arXiv subjects

Yi Xiong

Publications and source records attributed to Yi Xiong.

At least 37 records · Page 2Linked to original sources

arXiv2024

Cost-Effectiveness Analysis for Disease Prevention -- A Case Study on Colorectal Cancer Screening

Cancer Screening has been widely recognized as an effective strategy for preventing the disease. Despite its effectiveness, determining when to start screening is complicated, because starting too early increases the number of screenings over lifetime and thus costs but starting too late may miss the cancer that could have been prevented. Therefore, to make an informed recommendation on the age to start screening, it is necessary to conduct cost-effectiveness analysis to assess the gain in life years relative to the cost of screenings. As more large-scale observational studies become accessible, there is growing interest in evaluating cost-effectiveness based on empirical evidence. In this paper, we propose a unified measure for evaluating cost-effectiveness and a causal analysis for the continuous intervention of screening initiation age, under the multi-state modeling with semi-competing risks. Extensive simulation results show that the proposed estimators perform well in realistic scenarios. We perform a cost-effectiveness analysis of the colorectal cancer screening, utilizing data from the large-scale Women's Health Initiative. Our analysis reveals that initiating screening at age 50 years yields the highest quality-adjusted life years with an acceptable incremental cost-effectiveness ratio compared to no screening, providing real-world evidence in support of screening recommendation for colorectal cancer.

stat.ME↗

arXiv2024

Exploring Differences between Two Decades of Mental Health Related Emergency Department Visits by Youth via Recurrent Events Analyses

We aim to develop a tool for understanding how the mental health of youth aged less than 18 years evolve over time through administrative records of mental health related emergency department (MHED) visits in two decades. Administrative health data usually contain rich information for investigating public health issues; however, many restrictions and regulations apply to their use. Moreover, the data are usually not in a conventional format since administrative databases are created and maintained to serve non-research purposes and only information for people who seek health services is accessible. Analysis of administrative health data is thus challenging in general. In the MHED data analyses, we are particularly concerned with (i) evaluating dynamic patterns and impacts with doubly-censored recurrent event data, and (ii) re-calibrating estimators developed based on truncated data by leveraging summary statistics from the population. The findings are verified empirically via simulation. We have established the asymptotic properties of the inference procedures. The contributions of this paper are twofold. We present innovative strategies for processing doubly-censored recurrent event data, and overcoming the truncation induced by the data collection. In addition, through exploring the pediatric MHED visit records, we provide new insights into children/youths mental health changes over time.

stat.ME↗

arXiv2024

Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound

Standard plane localization is crucial for ultrasound (US) diagnosis. In prenatal US, dozens of standard planes are manually acquired with a 2D probe. It is time-consuming and operator-dependent. In comparison, 3D US containing multiple standard planes in one shot has the inherent advantages of less user-dependency and more efficiency. However, manual plane localization in US volume is challenging due to the huge search space and large fetal posture variation. In this study, we propose a novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US. Our contribution is two-fold. First, we equip the RL framework with a landmark-aware alignment module to provide warm start and strong spatial bounds for the agent actions, thus ensuring its effectiveness. Second, instead of passively and empirically terminating the agent inference, we propose a recurrent neural network based strategy for active termination of the agent's interaction procedure. This improves both the accuracy and efficiency of the localization system. Extensively validated on our in-house large dataset, our approach achieves the accuracy of 3.4mm/9.6° and 2.7mm/9.1° for the transcerebellar and transthalamic plane localization, respectively. Ourproposed RL framework is general and has the potential to improve the efficiency and standardization of US scanning.

