A5046956648- AI in cancer detection
- Cell Image Analysis Techniques
- Advanced Fluorescence Microscopy Techniques
- Molecular Biology Techniques and Applications
- Prostate Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Photoacoustic and Ultrasonic Imaging
- Single-cell and spatial transcriptomics
- Advanced Neural Network Applications
- Cervical Cancer and HPV Research
- Generative Adversarial Networks and Image Synthesis
- Advanced Optical Sensing Technologies
- Medical Imaging and Analysis
- Medical Image Segmentation Techniques
- Optical Coherence Tomography Applications
- Prostate Cancer Treatment and Research
- Neurobiology and Insect Physiology Research
- Advanced Electron Microscopy Techniques and Applications
- Network Time Synchronization Technologies
- Colorectal Cancer Surgical Treatments
- Seismic Imaging and Inversion Techniques
- Animal Behavior and Reproduction
- 3D Shape Modeling and Analysis
- Underwater Acoustics Research
- Advanced Biosensing Techniques and Applications
University of Washington
2020-2024
Georgia Institute of Technology
2022
Emory University
2022
Case Western Reserve University
2022
Allen Institute
2018-2021
Allen Institute for Brain Science
2018
Susquehanna University
1998
PPL (United States)
1982
Prostate cancer treatment planning is largely dependent upon examination of core-needle biopsies. The microscopic architecture the prostate glands forms basis for prognostic grading by pathologists. Interpretation these convoluted three-dimensional (3D) glandular structures via visual inspection a limited number two-dimensional (2D) histology sections often unreliable, which contributes to under- and overtreatment patients. To improve risk assessment decisions, we have developed workflow...
Abstract Prostate cancer treatment decisions rely heavily on subjective visual interpretation [assigning Gleason patterns or International Society of Urological Pathology (ISUP) grade groups] limited numbers two‐dimensional (2D) histology sections. Under this paradigm, interobserver variance is high, with ISUP grades not correlating well outcome for individual patients, and contributes to the over‐ undertreatment patients. Recent studies have demonstrated improved prognostication prostate...
For tumor resections, margin status typically correlates with patient survival but positive rates are generally high (up to 45% for head and neck cancer). Frozen section analysis (FSA) is often used intraoperatively assess the margins of excised tissue, suffers from severe under-sampling actual surface, inferior image quality, slow turnaround, tissue destructiveness.
Slide-free digital pathology techniques, including nondestructive 3D microscopy, are gaining interest as alternatives to traditional slide-based histology. In order facilitate clinical adoption of these fluorescence-based software methods have been developed convert grayscale fluorescence images into color that mimic the appearance standard absorptive chromogens such hematoxylin and eosin (H&E). However, false-coloring algorithms often require manual iterative adjustment parameters, with...
SignificanceIn recent years, we and others have developed non-destructive methods to obtain three-dimensional (3D) pathology datasets of clinical biopsies surgical specimens. For prostate cancer risk stratification (prognostication), standard-of-care Gleason grading is based on examining the morphology glands in thin 2D sections. This motivates us perform 3D segmentation our for purposes computational analysis glandular features that could offer improved prognostic performance.AimTo...
Recent advances in 3D pathology offer the ability to image orders-of-magnitude more tissue than conventional while providing a volumetric context that is lacking with 2D sections, all without requiring destructive sectioning. Generating high-quality datasets on consistent basis non-trivial, careful attention many details regarding preparation, imaging, and data/image processing an iterative process. Here we provide end-to-end protocol covering aspects of workflow (using light-sheet...
We present an annotation free deep-learning-assisted segmentation pipeline to automatically identify healthy and malignant glands in 3D microscopy images of prostate biopsies stained with fluorescent analogs H&E.
Open-top light-sheet (OTLS) microscopy offers rapid 3D imaging of large optically cleared specimens. This enables nondestructive pathology, which provides key advantages over conventional slide-based histology including comprehensive sampling without tissue sectioning/destruction and visualization diagnostically important structures. With clinical specimens are often labeled with small-molecule stains that broadly target nucleic acids proteins, mimicking hematoxylin eosin (H&E) dyes....
Abstract Light-sheet microscopy has emerged as the preferred means for high-throughput volumetric imaging of cleared tissues. However, there is a need user-friendly system that can address applications with varied requirements in terms resolution (mesoscopic to sub-micrometer), sample geometry (size, shape, and number), compatibility tissue-clearing protocols holders various refractive indices. We present ‘hybrid’ combines novel non-orthogonal dual-objective conventional (orthogonal)...
Abstract Light-sheet microscopy has emerged as the preferred means for high-throughput volumetric imaging of cleared tissues. However, there is a need user-friendly system that can address applications with varied requirements in terms resolution (mesoscopic to sub-micrometer), sample geometry (size, shape, and number), compatibility tissue-clearing protocols holders various refractive indices. We present ‘hybrid’ combines novel non-orthogonal dual-objective conventional (orthogonal)...
Fluorescence microscopy benefits from spatially and temporally homogeneous illumination with the area matched to shape size of camera sensor. Fiber-coupled schemes have added benefit straightforward robust alignment ease installation compared free-space coupled illumination. Commercial open-source fiber-coupled, homogenized recently become available public; however, there been no published comparisons speckle reduction date. We characterize three different multimode fibers in combination two...
Abstract Array tomography (AT) is a technique for acquiring high resolution highly multiplexed imagery from series of ultra-thin sections arranged as an array on rigid substrate. Specialized microscope control has been required to utilize AT imaging technique, which often time consuming, and yields small volume data sets. Here we present MosaicPlanner, open source software platform light level AT, that streamlines the acquisition process utilizes general API provided by Micro-Manager,...
Conventional pathology workflows rely on two-dimensional, slide-based analysis of thin tissue sections. This approach comes with several key limitations including limited sampling, lack 3D structural information, and destruction valuable clinical specimens. There is growing interest in nondestructive to address these shortcomings. Existing work has mainly focused small-scale proof-of-concept studies, due part the difficulty producing consistent, high-quality datasets across hundreds...
High-quality optical sectioning is required for volumetric imaging of densely labeled clinical tissues. We describe an optimized open-top light-sheet (OTLS) microscope with axially swept illumination to provide improved over large fields view.
A deep learning-model based on the nnU-Net framework was trained for 3D prostate gland segmentation. Compared to our previous ITAS3D pipeline, operation is simpler, faster, and can maintain good accuracy with lower-resolution inputs.
Consistently generating high-quality datasets across large sample cohorts is necessary for clinical translation of 3D pathology. We present an end-to-end workflow non-destructive pathology with emphasis on quality control.
Abstract Slide-free digital pathology techniques, including nondestructive 3D microscopy, are gaining interest as alternatives to traditional slide-based histology. In order facilitate clinical adoption of these fluorescence-based software methods have been developed convert grayscale fluorescence images into color that mimic the appearance standard absorptive chromogens such hematoxylin and eosin (H&E). However, false-coloring algorithms often require manual iterative adjustment...
Abstract Prostate cancer treatment planning is largely dependent upon examination of core-needle biopsies. In current clinical practice, the microscopic architecture prostate glands what forms basis for prognostic grading by pathologists. Interpretation these convoluted 3D glandular structures via visual inspection a limited number 2D histology sections often unreliable, which contributes to under- and over-treatment patients. To improve risk assessment decisions, we have developed workflow...