A5023901329- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Cancer Cells and Metastasis
- Pancreatic and Hepatic Oncology Research
- Immune cells in cancer
- Cell Image Analysis Techniques
- Cancer Genomics and Diagnostics
- Reconstructive Surgery and Microvascular Techniques
- Colorectal Cancer Screening and Detection
- Cancer, Hypoxia, and Metabolism
- Knee injuries and reconstruction techniques
- Cancer Immunotherapy and Biomarkers
- Immunotherapy and Immune Responses
- Bone fractures and treatments
- Medical Image Segmentation Techniques
- Dental Implant Techniques and Outcomes
- Hippo pathway signaling and YAP/TAZ
- High Altitude and Hypoxia
- Fibroblast Growth Factor Research
- Skin and Cellular Biology Research
- Diabetic Foot Ulcer Assessment and Management
- Traumatic Brain Injury and Neurovascular Disturbances
- Digital Imaging for Blood Diseases
- Mathematical Biology Tumor Growth
- Single-cell and spatial transcriptomics
Stony Brook School
2020-2024
Stony Brook University
2016-2024
Stony Brook University Hospital
2020
Tulane University
2013-2015
Quantitative assessment of spatial relations between tumor and tumor-infiltrating lymphocytes (TIL) is increasingly important in both basic science clinical aspects breast cancer research. We have developed evaluated convolutional neural network analysis pipelines to generate combined maps regions TILs routine diagnostic whole slide tissue images. The provide insight about the structural patterns distribution lymphocytic infiltrates facilitate improved quantification TILs. Both TIL analyses...
Tumor-infiltrating lymphocytes (TILs) have been established as a robust prognostic biomarker in breast cancer, with emerging utility predicting treatment response the adjuvant and neoadjuvant settings. In this study, role of TILs overall survival progression-free interval was evaluated two independent cohorts cancer from Cancer Genome Atlas (TCGA BRCA) Carolina Breast Study (UNC CBCS). We utilized machine learning computer vision algorithms to characterize TIL infiltrates digital whole-slide...
Abstract Bulk analyses of pancreatic ductal adenocarcinoma (PDAC) samples are complicated by the tumor microenvironment (TME), i.e. signals from fibroblasts, endocrine, exocrine, and immune cells. Despite this, we others have established stroma subtypes with prognostic significance. However, understanding underlying driving distinct stromal landscapes is still incomplete. Here integrate 92 single cell RNA-seq seven independent studies to build a reproducible PDAC atlas focus on tumor-TME...
Multiplex immunohistochemistry (mIHC) permits the labeling of six or more distinct cell types within a single histologic tissue section. The classification each type requires detection unique colored chromogens localized to cells expressing biomarkers interest. most comprehensive and reproducible method evaluate such slides is employ digital pathology image analysis pipelines whole-slide images (WSIs). Our suite deep learning tools quantitatively evaluates expression in mIHC WSIs. These...
ABSTRACT Amputation of the digit tip within terminal phalangeal bone rodents, monkeys, and humans results in near-perfect regeneration surrounding tissues; however, amputations at a more proximal level fail to produce same regenerative result. Digit is coordinated, multifaceted process that incorporates signaling from bioactive growth factors both tissue matrix several different cell populations. To elucidate mechanisms involved we developed novel multi-tissue slice-culture model regenerates...
Oxygen is critical for optimal bone regeneration. While axolotls and salamanders have retained the ability to regenerate whole limbs, mammalian regeneration restricted distal tip of digit (P3) in mice, primates, humans. Our previous study revealed oxygen microenvironment during dynamic temporally influential building degrading bone. Given that dependent on a changing environment, better understanding effects wounding, scarring, regeneration, ways artificially generate both hypoxic replete...
Multiplex immunohistochemistry (mIHC) is an innovative and cost-effective method that simultaneously labels multiple biomarkers in the same tissue section. Current platforms support labeling six or more cell types with different colored stains can be visualized brightfield light microscopy. However, analyzing interpreting multi-colored images comprised of thousands cells a challenging task for both pathologists current image analysis methods. We propose novel deep learning based predicts...
