A5086309547- Thermography and Photoacoustic Techniques
- Radiomics and Machine Learning in Medical Imaging
- Remote-Sensing Image Classification
- AI in cancer detection
- Infrared Thermography in Medicine
- Spectroscopy and Chemometric Analyses
- Infrared Target Detection Methodologies
- Photoacoustic and Ultrasonic Imaging
- Ultrasonics and Acoustic Wave Propagation
- Calibration and Measurement Techniques
- Advanced Image Fusion Techniques
- Thermoregulation and physiological responses
- Prostate Cancer Treatment and Research
- Neural Networks and Applications
- Prostate Cancer Diagnosis and Treatment
- Spectroscopy Techniques in Biomedical and Chemical Research
- Geochemistry and Geologic Mapping
- Lung Cancer Diagnosis and Treatment
- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Gene expression and cancer classification
- Non-Invasive Vital Sign Monitoring
- Advanced X-ray and CT Imaging
- Image Enhancement Techniques
- Human Pose and Action Recognition
University of Maryland, College Park
2021-2025
SUNY Upstate Medical University
2025
University of Maryland, Baltimore
2024
Université Laval
2016-2022
University of Pennsylvania
2020
California University of Pennsylvania
2019
Vision Technology (United States)
2008
The coronavirus pandemic is spreading around the world. Medical imaging modalities such as radiography play an important role in fight against COVID-19. Deep learning (DL) techniques have been able to improve medical tools and help radiologists make clinical decisions for diagnosis, monitoring prognosis of different diseases. Computer-Aided Diagnostic (CAD) systems can work efficiency by precisely delineating infections chest X-ray (CXR) images, thus facilitating subsequent quantification....
8583 Background: Tumor microenvironment (TME) plays a critical role in tumor progression and response to treatment, especially improving the immune checkpoint inhibitors (ICIs) non-small cell lung cancer (NSCLC). However, current methods are costly not feasible for routine clinical use characterizing TME. Addressing this, we recently developed Histo-TME, an AI-powered tool that accurately characterizes TME subtypes ICI responses from hematoxylin-eosin (H&E) scanned images. This study...
Active and passive thermography are two efficient techniques extensively used to measure heterogeneous thermal patterns leading subsurface defects for diagnostic evaluations. This study conducts a comparative analysis on low-rank matrix approximation methods in with applications of semi-, convex-, sparse- non-negative factorization (NMF) detecting patterns. These inherit the advantages principal component (PCT) sparse PCT, whereas tackle negative bases PCT constraints, exhibit clustering...
Recent progress in Thermal and infrared Non-Destructive Testing (IRNDT) different fields have provided interesting defect detection solutions. Principal Component Analysis (PCA) based K-means clustering been successfully introduced used many applications. However, PCA suffers from being relatively more sensitive to the noise due having a linear transformation. On other hand, Sparse (SPCA) has superior performance relation because of l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML"...
The presented approach addresses a review of the overheating that occurs during radiological examinations, such as magnetic resonance imaging, and series thermal experiments to determine thermally suitable fabric material should be used for gowns. Moreover, an automatic system detecting tracking fluctuation is presented. It applies hue-saturated-value-based kernelled k-means clustering, which initializes controls points lie on region-of-interest (ROI) boundary. Afterward, particle filter...
Thermal and infrared imagery creates considerable developments in Non-destructive Testing (NDT) area. An analysis for thermal NDT inspection is addressed applying a new technique computation of eigen-decomposition (factor analysis) similar to Principal Component Thermography(PCT). It referred as Candid Covariance-Free Incremental Thermography (CCIPCT). The proposed approach uses computational short-cut estimate covariance matrix Singular Value Decomposition(SVD) obtain faster PCT results,...
The proposed approach addresses the problem of retrieving emissivity hyperspectral data in spectroscopic imageries from indoor experiments. This methodology was tested on experimental that have been recorded with images working visible/near infrared and long-wave bands. technique provides a framework for computing down-welling spectral radiance applying non-negative matrix factorization (NMF) analysis. It necessary means non-uniform correction active thermographical obtained results indicate...
