A5066017625- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Medical Imaging Techniques and Applications
- Medical Image Segmentation Techniques
- Advanced Radiotherapy Techniques
- Atomic and Subatomic Physics Research
- Respiratory Support and Mechanisms
- Retinal Imaging and Analysis
- Inhalation and Respiratory Drug Delivery
- COVID-19 diagnosis using AI
- Pleural and Pulmonary Diseases
- AI in cancer detection
- Glaucoma and retinal disorders
- Ultrasound and Hyperthermia Applications
- Advanced X-ray and CT Imaging
- Radiation Dose and Imaging
- Retinal Diseases and Treatments
- Thermal Regulation in Medicine
- Effects of Radiation Exposure
- Digital Imaging for Blood Diseases
- Tracheal and airway disorders
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Asthma and respiratory diseases
- Image Retrieval and Classification Techniques
University of Iowa
2016-2025
University of Alabama at Birmingham
2024
Engineering Arts (United States)
2011-2023
University of Pittsburgh
2022
Praxis
2020
Case Western Reserve University
2016
Cornell University
2016
University of Wisconsin–Madison
2015
UW Health University Hospital
2015
University of Virginia
2012
Segmentation of pulmonary X-ray computed tomography (CT) images is a precursor to most image analysis applications. This paper presents fully automatic method for identifying the lungs in three-dimensional (3-D) CT images. The has three main steps. First, lung region extracted from by gray-level thresholding. Then, left and right are separated anterior posterior junctions dynamic programming. Finally, sequence morphological operations used smooth irregular boundary along mediastinum order...
EMPIRE10 (Evaluation of Methods for Pulmonary Image REgistration 2010) is a public platform fair and meaningful comparison registration algorithms which are applied to database intrapatient thoracic CT image pairs. Evaluation nonrigid techniques nontrivial task. This compounded by the fact that researchers typically test only on their own data, varies widely. For this reason, reliable assessment different has been virtually impossible in past. In work we present results launch phase...
This paper describes a framework for establishing reference airway tree segmentation, which was used to quantitatively evaluate fifteen different extraction algorithms in standardized manner. Because of the sheer difficulty involved manually constructing complete standard from scratch, we propose construct using results all that are be evaluated. We start by subdividing each segmented into its individual branch segments. Each segment is then visually scored trained observers determine...
Chronic obstructive pulmonary disease (COPD) remains a major cause of morbidity and mortality. Present-day diagnostic criteria are largely based solely on spirometric criteria. Accumulating evidence has identified substantial number individuals without COPD who suffer from respiratory symptoms and/or increased There is clear need for an expanded definition that linked to physiologic, structural (computed tomography [CT]) clinical disease. Using data the Genetic Epidemiology study (COPDGene
Quantifying functional small airways disease (fSAD) requires additional expiratory computed tomography (CT) scan, limiting clinical applicability. Artificial intelligence (AI) could enable fSAD quantification from chest CT scan at total lung capacity (TLC) alone (fSADTLC). To evaluate an AI model for estimating fSADTLC, compare it with dual-volume parametric response mapping (fSADPRM), and assess its associations repeatability in chronic obstructive pulmonary (COPD). We analyzed 2513...
The interpretation of experimental results from functional medical imaging is complicated by intersubject and interspecies differences in airway geometry. application computational models understanding the significance these requires methods for generation subject-specific geometric bronchial tree. In current study, curvilinear centerline diameter have been fitted to human ovine trees using detailed data segmented multidetector row X-ray-computed tomography scans. extended model entire...
The lungs exchange air with the external environment via pulmonary airways. Computed tomography (CT) scanning can be used to obtain detailed images of anatomy, including These have been measure airway geometry, study reactivity, and guide surgical interventions. Prior these applications, segmentation identify lumen in CT images. Airway tree performed manually by an image analyst, but complexity makes manual tedious extremely time-consuming. We describe a fully automatic technique for...
High-resolution X-ray computed tomography (CT) imaging is routinely used for clinical pulmonary applications. Since lung function varies regionally and because disease usually not uniformly distributed in the lungs, it useful to study lungs on a lobe-by-lobe basis. Thus, important segment only but lobar fissures as well. In this paper, we demonstrate use of an anatomic atlas, encoded with priori information anatomy, automatically oblique fissures. Sixteen volumetric CT scans from 16 subjects...