Abstract Background The immune microenvironment impacts tumor growth, invasion, metastasis, and patient survival may provide opportunities for therapeutic intervention in pancreatic ductal adenocarcinoma (PDAC). Although never studied as a potential modulator of the response most cancers, Keratin 17 (K17), biomarker aggressive (basal) molecular subtype PDAC, is intimately involved histogenesis psoriasis, basal cell carcinoma, cervical squamous carcinoma. Thus, we hypothesized that K17...
An amendment to this paper has been published and can be accessed via the original article.
Abstract Background. Keratin 17 (K17) is a negative prognostic and predictive biomarker, overexpressed in the biologically most aggressive forms of pancreatic ductal adenocarcinoma (PDAC). In other anatomic sites disease processes, K17 expression impacts inflammatory microenvironment, correlating with changes cytokines infiltration CD8+ T cells. Thus, we hypothesized that also immune response PDAC. Methods. We aimed to determine relationship between intratumoral peritumoral cell infiltrates...
<title>Abstract</title> Background: The immune microenvironment impacts tumor growth, invasion, metastasis, and patient survival may provide opportunities for therapeutic intervention in pancreatic ductal adenocarcinoma (PDAC). Although never studied as a potential modulator of the response most cancers, Keratin 17 (K17), biomarker aggressive (basal) molecular subtype PDAC, is intimately involved histogenesis psoriasis, basal cell carcinoma, cervical squamous carcinoma. Thus, we hypothesized...
Quantitative assessment of Tumor-TIL spatial relationships is increasingly important in both basic science and clinical aspects breast cancer research. We have developed evaluated convolutional neural network (CNN) analysis pipelines to generate combined maps regions tumor infiltrating lymphocytes (TILs) routine diagnostic whole slide tissue images (WSIs). produce interactive that provide 1) insight about the structural patterns distribution lymphocytic infiltrates 2) facilitate improved...
In the article titled “Endogenous bone regeneration is dependent upon a dynamic oxygen event” which was published in November 2014 issue of Journal Bone and Mineral Research (Volume 29, Issue 11, pages 2336–2345; DOI: 10.1002/jbmr.2261), please note following error: On 2339, 2341, 2342, Figures 2, 3, 4, 5 were inadvertently printed black white. The figures correctly color online version. version WileyOnlineLibrary available to all at http://onlinelibrary.wiley.com/doi/10.1002/jbmr.2261/full...
For the task of semantic segmentation, high-resolution (pixel-level) ground truth is very expensive to collect, especially for high resolution images such as gigapixel pathology images. On other hand, collecting low labels (labels a block pixels) these much more cost efficient. Conventional methods trained on low-resolution are only capable giving predictions. The existing state-of-the-art label super (LSR) method predicting labels, using supervision, given joint distribution between and...
Abstract By the year 2020, pancreatic cancer (PDAC) is projected to be second leading cause of deaths in United States. Current systemic therapies offer limited survival advantages subgroups patients, suggesting underlying biological differences this deadly cancer. Our lab has recently identified keratin-17 (K17) gene expression as a prognostic and predictive biomarker PDAC. Furthermore, we found that K17 acts an oncoprotein by promoting degradation tumor suppressor p27KIP1, while knockdown...
One in 200 people the U.S. is a survivor of limb amputation. The ideal replacement for an amputated would be regrowth patient's own limb. Mammals have prominent ability to regenerate digit tip (P3) including bone, surrounding connective tissue and epithelia. Bone fracture studies show that fluctuations oxygen tension can trigger bone repair cascades such as osteoblast differentiation osteoclast activation. Therefore, we hypothesize changes will facilitate regenerative process tip. Because...
Abstract The interaction of tumor, stroma, and immune cells in pancreatic ductal adenocarcinoma (PDAC) is complex difficult to quantify patient samples. Recently, deep learning algorithms have shown successes identifying tumor lymphocytes regions on whole-slide images derived from routinely collected histopathologic specimens. Cancer Genome Atlas (TCGA) particular has generated as well paired molecular data, thus allowing for combined spatial analyses tumor-lymphocyte interactions. We...