eess.IV↗

arXiv2023

FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound

Fetal pose estimation in 3D ultrasound (US) involves identifying a set of associated fetal anatomical landmarks. Its primary objective is to provide comprehensive information about the fetus through landmark connections, thus benefiting various critical applications, such as biometric measurements, plane localization, and fetal movement monitoring. However, accurately estimating the 3D fetal pose in US volume has several challenges, including poor image quality, limited GPU memory for tackling high dimensional data, symmetrical or ambiguous anatomical structures, and considerable variations in fetal poses. In this study, we propose a novel 3D fetal pose estimation framework (called FetusMapV2) to overcome the above challenges. Our contribution is three-fold. First, we propose a heuristic scheme that explores the complementary network structure-unconstrained and activation-unreserved GPU memory management approaches, which can enlarge the input image resolution for better results under limited GPU memory. Second, we design a novel Pair Loss to mitigate confusion caused by symmetrical and similar anatomical structures. It separates the hidden classification task from the landmark localization task and thus progressively eases model learning. Last, we propose a shape priors-based self-supervised learning by selecting the relatively stable landmarks to refine the pose online. Extensive experiments and diverse applications on a large-scale fetal US dataset including 1000 volumes with 22 landmarks per volume demonstrate that our method outperforms other strong competitors.

eess.IV↗

arXiv2022

SESNet: sequence-structure feature-integrated deep learning method for data-efficient protein engineering

Deep learning has been widely used for protein engineering. However, it is limited by the lack of sufficient experimental data to train an accurate model for predicting the functional fitness of high-order mutants. Here, we develop SESNet, a supervised deep-learning model to predict the fitness for protein mutants by leveraging both sequence and structure information, and exploiting attention mechanism. Our model integrates local evolutionary context from homologous sequences, the global evolutionary context encoding rich semantic from the universal protein sequence space and the structure information accounting for the microenvironment around each residue in a protein. We show that SESNet outperforms state-of-the-art models for predicting the sequence-function relationship on 26 deep mutational scanning datasets. More importantly, we propose a data augmentation strategy by leveraging the data from unsupervised models to pre-train our model. After that, our model can achieve strikingly high accuracy in prediction of the fitness of protein mutants, especially for the higher order variants (> 4 mutation sites), when finetuned by using only a small number of experimental mutation data (<50). The strategy proposed is of great practical value as the required experimental effort, i.e., producing a few tens of experimental mutation data on a given protein, is generally affordable by an ordinary biochemical group and can be applied on almost any protein.

q-bio.QM↗

arXiv2022

A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases

Gonadotrophin-releasing hormone receptor (GnRH1R) is a promising therapeutic target for the treatment of uterine diseases. To date, several GnRH1R antagonists are available in clinical investigation without satisfying multiple property constraints. To fill this gap, we aim to develop a deep learning-based framework to facilitate the effective and efficient discovery of a new orally active small-molecule drug targeting GnRH1R with desirable properties. In the present work, a ligand-and-structure combined model, namely LS-MolGen, was firstly proposed for molecular generation by fully utilizing the information on the known active compounds and the structure of the target protein, which was demonstrated by its superior performance than ligand- or structure-based methods separately. Then, a in silico screening including activity prediction, ADMET evaluation, molecular docking and FEP calculation was conducted, where ~30,000 generated novel molecules were narrowed down to 8 for experimental synthesis and validation. In vitro and in vivo experiments showed that three of them exhibited potent inhibition activities (compound 5 IC50 = 0.856 nM, compound 6 IC50 = 0.901 nM, compound 7 IC50 = 2.54 nM) against GnRH1R, and compound 5 performed well in fundamental PK properties, such as half-life, oral bioavailability, and PPB, etc. We believed that the proposed ligand-and-structure combined molecular generative model and the whole computer-aided workflow can potentially be extended to similar tasks for de novo drug design or lead optimization.

q-bio.BM↗

arXiv2022

Sublinear Regret for Learning POMDPs

We study the model-based undiscounted reinforcement learning for partially observable Markov decision processes (POMDPs). The oracle we consider is the optimal policy of the POMDP with a known environment in terms of the average reward over an infinite horizon. We propose a learning algorithm for this problem, building on spectral method-of-moments estimations for hidden Markov models, the belief error control in POMDPs and upper-confidence-bound methods for online learning. We establish a regret bound of $O(T^{2/3}\sqrt{\log T})$ for the proposed learning algorithm where $T$ is the learning horizon. This is, to the best of our knowledge, the first algorithm achieving sublinear regret with respect to our oracle for learning general POMDPs.