A novel splat feature classification method is presented with application to retinal hemorrhage detection in fundus images. Reliable of hemorrhages important the development automated screening systems which can be translated into practice. Under our supervised approach, color images are partitioned nonoverlapping segments covering entire image. Each segment, i.e., splat, contains pixels similar and spatial location. set features extracted from each describe its characteristics relative...
Pulmonary fissure detection in computed tomography (CT) is a critical component for automatic lobar segmentation. The majority of methods use feature descriptors that are hand-crafted, low-level, and have local spatial extent. design such detectors typically targeted toward normal anatomy, yielding low sensitivity to weak, abnormal fissures common clinical data sets. Furthermore, features commonly suffer from specificity, as the complex textures lung can be indistinguishable when global...
Background Approximately half of adults with chronic obstructive pulmonary disease (COPD) remain undiagnosed. Chest CT scans are frequently acquired in clinical practice and present an opportunity to detect COPD. Purpose To assess the performance radiomics features COPD diagnosis using standard-dose low-dose models. Materials Methods This secondary analysis included participants enrolled Genetic Epidemiology COPD, or COPDGene, study at baseline (visit 1) 10 years after 3). was defined by a...
Most emphysema is believed to arise from small airways disease, but recent data suggest begets more and that its progression may be due the mechanical stress experienced by normal lung regions adjacent existing emphysema. To determine whether new arises this penumbra of mechanically affected (MAL) or disease. We co-registered inspiratory chest computed tomography (CT) scans acquired at enrollment 5 years later in 4,972 participants enrolled a multicenter cohort. Using adaptive Gaussian...
Individuals at risk for chronic obstructive pulmonary disease (COPD) but without spirometric airflow obstruction can have respiratory symptoms and structural lung on chest computed tomography. Current guidelines recommend COPD diagnostic schemas that do not incorporate imaging abnormalities. To determine whether a multidimensional schema includes tomographic abnormalities identifies additional individuals with disease. This cohort study included 2 longitudinal cohorts: the Genetic...
Airway geometry measurements can provide information regarding pulmonary physiology and pathophysiology. There has been considerable interest in measuring intrathoracic airways two-dimensional (2-D) slices from volumetric X-ray computed tomography (CT). Such be used to evaluate track the progression of diseases affecting airways. A popular airway measurement method uses "half-max" criteria, which gray level at wall is estimated halfway between minimum maximum levels along a ray crossing...
Abstract Purpose To develop and test a computer‐aided diagnosis (CAD) system to improve the performance of radiologists in classifying lesions on breast MRI (BMRI). Materials Methods A CAD was developed that uses semiautomated segmentation method. After segmentation, 42 features based lesion shape, texture, enhancement kinetics were computed, 13 best selected used as inputs backpropagation neural network (BNN). The BNN trained tested using leave‐one‐out method 80 BMRI (37 benign, 43...
The human lungs are divided into five distinct anatomic compartments called the <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">lobes</i> , which separated by pulmonary xmlns:xlink="http://www.w3.org/1999/xlink">fissures</i> . accurate identification of fissures is increasing importance in early detection pathologies, and regional functional analysis lungs. We have developed an automatic method for segmentation fissures, based on information...
This paper proposes an algorithm to measure the width of retinal vessels in fundus photographs using graph-based segment both vessel edges simultaneously. First, simultaneous two-boundary segmentation problem is modeled as a two-slice, 3-D surface problem, which further converted into computing minimum closed set node-weighted graph. An initial generated from probability image. We use REVIEW database evaluate diameter measurement performance. The robust and estimates with subpixel accuracy....
Computer tomography (CT) imaging techniques permit the noninvasive measurement of regional lung function. Regional specific volume change (sVol), determined from in density over a tidal breath, should correlate with ventilation and expansion measured other techniques. sVol was validated against xenon (Xe)-CT-specific (sV) four anesthetized, intubated, mechanically ventilated sheep. Xe-CT used expiratory gated axial scanning during washin washout 55% Xe. changes tissue (H, houndsfield units)...
Purpose: Radiation therapy (RT) for lung cancer is commonly limited to subtherapeutic doses due unintended toxicity normal tissue. Reducing the frequency of occurrence and magnitude function loss may benefit from treatment plans that incorporate regional radiation dose information. In this article, authors propose a method quantitatively measures changes in tissue following course by using 4DCT image registration techniques. Methods: data sets before after RT two subjects are used study....