Kang Li

Rutgers, The State University of New Jersey | Rutgers · Department of Orthopaedics

Gait analysis for patients with orthopedic joint diseases is crucial to understand their functional status. Inertial measurement unit (IMU) systems, as alternatives to optical motion capture (OMC) systems, enable gait analysis outside the laboratory. However, their accuracy requires validated before widespread clinical use. Therefore, this study ev...

Multi-channel EEG signals are commonly used for the diagnosis and assessment of diseases such as epilepsy. Currently, various EEG diagnostic algorithms based on deep learning have been developed. However, most research efforts focus solely on diagnosing and classifying current signal data but do not consider the prediction of future trends for earl...

Background Knee osteoarthritis (OA) is a common and serious joint disease and patients mainly suffer from knee pain and dysfunction, significantly impacting their quality of life and daily activities. Non-pharmacological treatments and total knee arthroplasty (TKA) are the two major treatments for knee OA. TKA is the primary treatment for severe kn...

Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing. We introduce DICE (Discrete Inversion for Controllable Editing), the first approach to enable precise inversion for discrete diffusion models, including multinomial diffusion and masked gene...

Background Unicompartmental knee arthroplasty (UKA) has been proved to be a successful treatment for osteoarthritis patients. However, the stress shielding caused by mismatch in mechanical properties between human bones and artificial implants remains as a challenging issue. This study aimed to properly design a bionic porous tibial implant and eva...

The recent advent of in-context learning (ICL) capabilities in large pre-trained models has yielded significant advancements in the generalization of segmentation models. By supplying domain-specific image-mask pairs, the ICL model can be effectively guided to produce optimal segmentation outcomes, eliminating the necessity for model fine-tuning or...

Continuous hemodynamic monitoring in a wearable means can play a crucial role in managing hypertension and preventing catastrophic cardiovascular events. In this study, we have described the fully wearable tonometric device, referred to as flexible adaptive sensing tonometry (FAST), which is capable of continuous and accurate monitoring of hemodyna...

Anomalies or failures in medical equipment may lead to severe consequences. Data-driven prognostic and health management (PHM) approaches can improve maintenance efficiency and reduce maintenance costs at hospitals while protecting patients’ lives. However, currently, the research and application of PHM in medical equipment is still rather limited....

Background: Large language models (LLMs) have achieved great progress in natural language processing tasks and demonstrated the potential for use in clinical applications. Despite their capabilities, LLMs in the medical domain are prone to generating hallucinations (not fully reliable responses). Hallucinations in LLMs' responses create substantia...

Ensuring the general efficacy and goodness for human beings from medical large language models (LLM) before real-world deployment is crucial. However, a widely accepted and accessible evaluation process for medical LLM, especially in the Chinese context, remains to be established. In this work, we introduce "MedBench", a comprehensive, standardized...

Background Stress hyperglycemia occurs frequently in patients following acute myocardial infarction (AMI) and may aggravate myocardial stiffness, but relevant evidence is still lacking. Accordingly, this study aimed to examine the impact of admission stress hyperglycemia on left ventricular (LV) myocardial deformation in patients following AMI. Me...

Multimodal learning, integrating histology images and genomics, promises to enhance precision oncology with comprehensive views at microscopic and molecular levels. However, existing methods may not sufficiently model the shared or complementary information for more effective integration. In this study, we introduce a Unified Modeling Enhanced Mult...

Background: Evaluating and Enhancing Large Language Models' Performance in Domain-specific Medicine: Explainable LLM with DocOA. Objective: This study focused on evaluating and enhancing the clinical capabilities and explainability of LLMs in specific domains, using osteoarthritis (OA) management as a case study. Methods: A domain specific ben...

Background: The morphology and internal composition, particularly the nucleus-to-cross sectional area (NP-to-CSA) ratio of the lumbar intervertebral discs (IVDs), is important information for finite element models (FEMs) of spinal loadings and biomechanical behaviors, and, yet, this has not been well investigated and reported. Methods: Anonymize...

