A5015838477- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Advanced Radiotherapy Techniques
- Medical Image Segmentation Techniques
- Transplantation: Methods and Outcomes
- Cardiovascular Disease and Adiposity
- Extracellular vesicles in disease
- Cancer-related molecular mechanisms research
- Advanced Neural Network Applications
- Liver Disease Diagnosis and Treatment
- AI in cancer detection
- MicroRNA in disease regulation
- Lung Cancer Diagnosis and Treatment
- Anatomy and Medical Technology
- COVID-19 diagnosis using AI
- Dental Radiography and Imaging
- Infrared Thermography in Medicine
Radiology Associates
2019-2022
University of Pennsylvania
2016-2019
California University of Pennsylvania
2018
Automatic segmentation of 3D objects in computed tomography (CT) is challenging. Current methods, based mainly on artificial intelligence (AI) and end-to-end deep learning (DL) networks, are weak garnering high-level anatomic information, which leads to compromised efficiency robustness. This can be overcome by incorporating natural (NI) into AI methods via computational models human knowledge.
Overweight and underweight conditions are considered relative contraindications to lung transplantation due their association with excess mortality. Yet, recent work suggests that body mass index (BMI) does not accurately reflect adipose tissue in adults advanced diseases. Alternative more accurate measures of adiposity needed. Chest fat estimation by routine computed tomography (CT) imaging may therefore be important for identifying high-risk transplant candidates. In this paper, an...
Algorithms for image segmentation (including object recognition and delineation) are influenced by the quality of appearance in overall quality. However, issue how to perform evaluation as a function these factors has not been addressed literature. In this paper, we present solution problem. We devised set key criteria that influence (global regional): posture deviations, noise, beam hardening artifacts (streak artifacts), shape distortion, presence pathology, intensity deviation, contrast....
Contouring of the organs at risk is a vital part routine radiation therapy planning. For head and neck (H N) region, this more challenging due to complexity anatomy, presence streak artifacts, variations object appearance. In paper, we describe latest advances in our Automatic Anatomy Recognition (AAR) approach, which aims automatically contour multiple objects region on planning CT images. Our method has three major steps: model building, recognition, delineation. First, better-quality...
Segmentation of organs at risk (OARs) is a key step during the radiation therapy (RT) treatment planning process. Automatic anatomy recognition (AAR) recently developed body-wide multiple object segmentation approach, where designed as two dichotomous steps: (or localization) and delineation. Recognition high-level process determining whereabouts an object, delineation meticulous low-level precisely indicating space occupied by object. This study focuses on recognition. The purpose this...
Quantification of fat throughout the body is vital for study many diseases. In thorax, it important lung transplant candidates since obesity and being underweight are contraindications to transplantation given their associations with increased mortality. Common approaches thoracic segmentation all interactive in nature, requiring significant manual effort draw interfaces between muscle low efficiency questionable repeatability. The goal this paper explore a practical way subcutaneous adipose...
Recently, deep learning networks have achieved considerable success in segmenting organs medical images. Several methods used volumetric information with to achieve segmentation accuracy. However, these suffer from interference, risk of overfitting, and low accuracy as a result artifacts, the case very challenging objects like brachial plexuses. In this paper, address issues, we synergize strengths high-level human knowledge (i.e., natural intelligence (NI)) artificial (AI)) for recognition...
In this study, patients who underwent lung transplantation are categorized into two groups of successful (positive) or failed (negative) transplantations according to primary graft dysfunction (PGD), i.e., acute injury within 72 hours transplantation. Obesity being underweight is associated with an increased risk PGD. Adipose quantification and characterization via computed tomography (CT) imaging evolving topic interest. However, very little research PGD prediction using adipose quantity...
Image segmentation is the process of delineating regions occupied by objects interest in a given image. This operation fundamentally required first step numerous applications medical imagery. In imaging field, this activity has rich literature that spans over 45 years. spite advances, including deep learning (DL) networks (DLNs) recent years, problem defied robust, fail-safe, and satisfactory solution, especially for are manifest with low contrast, spatially sparse, have variable shape among...