal obesity on long-term adverse health outcomes in offspring

Author

Min-Jie ZHANG, Min-Zhe ZHANG, Rui CHEN, and Qi-Qiang HE

Subjects
pregnancy, obesity, offspring outcome, maternal obesity, Medicine
Abstract

Obesity has become a global public health problem. In recent years, increasing epidemiological evidence suggests that maternal obesity during pregnancy may not only cause adverse pregnancy outcomes, damage her own health and the health of fetus, but also cause varying degrees of health damage to offspring and impose a significant disease burden on society. This paper reviews the progress of epidemiological studies on the effects of maternal obesity on long-term adverse health outcomes in offspring, in order to provide a basis for developing related prevention strategies.

Published
2023
Full Text
View/download PDF

26. Association between perioperative blood transfusion and length of hospital stay in patients with osteoporotic fractures

Author

Si-ming Xu, Ke Lu, Xu-feng Yang, Yao-wei Ye, Min-zhe Xu, Qin Shi, Ya-qin Gong, and Chong Li

Subjects
Perioperative blood transfusion, Length of hospital stay, Osteoporotic fracture, Diseases of the musculoskeletal system, RC925-935
Abstract

Abstract Background Few studies have examined the relationship between perioperative blood transfusion (PBT) and length of hospital stay (LOS) in patients with osteoporotic fractures. This research aims to study the association between PBT and LOS. Methods This is a retrospective cross-sectional study from the Affiliated Kunshan Hospital of Jiangsu University, Suzhou, China, involving 2357 osteoporotic fractures (OPF) patients who received surgical treatment during hospitalization from January 2017 and March 2022. Multiple linear regression was used to analyze the relationship between PBT and LOS. In the analysis, PBT volume was the dependent variable, whereas LOS was the independent variable. Simultaneously, age, gender, body mass index, hemoglobin, primary diagnosis, American Society of Anesthesiologists, creatinine (Cr), anesthesia, surgical method, and Charlson comorbidity index were included as covariates. The generalized additive model was then used to study nonlinear associations. Two piecewise linear regression exemplary evaluated the inception results for smoothing the curve. Results Our results proved that PBT was positively correlated with LOS in the fully adjusted model (β, 0.21; 95% CI, 0.04 to 0.37; P

Published
2023
Full Text
View/download PDF

27. Association between serum 25-hydroxyvitamin D and fasting blood glucose in osteoporosis patients

Author

Yao-wei Ye, Ke Lu, Yi Yin, Xu-feng Yang, Si-ming Xu, Min-zhe Xu, Qin Shi, and Ya-qin Gong

Subjects
Medicine, Science
Abstract

Abstract Osteoporosis (OP) is often associated with other complications, such as impaired glucose homeostasis. Vitamin D deficiency is common and has been linked to bone metabolism and the regulation of blood sugar levels. The aim of this study was to evaluate the independent relationship between serum 25-hydroxyvitamin D (25[OH]D) and fasting blood glucose levels (FBG) in a group of patients diagnosed with OP. This is a retrospective cross-sectional study from a prospectively collected database at our tertiary referral center. Consecutive 2084 OP patients who were hospitalization were finally analyzed in this study. FBG is the dependent variable, serum 25(OH)D level of OP patients is exposure variable of this study. There was a linear significantly negative association between serum 25(OH)D and FBG (β, − 0.02; 95% CI − 0.03 to − 0.01; P = 0.0011) in the fully adjusted models. Specifically, when serum 25(OH)D level was less than 23.39 ng/mL, FBG decreased by 0.04 mmol/L for every 1 ng/mL increase of serum 25(OH)D level. When serum 25(OH)D was greater than 23.39 ng/ mL, the negative association was insignificant (P = 0.9616). If the association is confirmed, the clinical management of blood glucose in OP patients with serum 25(OH)D deficiency has instructive implications.

