A5051027046- Radiomics and Machine Learning in Medical Imaging
- Surgical Simulation and Training
- Medical Imaging Techniques and Applications
- Advanced Radiotherapy Techniques
- Advanced X-ray and CT Imaging
- Augmented Reality Applications
- Anatomy and Medical Technology
- Cell Image Analysis Techniques
- Medical Imaging and Analysis
- AI in cancer detection
- Robotics and Sensor-Based Localization
- Soft Robotics and Applications
- COVID-19 diagnosis using AI
- Medical Image Segmentation Techniques
- Single-cell and spatial transcriptomics
- Tuberculosis Research and Epidemiology
- Advanced Neural Network Applications
- Advanced Biosensing Techniques and Applications
- Lymphoma Diagnosis and Treatment
- Industrial Vision Systems and Defect Detection
- Bone fractures and treatments
- Lung Cancer Diagnosis and Treatment
- Advanced Fluorescence Microscopy Techniques
- Context-Aware Activity Recognition Systems
- Scientific Computing and Data Management
National Institutes of Health
2013-2025
National Institute of Allergy and Infectious Diseases
2019-2025
Springhouse
2024
Children's National
2012-2022
Government of the United States of America
2022
Murdoch Children's Research Institute
2018
Monash University
2018
United States National Library of Medicine
2013-2018
KWJ Engineering (United States)
2015
Virginia Tech
2013
Abstract Modern scientific endeavors increasingly require team collaborations to construct and interpret complex computational workflows. This work describes an image-analysis environment that supports the use of tools facilitate reproducible research support scientists with varying levels software development skills. The Jupyter notebook web application is basis enables flexible, well-documented, workflows via literate programming. Image-analysis made accessible programming experience...
Abstract Background With increasing research on system integration for image‐guided therapy (IGT), there has been a strong demand standardized communication among devices and software to share data such as target positions, images device status. Method We propose new, open, simple extensible network protocol IGT, named OpenIGTLink, transfer transform, image status messages. conducted performance tests use‐case evaluations in five clinical engineering scenarios. Results The was able position...
Many types of medical and scientific experiments acquire raw data in the form images. Various forms image processing analysis are used to transform into quantitative measures that basis subsequent statistical analysis. In this article we describe SimpleITK R package. is a simplified interface insight segmentation registration toolkit (ITK). ITK an open source C++ has been actively developed over past 18 years widely by community. provides packages for many interpreter environments, including...
The diverse composition of mammalian tissues poses challenges for understanding the cell-cell interactions required organ homeostasis and how spatial relationships are perturbed during disease. Existing methods such as single-cell genomics, lacking a context, traditional immunofluorescence, capturing only two to six molecular features, cannot resolve these issues. Imaging technologies have been developed address problems, but each possesses limitations that constrain widespread use. Here we...
The iterative bleaching extends multiplexity (IBEX) Knowledge-Base is a central portal for researchers adopting IBEX and related 2D 3D immunofluorescence imaging methods. design of the modeled after efforts in open-source software community includes three facets: development platform (GitHub), static website, service data archiving. facilitates practice open science throughout research life cycle by providing validation recommended non-recommended reagents, e.g., primary secondary...
When choosing an electromagnetic tracking system (EMTS) for image‐guided procedures several factors must be taken into consideration. Among others these include the system's refresh rate, number of sensors that need to tracked, size navigated region, interaction with environment, whether can embedded tools and provide desired transformation data, accuracy robustness. To date, only have been studied extensively are susceptibility EMTSs distortions caused by ferromagnetic materials. In this...
Blockade of the PD-1 coinhibitory pathway compromises immune control Mycobacterium tuberculosis infection in rhesus macaques.
We present a gradient-based method for rigid registration of patient preoperative computed tomography (CT) to its intraoperative situation with few fluoroscopic X-ray images obtained tracked C-arm. The is noninvasive, anatomy-based, requires simple user interaction, and includes validation. It generic easily customizable variety routine clinical uses in orthopaedic surgery. Gradient-based consists three steps: 1) initial pose estimation; 2) coarse geometry-based on bone contours, and; 3)...
This article describes FRACAS, a computer-integrated orthopedic system for assisting surgeons in performing closed medullary nailing of long bone fractures. FRACAS's goal is to reduce the surgeon's cumulative exposure radiation and surgical complications associated with alignment positioning errors fragments, nail insertion, distal screw locking. It replaces uncorrelated, static fluoroscopic images virtual reality display three-dimensional models created from preoperative computed tomography...