Thermography has been used extensively as a complementary diagnostic tool in breast cancer detection. Among thermographic methods, matrix factorization (MF) techniques show an unequivocal capability to detect thermal patterns corresponding vasodilation the cases. One of biggest challenges such is selecting best representation basis. In this study, embedding method proposed address problem and deep-semi-non-negative MF (Deep-SemiNMF) for thermography introduced, then tested 208 screening...
Continuum removal is vital in hyperspectral image analysis. It enables data to be used for any application and usually requires approximations or assumptions made. One of these related the calculation spectra background's blackbody temperature. Here, we present a new method calculate continuum process. The proposed eliminates ground-based infrared imagery by applying two acquisition sets before after using heating source. approach involves laboratory experiment on long-wave (LWIR; 7.7-11.8...
Detection of subsurface defects is undeniably a growing subfield infrared non-destructive testing (IR-NDT). There are many algorithms used for this purpose, where non-negative matrix factorization (NMF) considered to be an interesting alternative principal component analysis (PCA) by having no negative basis in decomposition. Here, application Semi (Semi-NMF) IR-NDT presented determine the Aluminum plate specimen through active thermographic method. To benchmark, defect detection accuracy...
Thermographic has proven to be effective for the early detection of breast cancer and with clinical examination (CBE). There are many matrix factorization methods developed computational thermography that can used extract thermal variations across acquisition time. These often summarize thermographic sequences simultaneously highlight predominant patterns. Finding a single infrared image capturing prevalent patterns changes remains challenging task in field. This study presents applications...
The recent applications in the field of thermography and Infrared Non-Destructive Testing (IRNDT) involved many different research fields, most these well-known infrared approaches have been utilized for thermal image enhancement, segmentation, particularly defect segmentation IRNDT. Principal Component Analysis (PCA) or Thermography (PCT) is one methods that has countlessly used it unequivocally constantly referred this field. Unfortunately, suffers from being a linear transformation...
Background: Lung cancer is one of the most common cancers in United States and fatal, with 142,670 deaths 2019. Accurately determining tumor response critical to clinical treatment decisions, ultimately impacting patient survival. To better differentiate between non-small cell lung (NSCLC) responders non-responders therapy, radiomic analysis emerging as a promising approach identify associated imaging features undetectable by human eye. However, plethora variables extracted from an image may...
Non-negative matrix factorization (NMF) solves the problem of negative basis in principal component analysis (PCA) and widely used diverse applications different fields.Here, we show an application sparse-NMF infrared non-destructive testing (IR-NDT) imaging.We applied Sparse-NMF to determine subsurface defects Aluminium plate specimen applying active thermographic method.To obtain results compared ability detect its computational load state-of-the-art approaches such as:...
The applications of hyperspectral infrared imagery in the different fields research are significant and growing. It is mainly used remote sensing for target detection, vegetation urban area categorization, astronomy geological applications. this technology consist mineral identification using airborne or satellite imagery. We address a quantitative qualitative assessment laboratory conditions. strive to identify nine grains (Biotite, Diopside, Epidote, Goethite, Kyanite, Scheelite,...
Classification of remote sensing images from urban area as a means to achieve necessitated information for some applications such automatic map updating and GIS, planning emergency response has become one the challenging subjects image processing researches. In this paper, method classification is addressed. First, motion based unsharp masking [MUSM] applied input enhance its high frequency components. Then, laplacian feature Bayesian classifier utilized. After that, size filter used large...
Hyperspectral imaging (HSI) in the long-wave infrared spectrum (LWIR) provides spectral and spatial information concerning emissivity of surface materials, which can be used for mineral identification. For this, an endmember, is purest form a mineral, as reference. All pure minerals have specific profiles electromagnetic wavelength, thought mineral's fingerprint. The main goal this paper identification by LWIR hyperspectral using machine learning scheme. has been recorded from energy emitted...
PurposeThis study investigated imaging biomarkers derived from PSMA-PET acquired pre- and post-metastasis-directed therapy (MDT) to predict 2-year metastasis-free survival (MFS), which provides valuable early response assessment improve patient outcomes.Materials/MethodsAn international cohort of 117 oligometastatic castration-sensitive prostate cancer (omCSPC) patients, comprising 34 John Hopkins Hospital (JHH) 83 Baskent University (BU), were treated with stereotactic ablative radiation...