A5056357448- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Spectroscopy Techniques in Biomedical and Chemical Research
- Infrared Thermography in Medicine
- Cell Image Analysis Techniques
- Molecular Biology Techniques and Applications
- Spectroscopy and Chemometric Analyses
- Genetics, Bioinformatics, and Biomedical Research
- Generative Adversarial Networks and Image Synthesis
- Photoacoustic and Ultrasonic Imaging
- Thermography and Photoacoustic Techniques
- Biomedical Text Mining and Ontologies
- Optical Coherence Tomography Applications
- Cancer Genomics and Diagnostics
- Digital Imaging for Blood Diseases
- Image Processing Techniques and Applications
- Artificial Intelligence in Healthcare and Education
- COVID-19 diagnosis using AI
- Viral Infections and Immunology Research
- Advanced Neural Network Applications
- Advanced MRI Techniques and Applications
- Animal Diversity and Health Studies
- Medical Imaging Techniques and Applications
- Brain Tumor Detection and Classification
- thermodynamics and calorimetric analyses
University of Illinois Urbana-Champaign
2020-2025
University of Illinois System
2021-2023
Urbana University
2022
Significance This study reports the ability to provide label-free molecular information from infrared (IR) spectroscopy via ubiquitous optical microscope. Modeling thermal-mechanical coupling of samples, we design, build, and validate an IR-optical hybrid (IR-OH) microscope that uses interferometry measure dimensional change in materials arising spectral absorption. We show seamless compatibility IR-OH with routine microscopy emerging computational ubiquity enables all-digital pathology...
Chemical imaging, especially mid-infrared spectroscopic microscopy, enables label-free biomedical analyses while achieving expansive molecular sensitivity. However, its slow speed and poor image quality impede widespread adoption. We present a microscope that provides high-throughput recording, low noise, high spatial resolution where the bottom-up design of optical train facilitates dual-axis galvo laser scanning diffraction-limited focal point over large areas using custom, compound,...
Oral potentially malignant disorders (OPMDs) are precursors to over 80% of oral cancers. Hematoxylin and eosin (H&E) staining, followed by pathologist interpretation tissue cellular morphology, is the current gold standard for diagnosis. However, this method qualitative, can result in errors during multi-step diagnostic process, results may have significant inter-observer variability. Chemical imaging (CI) offers a promising alternative, wherein label-free used record both morphology...
Infrared (IR) spectroscopic imaging is of potentially wide use in medical applications due to its ability capture both chemical and spatial information. This complexity the data necessitates using machine intelligence as well presents an opportunity harness a high-dimensionality set that offers far more information than today's manually-interpreted images. While convolutional neural networks (CNNs), including well-known U-Net model, have demonstrated impressive performance image...
Tumor grade assessment is critical to the treatment of cancers. A pathologist typically evaluates by examining morphologic organization in tissue using hematoxylin and eosin (H&E) stained sections. Fourier transform infrared spectroscopic (FT-IR) imaging provides an alternate view which spatially specific molecular information from unstained can be utilized. Here, we examine potential IR for grading colon cancer biopsy samples. We used a 148-patient cohort develop deep learning classifier...
Abstract Histopathology has been a cornerstone of biomedical tissue assessment for decades, involving labor-intensive and multi-step process that includes biopsy, gross examination, sampling, subsequent processing into snap-frozen or formalin-fixed paraffin-embedded (FFPE) blocks. These blocks are then sectioned, stained, examined microscopically to diagnose grade tissues. Despite its effectiveness, the traditional workflow is time-consuming, resource-intensive, reliant on chemical dyes...
Pathology remains a labor-intensive discipline, relying on workflows rooted in practices established over century ago. Despite incremental technological advancements, the diagnostic process—from tissue preparation to interpretation—still heavily depends thinly sliced sections stained and examined under brightfield microscopy by skilled pathologists. Difficult cases often necessitate iterative staining or complex immunohistochemistry (IHC) analyses. However, recent emergence of machine...
Histopathology has remained a cornerstone for biomedical tissue assessment over century, with resource-intensive workflow involving biopsy or excision, gross examination, sampling, processing to snap frozen formalin-fixed paraffin-embedded blocks, sectioning, staining, optical imaging, and microscopic assessment. Emerging chemical imaging approaches, including stimulated Raman scattering (SRS) microscopy, can directly measure inherent molecular composition in (thereby dispensing the need...
Myocardial fibrosis underpins a number of cardiovascular conditions and is difficult to identify with standard histologic techniques. Challenges include imaging, defining an objective threshold for classifying as mild or severe, understanding the molecular basis these changes.To develop novel, rapid, label-free approach accurately measure quantify extent in cardiac tissue using infrared spectroscopic imaging.We performed imaging combined that advanced machine learning-based algorithms assess...
Histopathology is critical for the diagnosis of many diseases, including cancer. These protocols typically require pathologists to manually evaluate slides under a microscope, which time-consuming and subjective, leading interest in machine learning automate analysis. However, computational techniques are limited by batch effects, where technical factors like differences preparation protocol or scanners can alter appearance slides, causing models trained on one institution fail when...
Infrared (IR) microscopes measure spectral information that quantifies molecular content to assign the identity of biomedical cells but lack spatial quality optical microscopy appreciate morphologic features. Here, we propose a method utilize semantic cellular from IR imaging with detail pathology images in deep learning-based approach image super-resolution. Using Generative Adversarial Networks (GANs), enhance beyond diffraction limit while retaining their contrast. This technique can be...
Significant biomedical research and clinical care rely on the histopathologic examination of tissue structure using microscopy stained tissue. Virtual staining (VS) offers a promising alternative with potential to reduce cost eliminate use toxic reagents. However, critical challenge hallucinations limits confidence in its use, necessitating VS co-pilot detect these hallucinations. Here, we first formally establish problem hallucination detection VS. Next, introduce scalable, post-hoc method...
MR fingerprinting (MRF) is a novel method for quantitative assessment of
The detection of semantic and covariate out-of-distribution (OOD) examples is a critical yet overlooked challenge in digital pathology (DP). Recently, substantial insight methods on OOD were presented by the ML community, but how do they fare DP applications? To this end, we establish benchmark study, our highlights being: 1) adoption proper evaluation protocols, 2) comparison diverse detectors both single multi-model setting, 3) exploration into advanced settings like transfer learning...
An optical microscopic examination of thinly cut stained tissue on glass slides prepared from a FFPE blocks is the gold standard for diagnostics. In addition, diagnostic abilities and expertise any pathologist dependent their direct experience with common as well rarer variant morphologies. Recently, deep learning approaches have been used to successfully show high level accuracy such tasks. However, obtaining expert-level annotated images an expensive time-consuming task artificially...