Published
2023
Full Text
View/download PDF

28. Controlling False Positive/Negative Rates for Deep-Learning-Based Prostate Cancer Detection on Multiparametric MR images

Author

Min, Zhe, Bianco, Fernando J., Yang, Qianye, Rodell, Rachael, Yan, Wen, Barratt, Dean, and Hu, Yipeng

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Prostate cancer (PCa) is one of the leading causes of death for men worldwide. Multi-parametric magnetic resonance (mpMR) imaging has emerged as a non-invasive diagnostic tool for detecting and localising prostate tumours by specialised radiologists. These radiological examinations, for example, for differentiating malignant lesions from benign prostatic hyperplasia in transition zones and for defining the boundaries of clinically significant cancer, remain challenging and highly skill-and-experience-dependent. We first investigate experimental results in developing object detection neural networks that are trained to predict the radiological assessment, using these high-variance labels. We further argue that such a computer-assisted diagnosis (CAD) system needs to have the ability to control the false-positive rate (FPR) or false-negative rate (FNR), in order to be usefully deployed in a clinical workflow, informing clinical decisions without further human intervention. This work proposes a novel PCa detection network that incorporates a lesion-level cost-sensitive loss and an additional slice-level loss based on a lesion-to-slice mapping function, to manage the lesion- and slice-level costs, respectively. Our experiments based on 290 clinical patients concludes that 1) The lesion-level FNR was effectively reduced from 0.19 to 0.10 and the lesion-level FPR was reduced from 1.03 to 0.66 by changing the lesion-level cost; 2) The slice-level FNR was reduced from 0.19 to 0.00 by taking into account the slice-level cost; (3) Both lesion-level and slice-level FNRs were reduced with lower FP/FPR by changing the lesion-level or slice-level costs, compared with post-training threshold adjustment using networks without the proposed cost-aware training., Comment: Accepted by 25th UK Conference on Medical Image Understanding and Analysis(MIUA 2021)

Published
2021

30. Association of 25-hydroxyvitamin D levels with lipid profiles in osteoporosis patients: a retrospective cross-sectional study

Author

Si-ming Xu, Ke Lu, Xu-feng Yang, Yao-wei Ye, Min-zhe Xu, Qin Shi, Ya-qin Gong, and Chong Li

Subjects
25(OH)D, Blood lipid, Osteoporosis, HDL-C, LDL-C, TG, Orthopedic surgery, RD701-811, Diseases of the musculoskeletal system, RC925-935
Abstract

Abstract Background In the literature, scarce data investigate the link between 25-hydroxyvitamin D (25[OH]D) and blood lipids in the osteoporosis (OP) population. 25(OH)D, as a calcium-regulating hormone, can inhibit the rise of parathyroid hormone, increase bone mineralization to prevent bone loss, enhance muscle strength, improve balance, and prevent falls in the elderly. This retrospective cross-sectional study aimed to investigate the association between serum 25(OH)D levels and lipid profiles in patients with osteoporosis, with the objective of providing insight for appropriate vitamin D supplementation in clinical settings to potentially reduce the incidence of cardiovascular disease, which is known to be a major health concern for individuals with osteoporosis. Methods This is a retrospective cross-sectional study from the Affiliated Kunshan Hospital of Jiangsu University, including 2063 OP patients who received biochemical blood analysis of lipids during hospitalization from January 2015 to March 2022. The associations between serum lipids and 25(OH)D levels were examined by multiple linear regression. The dependent variables in the analysis were the concentrations of serum lipoprotein, total cholesterol (TC), triglycerides (TGs), apolipoprotein-A, lipoprotein A, high-density lipoprotein cholesterol and low-density lipoprotein cholesterol (LDL-C). The independent variable was the concentration of blood serum 25(OH)D. At the same time, age, body mass index, sex, time and year of serum analysis, primary diagnosis, hypertension, diabetes, statins usage, beta-C-terminal telopeptide of type I collagen, procollagen type I N-terminal propeptide were covariates. Blood samples were collected in the early morning after the overnight fasting and were analyzed using an automated electrochemiluminescence immunoassay on the LABOSPECT 008AS platform (Hitachi Hi-Tech Co., Ltd., Tokyo, Japan). The generalized additive model was further applied for nonlinear associations. The inception result for smoothing the curve was evaluated by two-piecewise linear regression exemplary. Results Our results proved that in the OP patients, the serum 25(OH)D levels were inversely connected with blood TGs concentration, whereas they were positively associated with the HDL, apolipoprotein-A, and lipoprotein A levels. In the meantime, this research also found a nonlinear relationship and threshold effect between serum 25(OH)D and TC, LDL-C. Furthermore, there were positive correlations between the blood serum 25(OH)D levels and the levels of TC and LDL-C when 25(OH)D concentrations ranged from 0 to 10.04 ng/mL. However, this relationship was not present when 25(OH)D levels were higher than 10.04 ng/mL. Conclusions Our results demonstrated an independent relationship between blood lipids and vitamin D levels in osteoporosis patients. While we cannot establish a causal relationship between the two, our findings suggest that vitamin D may have beneficial effects on both bone health and blood lipid levels, providing a reference for improved protection against cardiovascular disease in this population. Further research, particularly interventional studies, is needed to confirm these associations and investigate their underlying mechanisms.

