A5108136531- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Treatments and Mutations
- Medical Imaging and Pathology Studies
- COVID-19 diagnosis using AI
- Medical Imaging Techniques and Applications
- Lung Cancer Research Studies
- Cancer Genomics and Diagnostics
- AI in cancer detection
- Global Cancer Incidence and Screening
- Advanced X-ray and CT Imaging
- Colorectal Cancer Screening and Detection
- Bioinformatics and Genomic Networks
- Computational Drug Discovery Methods
- Bladder and Urothelial Cancer Treatments
- Genetic factors in colorectal cancer
- Nutrition and Health in Aging
- Fungal Infections and Studies
- Advanced Neural Network Applications
- Cancer Immunotherapy and Biomarkers
- Artificial Intelligence in Healthcare
- PI3K/AKT/mTOR signaling in cancer
- Mast cells and histamine
- Cancer Cells and Metastasis
- Tracheal and airway disorders
Vanderbilt University Medical Center
2012-2025
Vanderbilt University
2016-2023
Pulmonary and Allergy Associates
2021
Vanderbilt-Ingram Cancer Center
2020
Nashville VA Medical Center
2019
VA Tennessee Valley Healthcare System
2018
The management of indeterminate pulmonary nodules (IPNs) remains challenging, resulting in invasive procedures and delays diagnosis treatment. Strategies to decrease the rate unnecessary optimize surveillance regimens are needed.
“Just Accepted” papers have undergone full peer review and been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, proof before it is published its final version. Please note that during production of the copyedited article, errors may be discovered which could affect content. Purpose To evaluate performance eight lung cancer prediction models on patient cohorts with screening-detected, incidentally-detected,...
Purpose: We propose a systematic methodology to quantify incidentally identified pulmonary nodules based on observed radiological traits (semantics) quantified point scale and machine-learning method using these data predict cancer status.Experimental Design: investigated 172 patients who had low-dose CT images, with 102 70 grouped into training validation cohorts, respectively. On the 24 were systematically scored linear classifier was built relate malignant status. The model formed both...
Rationale: Patients with indeterminate pulmonary nodules (IPNs) at risk of cancer undergo high rates invasive, costly, and morbid procedures. Objectives: To train externally validate a prediction model that combined clinical, blood, imaging biomarkers to improve the noninvasive management IPNs. Methods: In this prospectively collected, retrospective blinded evaluation study, probability was calculated for 456 patient using Mayo Clinic model, patients were categorized into low-,...
Abstract Genomic profiling of bronchoalveolar lavage (BAL) samples may be useful for tumor and diagnosis in the clinic. Here, we compared tumor-derived mutations detected BAL from subjects with non–small cell lung cancer (NSCLC) to those matched plasma samples. Cancer Personalized Profiling by Deep Sequencing (CAPP-Seq) was used genotype DNA purified BAL, plasma, patients NSCLC. The characteristics cell-free (cfDNA) isolated fluid were first characterized optimize technical approach. Somatic...
Abstract Background: The heterogeneous biology of cancer subtypes, especially in lung cancer, poses significant challenges for biomarker development. Standard model building techniques often fall short accurately incorporating various histologic subtypes because their diverse biological characteristics. This study explores a nested to address this issue, aiming improve early detection. Methods: included 337 patients from two clinical sites. Blood biomarkers were analyzed and statistical...
Abstract A deep learning model (LCP CNN) for the stratification of indeterminate pulmonary nodules (IPNs) demonstrated better discrimination than commonly used clinical prediction models. However, LCP CNN score is based on a single timepoint that ignores longitudinal information when prior imaging studies are available. Clinically, IPNs often followed over time and temporal trends in nodule size or morphology inform management. In this study we investigated whether change scores was...
Introduction Implementation of low-dose chest computed tomography (CT) lung cancer screening and the ever-increasing use cross-sectional imaging are resulting in identification many screen- incidentally detected indeterminate pulmonary nodules. While management nodules with low or high pre-test probability malignancy is relatively straightforward, those intermediate commonly require advanced biopsy. Noninvasive risk stratification tools highly desirable. Methods We previously developed...
Early detection of lung cancer is essential in reducing mortality. Recent studies have demonstrated the clinical utility low-dose computed tomography (CT) to detect among individuals selected based on very limited information. However, this strategy yields high false positive rates, which can lead unnecessary and potentially harmful procedures. To address such challenges, we established a pipeline that co-learns from detailed demographics 3D CT images. Toward end, leveraged data Consortium...
