A5050587380- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Prostate Cancer Treatment and Research
- Total Knee Arthroplasty Outcomes
- Parkinson's Disease Mechanisms and Treatments
- Neurological disorders and treatments
- Radiopharmaceutical Chemistry and Applications
- Osteoarthritis Treatment and Mechanisms
- COVID-19 diagnosis using AI
- Lung Cancer Diagnosis and Treatment
- Anomaly Detection Techniques and Applications
- Voice and Speech Disorders
- Shoulder Injury and Treatment
- AI in cancer detection
- Cancer, Lipids, and Metabolism
- Orthopedic Infections and Treatments
- Advanced MRI Techniques and Applications
- Network Security and Intrusion Detection
- Artificial Immune Systems Applications
- Adversarial Robustness in Machine Learning
- Orthopaedic implants and arthroplasty
- Sports injuries and prevention
- Imbalanced Data Classification Techniques
- Musculoskeletal pain and rehabilitation
Johns Hopkins University
2018-2024
Nova Southeastern University
2024
Courant Institute of Mathematical Sciences
2020-2023
New York University
2020-2023
Johns Hopkins Medicine
2021-2022
University of Baltimore
2018
Background The methods for assessing knee osteoarthritis (OA) do not provide enough comprehensive information to make robust and accurate outcome predictions. Purpose To develop a deep learning (DL) prediction model risk of OA progression by using radiographs in patients who underwent total replacement (TKR) matched control did undergo TKR. Materials Methods In this retrospective analysis that used data from the Initiative, DL on was developed predict both likelihood patient undergoing TKR...
Automatic detection and characterization of cancer are important clinical needs to optimize early treatment. We developed a deep, semisupervised transfer learning approach for fully automated, whole-body tumor segmentation prognosis on PET/CT. <b>Methods:</b> This retrospective study consisted 611 <sup>18</sup>F-FDG PET/CT scans patients with lung cancer, melanoma, lymphoma, head neck breast 408 prostate-specific membrane antigen (PSMA) prostate cancer. The had nnU-net backbone learned the...
The objective of this study was to develop a PET tumor-segmentation framework that addresses the challenges limited spatial resolution, high image noise, and lack clinical training data with ground-truth tumor boundaries in imaging. We propose three-module PET-segmentation context segmenting primary tumors 3D FDG-PET images patients lung cancer on per-slice basis. first module generates containing highly realistic known using new stochastic physics-based approach, addressing data. second...
Diagnosis of Parkinson's disease (PD) is informed by the presence progressive motor and non-motor symptoms imaging dopamine transporter with [
Current methods for assessing knee osteoarthritis (OA) do not provide comprehensive information to make robust and accurate outcome predictions. Deep learning (DL) risk assessment models were developed predict the progression of OA total replacement (TKR) over a 108-month follow-up period using baseline MRI. Participants our retrospective study consisted 353 case-control pairs subjects from Osteoarthritis Initiative with without TKR matched according age, sex, ethnicity, body mass index. A...
Accurate classification of sites interest on prostate-specific membrane antigen (PSMA) positron emission tomography (PET) images is an important diagnostic requirement for the differentiation prostate cancer (PCa) from foci physiologic uptake. We developed a deep learning and radiomics framework to perform lesion-level patient-level PSMA PET patients with PCa. This was IRB-approved, HIPAA-compliant, retrospective study. Lesions [18F]DCFPyL PET/CT scans were assigned reporting data system...
There are currently no established disease modifying therapies for PD, and prediction of outcome in PD to power clinical studies is a very important area research. Assessment informed by imaging the dopamine system with transporter (DAT) single-photon emission computed tomography (SPECT) presence key symptoms. Recently, deep-learning based methods have shown promise medical image analysis tasks detection. The purpose this study was develop approach predict patients using longitudinal data...
While machine learning (ML) methods may significantly improve image quality for SPECT imaging the diagnosis and monitoring of Parkinson's disease (PD), they require a large amount data training. It is often difficult to collect population patient support ML research, ground truth lesion also unknown. This paper leverages generative adversarial network (GAN) generate digital brain phantoms training ML-based PD algorithms. A total 594 PET 3D models from 155 patients (113 male 42 female) were...
Coronavirus disease 2019 (COVID-19), a highly contagious respiratory disease, has rapidly become global pandemic. Chest X-ray imaging could serve an important role in early diagnosis of the disease. Deep learning methods have recently shown promise detection tasks. The aim this study was to develop deep learning-based approach for COVID-19 chest images. Data were extracted from opensource database developed by Cohen JP. data consisted images patients with COVID-19, other pneumonias or no...
Polletta, J, Leung, K, Diaz, D, Branum, N, and Mokha, M. Influence of interlimb lean muscle mass asymmetry on countermovement jump neuromuscular performance qualities among American football players. J Strength Cond Res XX(X): 000-000, 2024-Body composition is a determinant athletic performance. The purpose this study was to determine the influence lower limb (LMM) (CMJ) kinetic during both eccentric concentric CMJ phases. Seventy-four players (age, 23.0 ± 0.9 years; height, 1.86 0.07 m;...
Automatic characterization of malignant disease is an important clinical need to facilitate early detection and treatment cancer. A deep semi-supervised transfer learning approach was developed for automated whole-body tumor segmentation prognosis on positron emission tomography (PET)/computed (CT) scans using limited annotations. This study analyzed five datasets consisting 408 prostate-specific membrane antigen (PSMA) PET/CT prostate cancer patients 611 18F-fluorodeoxyglucose (18F-FDG)...