Published
2023
Full Text
View/download PDF

31. DeepReg: a deep learning toolkit for medical image registration

Author

Fu, Yunguan, Brown, Nina Montaña, Saeed, Shaheer U., Casamitjana, Adrià, Baum, Zachary M. C., Delaunay, Rémi, Yang, Qianye, Grimwood, Alexander, Min, Zhe, Blumberg, Stefano B., Iglesias, Juan Eugenio, Barratt, Dean C., Bonmati, Ester, Alexander, Daniel C., Clarkson, Matthew J., Vercauteren, Tom, and Hu, Yipeng

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

DeepReg (https://github.com/DeepRegNet/DeepReg) is a community-supported open-source toolkit for research and education in medical image registration using deep learning., Comment: Accepted in The Journal of Open Source Software (JOSS)

Published
2020
Full Text
View/download PDF

38. Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition

Author

Zhu, Delong, Liu, Jianbang, Ma, Nachuan, Min, Zhe, and Meng, Max Q. -H.

Subjects
Computer Science - Robotics, Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Elevator button recognition is considered an indispensable function for enabling the autonomous elevator operation of mobile robots. However, due to unfavorable image conditions and various image distortions, the recognition accuracy remains to be improved. In this paper, we present a novel algorithm that can autonomously correct perspective distortions of elevator panel images. The algorithm first leverages the Gaussian Mixture Model (GMM) to conduct a grid fitting process based on button recognition results, then utilizes the estimated grid centers as reference features to estimate camera motions for correcting perspective distortions. The algorithm performs on a single image autonomously and does not need explicit feature detection or feature matching procedure, which is much more robust to noises and outliers than traditional feature-based geometric approaches. To verify the effectiveness of the algorithm, we collect an elevator panel dataset of 50 images captured from different angles of view. Experimental results show that the proposed algorithm can accurately estimate camera motions and effectively remove perspective distortions.

Published
2019

42. ReHand: Secure Region-based Fast Handover with User Anonymity for Small Cell Networks in 5G

Author

Fan, Chun-I, Huang, Jheng-Jia, Zhong, Min-Zhe, Hsu, Ruei-Hau, Chen, Wen-Tsuen, and Lee, Jemin

Subjects
Computer Science - Cryptography and Security
Abstract

Due to the expectedly higher density of mobile devices and exhaust of radio resources, the fifth generation (5G) mobile networks introduce small cell concept in the radio access technologies, so-called Small Cell Networks (SCNs), to improve radio spectrum utilization. However, this increases the chance of handover due to smaller coverage of a micro base station, i.e., home eNodeB (HeNB) in 5G. Subsequently, the latency will increase as the costs of authenticated key exchange protocol, which ensures entity authentication and communication confidentiality for secure handover, also increase totally. Thus, this work presents a secure region-based handover scheme (ReHand) with user anonymity and fast revocation for SCNs in 5G. ReHand greatly reduces the communication costs when UEs roam between small cells within the region of a macro base station, i.e., eNB in 5G, and the computation costs due to the employment of symmetry-based cryptographic operations. Compared to the three elaborated related works, ReHand dramatically reduces the costs from 82.92% to 99.99%. Nevertheless, this work demonstrates the security of ReHand by theoretically formal proofs., Comment: Under submission to possible journal publications

Published
2018

44. Association between fibrinogen-to-albumin ratio and bone metabolism markers (β-CTX and P1NP) in Chinese individuals with osteoporotic fracture: a cross-sectional investigation.