cs.LG↗

arXiv2022

Fine-grained Correlation Loss for Regression

Regression learning is classic and fundamental for medical image analysis. It provides the continuous mapping for many critical applications, like the attribute estimation, object detection, segmentation and non-rigid registration. However, previous studies mainly took the case-wise criteria, like the mean square errors, as the optimization objectives. They ignored the very important population-wise correlation criterion, which is exactly the final evaluation metric in many tasks. In this work, we propose to revisit the classic regression tasks with novel investigations on directly optimizing the fine-grained correlation losses. We mainly explore two complementary correlation indexes as learnable losses: Pearson linear correlation (PLC) and Spearman rank correlation (SRC). The contributions of this paper are two folds. First, for the PLC on global level, we propose a strategy to make it robust against the outliers and regularize the key distribution factors. These efforts significantly stabilize the learning and magnify the efficacy of PLC. Second, for the SRC on local level, we propose a coarse-to-fine scheme to ease the learning of the exact ranking order among samples. Specifically, we convert the learning for the ranking of samples into the learning of similarity relationships among samples. We extensively validate our method on two typical ultrasound image regression tasks, including the image quality assessment and bio-metric measurement. Experiments prove that, with the fine-grained guidance in directly optimizing the correlation, the regression performances are significantly improved. Our proposed correlation losses are general and can be extended to more important applications.

cs.CV↗

arXiv2022

Weakly-supervised High-fidelity Ultrasound Video Synthesis with Feature Decoupling

Ultrasound (US) is widely used for its advantages of real-time imaging, radiation-free and portability. In clinical practice, analysis and diagnosis often rely on US sequences rather than a single image to obtain dynamic anatomical information. This is challenging for novices to learn because practicing with adequate videos from patients is clinically unpractical. In this paper, we propose a novel framework to synthesize high-fidelity US videos. Specifically, the synthesis videos are generated by animating source content images based on the motion of given driving videos. Our highlights are three-fold. First, leveraging the advantages of self- and fully-supervised learning, our proposed system is trained in weakly-supervised manner for keypoint detection. These keypoints then provide vital information for handling complex high dynamic motions in US videos. Second, we decouple content and texture learning using the dual decoders to effectively reduce the model learning difficulty. Last, we adopt the adversarial training strategy with GAN losses for further improving the sharpness of the generated videos, narrowing the gap between real and synthesis videos. We validate our method on a large in-house pelvic dataset with high dynamic motion. Extensive evaluation metrics and user study prove the effectiveness of our proposed method.

cs.CV↗

arXiv2022

Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound

Standard plane recognition plays an important role in prenatal ultrasound (US) screening. Automatically recognizing the standard plane along with the corresponding anatomical structures in US image can not only facilitate US image interpretation but also improve diagnostic efficiency. In this study, we build a novel multi-label learning (MLL) scheme to identify multiple standard planes and corresponding anatomical structures of fetus simultaneously. Our contribution is three-fold. First, we represent the class correlation by word embeddings to capture the fine-grained semantic and latent statistical concurrency. Second, we equip the MLL with a graph convolutional network to explore the inner and outer relationship among categories. Third, we propose a novel cluster relabel-based contrastive learning algorithm to encourage the divergence among ambiguous classes. Extensive validation was performed on our large in-house dataset. Our approach reports the highest accuracy as 90.25% for standard planes labeling, 85.59% for planes and structures labeling and mAP as 94.63%. The proposed MLL scheme provides a novel perspective for standard plane recognition and can be easily extended to other medical image classification tasks.