Abstract Objective: To explore the relationship between two-year changes in muscle strength and cartilage according to knee pain in mild and moderate knee Osteoarthritis (OA). Design: 279 participants were retrospectively obtained from the Osteoarthritis Initiative. Western Ontario McMaster University (WOMAC) and Knee Injury and Osteoarthritis Out...

Osteophytes are frequently observed in elderly people and most commonly appear at the anterior edge of the cervical and lumbar vertebrae body. The anterior osteophytes keep developing and will lead to neck/back pain over time. In clinical practice, the accurate measurement of the anterior osteophyte length and the understanding of the temporal prog...

Adapting a medical image segmentation model to a new domain is important for improving its cross-domain transferability, and due to the expensive annotation process, Unsupervised Domain Adaptation (UDA) is appealing where only unlabeled images are needed for the adaptation. Existing UDA methods are mainly based on image or feature alignment with ad...

BACKGROUND With the increasing interest of Large Language Models’ (LLMs) application in the medical field, the feasibility of its potential usage as a Standardized Patient (SP) in medical assessment is rarely evaluated. Specifically, we delved into the potential of using ChatGPT, a representative LLM, in transforming medical education by serving as...

Full-length radiographs contain information from which many anatomical parameters of the pelvis, femur, and tibia may be derived, but only a few anatomical parameters are used for musculoskeletal modeling. This study aimed to develop a fully automatic algorithm to extract anatomical parameters from full-length radiograph to generate a musculoskelet...

BACKGROUND The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored. OBJECTIVE This study focused on evaluating and enhancing the clinical capabilities and explainability of LLMs in specific domains, using OA management as a case stu...

Monitoring the healing progress of diabetic foot ulcers is a challenging process. Accurate segmentation of foot ulcers can help podiatrists to quantitatively measure the size of wound regions to assist prediction of healing status. The main challenge in this field is the lack of publicly available manual delineation, which can be time consuming and...

This study develops and evaluates a novel multimodal medical image zero-shot segmentation algorithm named Text-Visual-Prompt SAM (TV-SAM) without any manual annotations. TV-SAM incorporates and integrates large language model GPT-4, Vision Language Model GLIP, and Segment Anything Model (SAM), to autonomously generate descriptive text prompts and v...

Abstract Background The breakdown of healthcare facilities is a huge challenge for hospitals. Medical images obtained by Computed Tomography (CT) provide information about the patients' physical conditions and play a critical role in diagnosis of disease. To deliver high-quality medical images on time, it is essential to minimize the occurrence fre...

Large language models (LLMs) are a class of artificial intelligence models based on deep learning, which have great performance in various tasks, especially in natural language processing (NLP). Large language models typically consist of artificial neural networks with numerous parameters, trained on large amounts of unlabeled input using self-supe...

Objective To assess the relationship between walking exercise and medial joint space narrowing (JSN) progression, symptoms, and knee extensor muscle strength (EMS) in early knee osteoarthritis (OA) patients. Methods This nested cohort study within the Osteoarthritis Initiative included participants aged 50 and above with knee OA (Kellgren-Lawrence...

We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. While most current methods focus on explaining graph nodes, edges, or features, we argue that, as the inherent functional mechanism of GNNs, message flows are more natural for performing explainability. To this end, we propose a...

Congenital heart disease (CHD) is the most common congenital malformation and imaging examination is an important means to diagnose it. Currently, deep learning-based methods have achieved remarkable results in various types of imaging examinations. However, the issues of large parameter size and low throughput limit their clinical applications. In...

Background This systematic review and meta-analysis aims to compare the effectiveness of home-based tele-rehabilitation programs with hospital-based rehabilitation programs in improving pain and function at various time points (≤6 weeks, ≤14 weeks, and ≤ 52 weeks) following the initial total knee arthroplasty. Methods This study used PRISMA and AM...

The prognostic analysis for high grade serous adenocarcinoma (HGSC) holds significant clinical importance. However, current prognostic analysis primarily relies on statistical techniques like logistic regression and chi-square analysis alongside traditional machine learning methods based on pattern recognition. These approaches face challenges in a...