Background 18 F-fluorodeoxyglucose (FDG) PET/CT is recommended for evaluation of intermediate-risk indeterminate pulmonary nodules (IPNs). While highly sensitive, the specificity FDG remains suboptimal differentiating malignant from benign nodules, particularly in areas where fungal lung diseases are prevalent. Thus, a cancer-specific imaging probe greatly needed. In this study, we tested hypothesis that PET radiotracer (S)-4-(3-[ F]-fluoropropyl)-L-glutamic acid (FSPG) improves diagnostic...
Granulomas caused by infectious lung diseases present as indeterminate pulmonary nodules (IPNs) on radiography. Newly available serum enzyme immunoassay (EIA) for histoplasmosis has not been studied the evaluation of IPNs. We investigated biomarkers antibodies an indication benign disease in IPNs from a highly endemic region.A total 152 samples patients presenting with ≤30 mm maximum diameter were analyzed immunodiffusion and EIA IgG IgM tests. Serology FDG-PET/CT scan diagnostic test...
Lung cancer is the deadliest in United States and worldwide, lung adenocarcinoma (LUAD) most prevalent histologic subtype States. LUAD exhibits a wide range of aggressiveness risk recurrence, but biological underpinnings this behavior are poorly understood. Past studies have focused on characteristics tumor itself, ability immune response to contain growth represents an alternative or complementary hypothesis. Emerging technologies enable us investigate spatial distribution specific cell...
Certain body composition phenotypes, like sarcopenia, are well established as predictive markers for post-surgery complications and overall survival of lung cancer patients. However, their association with incidental risk in the screening population is still unclear. We study feasibility analysis using chest low dose computed tomography (LDCT). A two-stage fully automatic pipeline developed to assess cross-sectional area components including subcutaneous adipose tissue (SAT), muscle,...
There is a need for biomarkers that improve accuracy compared with current demographic risk indices to detect individuals at the highest lung cancer risk. Improved determination will enable more effective screening and better stratification of nodules into high or low-risk category. We previously reported discovery biomarker characterized by increased prevalence TP53 somatic mutations in airway epithelial cells (AEC). Here we present results from validation study an independent retrospective...
Lung adenocarcinoma (LUAD) is the predominant type of lung cancer in U.S. and exhibits a broad variety behaviors ranging from indolent to aggressive. Identification biological determinants LUAD behavior at early stages can improve existing diagnostic treatment strategies. Extracellular matrix (ECM) remodeling cancer-associated fibroblasts play crucial role regulation aggressiveness there growing need investigate their determination stages. We analyzed tissue samples isolated patients with...
Annual low dose computed tomography (CT) lung screening is currently advised for individuals at high risk of cancer (e.g., heavy smokers between 55 and 80 years old). The recommended practice significantly reduces all-cause mortality, but the vast majority results are negative cancer. If patients very could be identified based on individualized, image-based biomarkers, health care resources more efficiently allocated to higher reduce overall exposure ionizing radiation. In this work, we...
Blood-based next-generation sequencing assays of circulating tumor DNA (ctDNA) have the ability to detect tumor-associated mutations in patients with SCLC. We sought characterize relationship between ctDNA mean variant allele frequency (VAF) and radiographic total-body volume (TV) SCLC.We identified matched blood draws computed tomography (CT) or positron emission (PET) scans within a prospective SCLC banking cohort. sequenced plasma using our previously developed 14-gene SCLC-specific...
Lung adenocarcinoma (ADC), the most common lung cancer type, is recognized increasingly as a disease spectrum. To guide individualized patient care, non-invasive means of distinguishing indolent from aggressive ADC subtypes needed urgently. Computer-Aided Nodule Assessment and Risk Yield (CANARY) novel computed tomography (CT) tool that characterizes early ADCs by detecting nine distinct CT voxel classes, representing spectrum lepidic to invasive growth, within an ADC. CANARY...
Clinical data elements (CDEs) (e.g., age, smoking history), blood markers and chest computed tomography (CT) structural features have been regarded as effective means for assessing lung cancer risk. These independent variables can provide complementary information we hypothesize that combining them will improve the prediction accuracy. In practice, not all patients these available. this paper, propose a new network design, termed multi-path multi-modal missing (M3Net), to integrate (i.e.,...