cs.CV↗

arXiv2022

Macroscopic analysis of time dependent plasticity in Ti alloys

Component failure due to cold dwell fatigue of titanium and its alloys is a long-standing problem which has significant safety and economic implications to the aviation industry. This can be addressed by understanding the governing mechanisms of time dependent plasticity behaviour of Ti at low temperatures. Here, stress relaxation tests were performed at four different temperatures on three major alloy systems: commercially pure titanium (two alloys with different oxygen content), Ti-6Al-4V (two microstructures with differing beta phase fractions) and Ti-6Al-2Sn-4Zr-xMo (two alloys with different Mo content x= 2 or 6, and portion of beta phase). Key parameters controlling the time dependent plasticity were determined as a function of temperature. Both activation volume and energy were found to increase with temperature in all six alloys. It was found that the dwell fatigue effect is more significant by oxygen alloying but is suppressed by the addition of Mo. The presence of the beta phase did not strongly affect the dwell fatigue, however, it was suppressed at high temperature due to the low strain rate and strain rate sensitivity.

cond-mat.mtrl-sci↗

arXiv2021

Debiasing Samples from Online Learning Using Bootstrap

It has been recently shown in the literature that the sample averages from online learning experiments are biased when used to estimate the mean reward. To correct the bias, off-policy evaluation methods, including importance sampling and doubly robust estimators, typically calculate the conditional propensity score, which is ill-defined for non-randomized policies such as UCB. This paper provides a procedure to debias the samples using bootstrap, which doesn't require the knowledge of the reward distribution and can be applied to any adaptive policies. Numerical experiments demonstrate the effective bias reduction for samples generated by popular multi-armed bandit algorithms such as Explore-Then-Commit (ETC), UCB, Thompson sampling (TS) and $ε$-greedy (EG). We analyze and provide theoretical justifications for the procedure under the ETC algorithm, including the asymptotic convergence of the bias decay rate in the real and bootstrap worlds.

cs.LG↗

arXiv2021

Weighted ellipse fitting routine for spotty or incomplete Debye-Scherrer rings on a 2D detector

We introduce a weighted ellipse fitting routine to measure Debye Scherrer rings acquired on 2D area detectors and demonstrate its use in strain determination. The method is relatively robust against incomplete rings due to low number of grains in the diffraction volume (spotty rings), or strong texture (intensity depletion in some azimuths). The method works by applying an annular mask around each diffraction ring and fitting an ellipse, using all pixel positions and their diffracted intensity as weights in the minimisation. We compare this method to the more popular cake integration method, and show that the weighted ellipse method works when the cake integration method fails or works poorly. The lattice strain sensitivity from spotty diffraction rings is in the order or 2E-5 or better. The algorithm has been made available for public use and works with 2D diffraction patterns acquired in a laboratory scale XRD equipment, TEM or a synchrotron.

physics.app-ph↗

arXiv2021

Privacy-Preserved Average Consensus Algorithms with Edge-based Additive Perturbations

In this paper, we consider the privacy preservation problem in both discrete- and continuous-time average consensus algorithms with strongly connected and balanced graphs, against either internal honest-but-curious agents or external eavesdroppers. A novel algorithm is proposed, which adds edge-based perturbation signals to the process of consensus computation. Our algorithm can be divided into two phases: a coordinated scrambling phase, which is for privacy preservation, and a convergence phase. In the scrambling phase, each agent is required to generate some perturbation signals and add them to the edges leading out of it. In the convergence phase, the agents update their states following a normal updating rule. It is shown that an internal honest-but-curious agent can obtain the privacy of a target agent if and only if no other agents can communicate with the target agent.

eess.SY↗

arXiv2021

Cold dwell behaviour of Ti$_6$Al alloy: Understanding load shedding using digital image correlation and crystal plasticity simulations

Digital image correlation (DIC) and crystal plasticity simulation were utilised to study cold dwell behaviour in a coarse grain Ti-6Al alloy at 3 different temperatures up to 230 C. Strains extracted from large volume grains were measured during creep by DIC and were used to calibrate the crystal plasticity model. The values of critical resolved shear stresses (CRSS) of the two main slip systems (basal and prismatic) were determined as a function of temperature. Stress along paths across the boundaries of two grain pairs, (1) a `rogue' grain pair and (2) a `non-rogue' grain pair, were determined at different temperatures. Load shedding was observed in the `rogue' grain pair, where a stress increment during the creep period was found in the `hard' grain. At elevated temperatures, 120 C was found to be the worst-case scenario as the stress difference at the grain boundaries of these two grain pairs were found to be the largest among the three temperatures. This can be attributed to the fact that the strain rate sensitivity of both prismatic and basal slip systems is at its greatest in this worst-case scenario temperature.