Importance This study adopted multi-agent framework in large language models to enhance diagnosis in complex medical cases, particularly rare diseases, revealing limitation in current training and benchmarking of LLMs in healthcare. Objective This study aimed to develop MAC LLMs for medical diagnosis, and compare the knowledge base and diagnostic...

Radiomics is an important research direction in the field of medical image analysis. Although the number of publications is increasing year by year, it has been difficult to translate into clinical practice due to the small size of clinical data. In most cases, Radiomics data can be considered as small tabular data. Deep learning is often less effe...

Despite the large demand for dental restoration each year, the design of crown restorations is mainly performed via manual software operation, which is tedious and subjective. Moreover, the current design process lacks biomechanics optimization, leading to localized stress concentration and reduced working life. To tackle these challenges, we devel...

Objective: Precise hip joint morphometry measurement from CT images is crucial for successful preoperative arthroplasty planning and biomechanical simulations. Although deep learning approaches have been applied to clinical bone surgery planning, there is still a lack of relevant research on quantifying hip joint morphometric parameters from CT im...

The use of preoperative CT and intraoperative fluoroscopic-guided surgical robotic assistance for spinal disease treatment has gained significant attention among surgeons. However, the intraoperative robotic systems lack guidance based on three-dimensional anatomical structures, rendering them unusable when there is a mismatch between preoperative...

This study investigates the effect of changing channel ordering at the input end of EEGNet on the classification performance of deep learning algorithms, based on the entropy weight graph using phase locking value (PLV). The PLV is computed to reflect the phase synchronization relationship between different EEG channels and an adjacency matrix is c...

The soft exosuit has been proven to improve the pilot’s walking ability and reduce metabolic consumption, yet, its gait assistance strategy still suffers from the problem of insufficient personalized adaption. This paper proposes a Segmented Dynamic Movement Primitives (SDMPs) -based gait assistive strategy to address this problem. This strategy us...

Robotic devices are capable of reducing the physical burden on rehabilitation therapists and providing training programs of good repeatability, high efficiency and high precision. When designing the kinematic structure for rehabilitation robots, there has been a growing interest towards 1-degree-of-freedom (DOF) end-effector mechanisms due to their...

For the safe and smooth robot-assisted healthcare task execution, real-time motion tracking controls and compliant physical human–robot interactions are concurrently important control objectives. In this work, the uncertainty and disturbance estimator (UDE)-based robust region tracking controller for a robot manipulator is developed. The regional f...

Accurate 3D cardiac reconstruction from cine magnetic resonance imaging (cMRI) is crucial for improved cardiovascular disease diagnosis and understanding of the heart’s motion. However, current cardiac MRI-based reconstruction technology used in clinical settings is 2D with limited through-plane resolution, resulting in low-quality reconstructed ca...

Masked autoencoder (MAE) has attracted unprecedented attention and achieves remarkable performance in many vision tasks. It reconstructs random masked image patches (known as proxy task) during pretraining and learns meaningful semantic representations that can be transferred to downstream tasks. However, MAE has not been thoroughly explored in ult...

Foundation models, often pre-trained with large-scale data, have achieved paramount success in jump-starting various vision and language applications. Recent advances further enable adapting foundation models in downstream tasks efficiently using only a few training samples, e.g., in-context learning. Yet, the application of such learning paradigms...

Deep learning methods are often hampered by issues such as data imbalance and data-hungry. In medical imaging, malignant or rare diseases are frequently of minority classes in the dataset, featured by diversified distribution. Besides that, insufficient labels and unseen cases also present conundrums for training on the minority classes. To confron...

Background Large-scale medical equipment, which is extensively implemented in medical services, is of vital importance for diagnosis but vulnerable to various anomalies and failures. Most hospitals that conduct regular maintenance have been suffering from medical equipment-related incidents for years. Currently, the Internet of Medical Things (IoMT...

Background Although there are many studies on the prognostic factors of left ventricular myocardial noncompaction (LVNC), the determinants are varied and not entirely consistent. This study aimed to build predictive models using radiomics features and machine learning to predict major adverse cardiovascular events (MACEs) in patients with LVNC. Me...