This article addresses the two key challenges in computer-assisted percutaneous tumor ablation: planning multiple overlapping ablations for large tumors while avoiding critical structures, and executing prescribed plan. Toward semiautomatic treatment image-guided surgical interventions, we develop a systematic approach to needle-based ablation placement task, ranging from preoperative algorithms an intraoperative execution platform. The system incorporates clinical constraints on...
Purpose Cardiac image segmentation is a critical process for generating personalized models of the heart and quantifying cardiac performance parameters. Fully automatic left ventricle (LV), right (RV), myocardium from cine MR images challenging due to variability normal abnormal anatomy, as well imaging protocols. This study proposes multi‐task learning (MTL)‐based regularization convolutional neural network (CNN) obtain accurate segmenation structures images. Methods We train CNN perform...
This paper presents an overview of the image-guided surgery toolkit (IGSTK). IGSTK is open source C++ software library that provides basic components needed to develop applications. It intended for fast prototyping and development The was developed through a collaboration between academic industry partners. Because designed safety-critical applications, team has adopted lightweight processes emphasizes safety robustness while, at same time, supporting geographically separated developers. A...
Estimating the location of a tracked tool's tip relative to its Dynamic Reference Frame (DRF) and localizing specific point in tracking system's coordinate frame are fundamental tasks image-guided procedures. The most common approach estimating these values is by pivoting tool around fixed point. transformations from DRF input. output translation tracker's While input unique, there multiple mathematical formulations for performing this estimation task. question is, equivalent terms precision...
This article describes FRACAS, a computer-integrated orthopedic system for assisting surgeons in performing closed medullary nailing of long bone fractures. FRACAS's goal is to reduce the surgeon's cumulative exposure radiation and surgical complications associated with alignment positioning errors fragments, nail insertion, distal screw locking. It replaces uncorrelated, static fluoroscopic images virtual reality display three-dimensional models created from preoperative computed tomography...
Radiofrequency ablation of primary and metastatic liver tumors is becoming a potential alternative to surgical resection. We propose novel system that uses real‐time electromagnetic position sensing the needle tip help with precision guidance into tumor. The purpose this study was evaluate technology in phantom animal models. Using an navigation device, instrumented needles were advanced radioopaque tumor targets respiratory phantom. featured moving target simulated cranio‐caudal motion due...
This paper presents a novel image-guided robot-based system to assist orthopedic surgeons in performing distal locking of long bone intramedullary nails. The consists bone-mounted miniature robot fitted with drill guide that provides rigid mechanical guidance for hand-held drilling the screws' pilot holes. is automatically positioned so and nail axes coincide, using single fluoroscopic X-ray image. Since rigidly attached or bone, no leg immobilization real-time tracking required. We describe...
We present three image-guided navigation systems developed for needle-based interventional radiology procedures, using the open source surgery toolkit (IGSTK). The clinical procedures we address are vertebroplasty, RF ablation of large lung tumors, and biopsy. In our system replaces use fluoroscopy, reducing radiation exposure to patient physician. evaluate this a custom phantom compare results obtained by medical student, an fellow, attending provides automated plan that minimizes damage...
The introduction of software technology in a life-dependent environment requires the development team to execute process that ensures high level reliability and correctness. Despite their popularity, agile methods are generally assumed be inappropriate as family these environments due lack emphasis on documentation, traceability, other formal techniques. Agile methods, notably Scrum, favor empirical control, or small constant adjustments tight feedback loop. This paper challenges assumption...
Classification of drug-resistant tuberculosis (DR-TB) and drug-sensitive (DS-TB) from chest radiographs remains an open problem. Our previous cross validation performance on publicly available X-ray (CXR) data combined with image augmentation, the addition synthetically generated images achieved a 85% AUC deep convolutional neural network (CNN). However, when we evaluated CNN model trained to classify DR-TB DS-TB unseen data, significant degradation was observed (65% AUC). Hence, in this...
According to the 2022 World Health Organization's Global Tuberculosis (TB) report, an estimated 10.6 million people fell ill with TB, and 1.6 died from disease in 2021. In addition, 2021 saw a reversal of decades-long trend declining TB infections deaths, increase 4.5% number who compared 2020, yearly 450,000 cases drug resistant TB. Estimating severity pulmonary using frontal chest X-rays (CXR) can enable better resource allocation constrained settings monitoring treatment response,...