Author

Feng, Li-long, Lu, Ke, Li, Chong, Xu, Min-zhe, Ye, Yao-wei, Yin, Yi, and Shan, Hui-qiang

Subjects
BONE health, BONE metabolism, GENERALIZED estimating equations, BONE fractures, COLLAGEN
Abstract

Objective: Research on the link between inflammatory indicators and markers of bone metabolism is currently lacking, especially the interaction between Procollagen type 1 N-terminal propeptide (P1NP), the β-C-terminal telopeptide of type 1 collagen (β-CTX), and the fibrinogen-to-albumin ratio (FAR). This study intends to fill that knowledge gap by investigating the possible link between inflammatory indicators and bone metabolism. Methods: This observational study included 718 individuals diagnosed with osteoporotic fractures from Kunshan Hospital Affiliated to Jiangsu University between January 2017 and July 2022. After accounting for several confounders, the independent connection between FAR levels and β-CTX and P1NP was investigated via Generalized Estimating Equations (GEE). On top of that, we used a generalized additive model (GAM) to find any non-linear correlations, and a two-piecewise linear regression model to find the threshold effects in the smoothing curves that came out of it. To ensure the aforementioned result was stable, a subgroup analysis was carried out. Results: The results showed a positive linear correlation between FAR and β-CTX [β = 1.077, 95% confidence interval (CI): 0.24 to 1.92, P = 0.012]. The study's findings demonstrated that FAR and P1NP fit curves in an inverted U-shaped pattern, and an inflection point K = 0.0685 for FAR was detected. P1NP showed a positive correlation with FAR below the inflection point (β = 306.10, 95% CI: 47.37 to 564.83, P = 0.021), and a negative correlation with FAR beyond the inflection point (β = -117.57, 95% CI: -231.34 to -3.80, P = 0.043). The subgroup analysis revealed that women had a more significant association between FAR and β-CTX in women than in men. Conclusions: The results provide useful insights into the potential association between FAR and markers of bone metabolism. The study may provide a novel clinical implication by introducing FAR as a potential reference indicator for assessing bone health, offering a cost-effective and conveniently obtainable biomarker to monitor inflammation to improve bone metabolism in the treatment of osteoporosis. [ABSTRACT FROM AUTHOR]

Published
2025
Full Text
View/download PDF

50. Utilizing a pH-responsive palladium nanocomposite to fabricate adhesion-enhanced and highly reliable copper coating on nylon 6 fabrics

Author

Jhu-Lin You, Yi-Shin Chen, Chang-Pin Chang, Min-Zhe Wu, and Ming-Der Ger

Subjects
Nylon 6 fabrics, Copper layer, Nanocomposite, pH-responsive, Electroless plating, Conductive polymers, Mining engineering. Metallurgy, TN1-997
Abstract

Conductive fibers are an important part of wearable electronic devices or smart textiles while several grand challenges have to be still overcome. In this study, we describe a simple and efficient method to prepare a copper layer on nylon 6 fabrics by using a pH-responsive styrene (St)-co-N, N-dimethyl-dimethylaminoethyl methacrylate (DMAEMA)/Pd nanocomposite. The St-co-DMAEMA/Pd can effectively enhance the adhesion between the copper layer and the substrate. Nylon 6 fabric is treated with an optimal acid concentration of 2.0 M before electroless deposition. The pretreatment will promote the affinity between the nanocomposite catalyst and the modified nylon 6 fabric and form a more favorable environment for copper deposition. Furthermore, the process yields excellent copper deposition (1.59 μm) onto nylon 6 fabric after electroless plating for 20 min. The copper layer formed by the method has a low resistance of about 2.51 Ω and the variation of resistance before and after bending test is small. In addition, the characteristic of pH responsive copolymers (St-co-DMAEMA) that displays high hydrophilicity at low pH values and high hydrophobicity at high pH values is crucial for electroless copper plating. This facile method is successfully applied in the metallization of nylon 6 fabric.

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results