Accurate 3D cardiac reconstruction from cine magnetic resonance imaging (cMRI) is crucial for improved cardiovascular disease diagnosis and understanding of the heart's motion. However, current cardiac MRI-based reconstruction technology used in clinical settings is 2D with limited through-plane resolution, resulting in low-quality reconstructed ca...

Ultrasound based estimation of fetal biometry is extensively used to diagnose prenatal abnormalities and to monitor fetal growth, for which accurate segmentation of the fetal anatomy is a crucial prerequisite. Although deep neural network-based models have achieved encouraging results on this task, inevitable distribution shifts in ultrasound image...

It is necessary to analyze the whole-body kinematics (including joint locations and joint angles) to assess risks of fatal and musculoskeletal injuries in occupational tasks. Human pose estimation has gotten more attention in recent years as a method to minimize the errors in determining joint locations. However, the joint angles are not often esti...

Karyotyping is of importance for detecting chromosomal aberrations in human disease. However, chromosomes easily appear curved in microscopic images, which prevents cytogeneticists from analyzing chromosome types. To address this issue, we propose a framework for chromosome straightening, which comprises a preliminary processing algorithm and a gen...

Infection with COVID-19 can cause severe complication in the respiratory system, which may be related to increased respiratory resistance. Computational fluid dynamics(CFD) was used in this study to calculate the airway resistance based on the airway anatomy and a common air flowrate. The correlation between airway resistance and COVID-19 prognosis...

Generalization to previously unseen images with potential domain shifts is essential for clinically applicable medical image segmentation. Disentangling domain-specific and domain-invariant features is key for Domain Generalization (DG). However, existing DG methods struggle to achieve effective disentanglement. To address this problem, we propose...

Pretraining with large-scale 3D volumes has a potential for improving the segmentation performance on a target medical image dataset where the training images and annotations are limited. Due to the high cost of acquiring pixel-level segmentation annotations on the large-scale pretraining dataset, pretraining with unannotated images is highly desir...

The Segment Anything Model (SAM) has recently emerged as a groundbreaking model in the field of image segmentation. Nevertheless, both the original SAM and its medical adaptations necessitate slice-by-slice annotations, which directly increase the annotation workload with the size of the dataset. We propose MedLSAM to address this issue, ensuring a...

Karyotyping is of importance for detecting chromosomal aberrations in human disease. However, chromosomes easily appear curved in microscopic images, which prevents cytogeneticists from analyzing chromosome types. To address this issue, we propose a framework for chromosome straightening, which comprises a preliminary processing algorithm and a gen...

PurposePelvic bone segmentation and landmark definition from computed tomography (CT) images are prerequisite steps for the preoperative planning of total hip arthroplasty. In clinical applications, the diseased pelvic anatomy usually degrades the accuracies of bone segmentation and landmark detection, leading to improper surgery planning and poten...

Foundation models, often pre-trained with large-scale data, have achieved paramount success in jump-starting various vision and language applications. Recent advances further enable adapting foundation models in downstream tasks efficiently using only a few training samples, e.g., in-context learning. Yet, the application of such learning paradigms...

Masked autoencoder (MAE) has attracted unprecedented attention and achieves remarkable performance in many vision tasks. It reconstructs random masked image patches (known as proxy task) during pretraining and learns meaningful semantic representations that can be transferred to downstream tasks. However, MAE has not been thoroughly explored in ult...

Portal hypertension is the initial and main consequence of liver cirrhosis. Currently the diagnosis relies on invasive and complex operation. This study proposed a new computational method in computational fluid dynamics (CFD) analysis to noninvasively measure the portal pressure gradient (PPG) by considering the liver region as porous media to acc...

Abdominal multi-organ segmentation in multi-sequence magnetic resonance images (MRI) is of great significance in many clinical scenarios, e.g., MRI-oriented pre-operative treatment planning. Labeling multiple organs on a single MR sequence is a time-consuming and labor-intensive task, let alone manual labeling on multiple MR sequences. Training a m...