cond-mat.mtrl-sci↗

arXiv2021

Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound

3D ultrasound (US) has become prevalent due to its rich spatial and diagnostic information not contained in 2D US. Moreover, 3D US can contain multiple standard planes (SPs) in one shot. Thus, automatically localizing SPs in 3D US has the potential to improve user-independence and scanning-efficiency. However, manual SP localization in 3D US is challenging because of the low image quality, huge search space and large anatomical variability. In this work, we propose a novel multi-agent reinforcement learning (MARL) framework to simultaneously localize multiple SPs in 3D US. Our contribution is four-fold. First, our proposed method is general and it can accurately localize multiple SPs in different challenging US datasets. Second, we equip the MARL system with a recurrent neural network (RNN) based collaborative module, which can strengthen the communication among agents and learn the spatial relationship among planes effectively. Third, we explore to adopt the neural architecture search (NAS) to automatically design the network architecture of both the agents and the collaborative module. Last, we believe we are the first to realize automatic SP localization in pelvic US volumes, and note that our approach can handle both normal and abnormal uterus cases. Extensively validated on two challenging datasets of the uterus and fetal brain, our proposed method achieves the average localization accuracy of 7.03 degrees/1.59mm and 9.75 degrees/1.19mm. Experimental results show that our light-weight MARL model has higher accuracy than state-of-the-art methods.

cs.CV↗

arXiv2021

Agent with Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound

Accurate standard plane (SP) localization is the fundamental step for prenatal ultrasound (US) diagnosis. Typically, dozens of US SPs are collected to determine the clinical diagnosis. 2D US has to perform scanning for each SP, which is time-consuming and operator-dependent. While 3D US containing multiple SPs in one shot has the inherent advantages of less user-dependency and more efficiency. Automatically locating SP in 3D US is very challenging due to the huge search space and large fetal posture variations. Our previous study proposed a deep reinforcement learning (RL) framework with an alignment module and active termination to localize SPs in 3D US automatically. However, termination of agent search in RL is important and affects the practical deployment. In this study, we enhance our previous RL framework with a newly designed adaptive dynamic termination to enable an early stop for the agent searching, saving at most 67% inference time, thus boosting the accuracy and efficiency of the RL framework at the same time. Besides, we validate the effectiveness and generalizability of our algorithm extensively on our in-house multi-organ datasets containing 433 fetal brain volumes, 519 fetal abdomen volumes, and 683 uterus volumes. Our approach achieves localization error of 2.52mm/10.26 degrees, 2.48mm/10.39 degrees, 2.02mm/10.48 degrees, 2.00mm/14.57 degrees, 2.61mm/9.71 degrees, 3.09mm/9.58 degrees, 1.49mm/7.54 degrees for the transcerebellar, transventricular, transthalamic planes in fetal brain, abdominal plane in fetal abdomen, and mid-sagittal, transverse and coronal planes in uterus, respectively. Experimental results show that our method is general and has the potential to improve the efficiency and standardization of US scanning.

eess.IV↗

arXiv2021

Regime Switching Bandits

We study a multi-armed bandit problem where the rewards exhibit regime switching. Specifically, the distributions of the random rewards generated from all arms are modulated by a common underlying state modeled as a finite-state Markov chain. The agent does not observe the underlying state and has to learn the transition matrix and the reward distributions. We propose a learning algorithm for this problem, building on spectral method-of-moments estimations for hidden Markov models, belief error control in partially observable Markov decision processes and upper-confidence-bound methods for online learning. We also establish an upper bound $O(T^{2/3}\sqrt{\log T})$ for the proposed learning algorithm where $T$ is the learning horizon. Finally, we conduct proof-of-concept experiments to illustrate the performance of the learning algorithm.

cs.LG↗