A5020121219- Optical Coherence Tomography Applications
- Advanced Fluorescence Microscopy Techniques
- Photoacoustic and Ultrasonic Imaging
- Spectroscopy Techniques in Biomedical and Chemical Research
- Nanoplatforms for cancer theranostics
- Cell Image Analysis Techniques
- Angiogenesis and VEGF in Cancer
- Extracellular vesicles in disease
- Characterization and Applications of Magnetic Nanoparticles
- Wound Healing and Treatments
- 3D Printing in Biomedical Research
- Face recognition and analysis
- Photodynamic Therapy Research Studies
- Advanced Biosensing Techniques and Applications
- Ultra-Wideband Communications Technology
- Emotion and Mood Recognition
- Spam and Phishing Detection
- Viral Infectious Diseases and Gene Expression in Insects
- Optical Imaging and Spectroscopy Techniques
- Image Processing Techniques and Applications
- Lipid Membrane Structure and Behavior
- Ion channel regulation and function
- Retinal and Macular Surgery
- Machine Learning and ELM
- Antenna Design and Analysis
University of Illinois Urbana-Champaign
2016-2025
National Institute of Biomedical Imaging and Bioengineering
2024-2025
University of Illinois System
2017-2024
Singidunum University
2016-2024
Illinois College
2013-2022
University of Gothenburg
2021
Optica
2021
C4 Imaging (United States)
2021
University of Applied Health Sciences
2020
Bioengineering Center
2019
This paper presents a multimodal emotion recognition system, which is based on the analysis of audio and visual cues. From channel, Mel-Frequency Cepstral Coefficients, Filter Bank Energies prosodic features are extracted. For part, two strategies considered. First, facial landmarks' geometric relations, i.e., distances angles, computed. Second, we summarize each emotional video into reduced set key-frames, taught to visually discriminate between emotions. In order do so, convolutional...
Abstract Intravital microscopy (IVM) emerged and matured as a powerful tool for elucidating pathways in biological processes. Although label-free multiphoton IVM is attractive its non-perturbative nature, wide application has been hindered, mostly due to the limited contrast of each imaging modality challenge integrate them. Here we introduce simultaneous autofluorescence-multiharmonic (SLAM) microscopy, single-excitation source nonlinear platform that uses custom-designed excitation window...
Abstract Wide local excision (WLE) is a common surgical intervention for solid tumors such as those in melanoma, breast, pancreatic, and gastrointestinal cancer. However, adequate margin assessment during WLE remains significant challenge, resulting reinterventions to achieve control. Currently, no label-free imaging method available surgeons examine the resection bed vivo microscopic residual Optical coherence tomography (OCT) enables real-time high-resolution of tissue microstructure....
Dynamic magnetomotion of magnetic nanoparticles (MNPs) detected with magnetomotive optical coherence tomography (MM-OCT) represents a new methodology for contrast enhancement and therapeutic interventions in molecular imaging. In this study, we demonstrate vivo imaging dynamic functionalized iron oxide MNPs using MM-OCT preclinical mammary tumor model. Using targeted MNPs, images exhibit strong signals tumor, no significant were measured from tumors rats injected nontargeted or saline. The...
Intraoperative imaging of tumor microenvironment reveals correlations between extracellular vesicle density and breast pathology.
Abstract Feature selection and hyper-parameters optimization (tuning) are two of the most important challenging tasks in machine learning. To achieve satisfying performance, every learning model has to be adjusted for a specific problem, as efficient universal approach does not exist. In addition, data sets contain irrelevant redundant features that can even have negative influence on model’s performance. Machine applied almost everywhere; however, due high risks involved with growing number...
Despite extensive interest, extracellular vesicle (EV) research remains technically challenging. One of the unexplored gaps in EV has been inability to characterize spatially and functionally heterogeneous populations EVs based on their metabolic profile. In this paper, we utilize intrinsic optical structural contrast demonstrate vivo/in situ characterization a variety unprocessed (pre)clinical samples. With pixel-level segmentation mask provided by deep neural network, individual can be...
Successful treatment of breast cancer typically requires surgical removal the tumor.Optical coherence tomography (OCT) has been previously developed for real-time imaging margin.However, it can be difficult to distinguish between normal stromal tissue and based on scattering intensity structure alone.Polarization-sensitive optical (PS-OCT) is sensitive form birefringence biological tissue.We report development a high-speed PS-OCT system ex vivo human tissue, showing enhanced contrast healthy...
Two-photon fluorescence lifetime imaging microscopy (2P-FLIM) of autofluorescent metabolic coenzymes has been widely used to investigate energetic perturbations in living cells and tissues a label-free manner with subcellular resolution. While the currently state-of-the-art instruments are highly sensitive local molecular changes associated these processes, they inherently slow limit study dynamic environments. Here, sustained video-rate 2P-FLIM system is demonstrated for time-lapse reduced...
Evaluation of lymph node (LN) status is an important factor for detecting metastasis and thereby staging breast cancer. Currently utilized clinical techniques involve the surgical disruption resection lymphatic structure, whether nodes or axillary contents, histological examination. While reasonably effective at detection macrometastasis, majority resected are histologically negative. Improvements need to be made better detect micrometastasis, minimize eliminate complications, provide...
The rapid growth of number devices that are connected to internet things (IoT) networks, increases the severity security problems need be solved in order provide safe environment for network data exchange. discovery new vulnerabilities is everyday challenge experts and many novel methods detection prevention intrusions being developed dealing with this issue. To overcome these shortcomings, artificial intelligence (AI) can used development advanced intrusion systems (IDS). This allows such...
The selection of high-performing cell lines is crucial for biopharmaceutical production but often time-consuming and labor-intensive. We investigated label-free multimodal nonlinear optical microscopy non-perturbative profiling based on their intrinsic molecular contrast. Employing simultaneous autofluorescence multiharmonic (SLAM) with fluorescence lifetime imaging (FLIM), we characterized Chinese hamster ovary (CHO) at early passages (0–2). A machine learning (ML)-assisted analysis...
Label-free molecular imaging of the tumor microenvironment interrelates well-known events in carcinogenesis across spatial scales.
Recent advances in label-free virtual histology promise a new era for real-time molecular diagnosis the operating room and during biopsy procedures. To take full advantage of rich, multidimensional information provided by these technologies, reproducible reliable computational tools that could facilitate are great demand. In this study, we developed deep-learning-based framework to recognize cancer versus normal human breast tissue from images, with tile-level AUC (area under receiver curve)...
We report an automated differentiation model for classifying malignant tumor, fibro-adipose, and stroma in human breast tissues based on polarization-sensitive optical coherence tomography (PS-OCT). A total of 720 PS-OCT images from 72 sites 41 patients with H&E histology-confirmed diagnoses as the gold standard were employed this study. The is trained by features extracted both one OCT-based metric (i.e., intensity) four PS-OCT-based metrics phase difference between two channels ( PD ),...