A5086378073- Particle physics theoretical and experimental studies
- High-Energy Particle Collisions Research
- Particle Detector Development and Performance
- Quantum Chromodynamics and Particle Interactions
- Radiomics and Machine Learning in Medical Imaging
- Cancer Immunotherapy and Biomarkers
- Lung Cancer Diagnosis and Treatment
- Esophageal Cancer Research and Treatment
- Dark Matter and Cosmic Phenomena
- Cosmology and Gravitation Theories
- Ferroptosis and cancer prognosis
- Computational Physics and Python Applications
- AI in cancer detection
- Single-cell and spatial transcriptomics
- Cancer Genomics and Diagnostics
- Neutrino Physics Research
- Lung Cancer Treatments and Mutations
- Black Holes and Theoretical Physics
- Colorectal Cancer Screening and Detection
- Colorectal Cancer Surgical Treatments
- Immune Cell Function and Interaction
- Immune cells in cancer
- Molecular Biology Techniques and Applications
- Particle accelerators and beam dynamics
- Cell Image Analysis Techniques
New York University
2024-2025
NYU Langone Health
2025
University of Pennsylvania
2010-2024
Memorial Sloan Kettering Cancer Center
2021-2024
Children's Hospital of Philadelphia
2023-2024
Universidade de São Paulo
2024
Sapienza University of Rome
2024
Kettering University
2022-2023
Columbia University Irving Medical Center
2019-2023
Columbia University
2016-2021
Abstract Identification of adverse drug reactions (ADRs) during the post-marketing phase is one most important goals safety surveillance. Spontaneous reporting systems (SRS) data, which are mainstay traditional surveillance, used for hypothesis generation and to validate newer approaches. The publicly available US Food Drug Administration (FDA) Adverse Event Reporting System (FAERS) data requires substantial curation before they can be appropriately, applying different strategies cleaning...
Abstract Patients with high-grade serous ovarian cancer suffer poor prognosis and variable response to treatment. Known prognostic factors for this disease include homologous recombination deficiency status, age, pathological stage residual status after debulking surgery. Recent work has highlighted important information captured in computed tomography histopathological specimens, which can be exploited through machine learning. However, little is known about the capacity of combining...
Immunotherapy is used to treat almost all patients with advanced non-small cell lung cancer (NSCLC); however, identifying robust predictive biomarkers remains challenging. Here we show the capacity of integrating medical imaging, histopathologic and genomic features predict immunotherapy response using a cohort 247 NSCLC multimodal baseline data obtained during diagnostic clinical workup, including computed tomography scan images, digitized programmed death ligand-1 immunohistochemistry...
Abstract High-grade serous ovarian cancer (HGSOC) is an archetypal of genomic instability 1–4 patterned by distinct mutational processes 5,6 , tumour heterogeneity 7–9 and intraperitoneal spread 7,8,10 . Immunotherapies have had limited efficacy in HGSOC 11–13 highlighting unmet need to assess how the anatomical sites foci determine immunological states microenvironment. Here we carried out integrative analysis whole-genome sequencing, single-cell RNA digital histopathology multiplexed...
Abstract Multiplexed imaging offers a powerful approach to characterize the spatial topography of tissues in both health and disease. To analyze such data, specific combination markers that are present each cell must be enumerated enable accurate phenotyping, process often relies on unsupervised clustering. We constructed Pan-Multiplex (Pan-M) dataset containing 197 million distinct annotations marker expression across 15 different types. used Pan-M create Nimbus, deep learning model predict...
Abstract PD-L1 is the only approved biomarker for pembrolizumab in metastatic breast cancer response to combination chemo-immunotherapy. We searched tissue-based immune biomarkers of triple negative (mTNBC) patients prospectively treated with front-line chemoimmunotherapy on ENHANCE-1 study eribulin and pembrolizumab. used quantitative multiplexed immunofluorescence (qmIF) evaluate populations pre-treatment tissue characterize associations clinical outcomes. was a single arm phase Ib/II...
Multiplex immunofluorescence (mIF) is a promising tool for immunotherapy biomarker discovery in melanoma and other solid tumors. mIF captures detailed phenotypic information of immune cells the tumor microenvironment, as well spatial data that can reveal biologically relevant interactions among cell types. Given complexity data, development automated analysis pipelines crucial advancing discovery. In pre-treatment samples from 50 patients treated with checkpoint inhibitors (ICIs), higher...
We quantitatively characterized the change in temporospatial expression of repressive and stimulatory checkpoints across immune cell populations tumor microenvironment a cohort high grade serous ovarian carcinomas (HGSOC) using matched samples before after neoadjuvant platinum-based chemotherapy.Using retrospectively collected tissue from 9 patients, were assessed multiplex immunofluorescence Vectra Multispectral Imaging System (Perkin Elmer). used multiple panels to assess: (AE1/AE3), T...
Abstract Defining cellular and subcellular structures in images, referred to as cell segmentation, is an outstanding obstacle scalable single-cell analysis of multiplex imaging data. While advances machine learning-based segmentation have led potentially robust solutions, such algorithms typically rely on large amounts example annotations, known training Datasets consisting annotations which are thoroughly assessed for quality rarely released the public. As a result, there lack widely...
Summary Pediatric high-grade glioma (pHGG) is an incurable central nervous system malignancy that a leading cause of pediatric cancer death. While pHGG shares many similarities to adult glioma, it increasingly recognized as molecularly distinct, yet highly heterogeneous disease. In this study, we longitudinally profiled diverse cohort 16 patients before and after standard therapy through single-nucleus RNA ATAC sequencing, whole-genome CODEX spatial proteomics capture the evolution tumor...
Immune checkpoint inhibitor (ICI) therapies can increase the risk of cardiovascular events in survivors cancer by worsening atherosclerosis. Here we map expression immune checkpoints (ICs) within human carotid and coronary atherosclerotic plaques, revealing a network cell interactions that ICI treatments unintentionally target arteries. We identify population mature, regulatory CCR7+FSCN1+ dendritic cells, similar to those described tumors, as hub IC-mediated signaling plaques. Additionally,...
Generative Adversarial Networks (GANs) represent a promising class of generative networks that combine neural with game theory. From generating realistic images and videos to assisting musical creation, GANs are transforming many fields arts sciences. However, their application healthcare has not been fully realized, more specifically in electronic health records (EHR) data. In this paper, we propose framework for exploring the value context continuous laboratory time series We devise an...
Accurate prognostic biomarkers in early-stage melanoma are urgently needed to stratify patients for clinical trials of adjuvant therapy. We applied a previously developed open source deep learning algorithm detect tumor-infiltrating lymphocytes (TILs) hematoxylin and eosin (H&E) images melanomas. tested whether automated digital (TIL) analysis (ADTA) improved accuracy prediction disease specific survival (DSS) based on current pathology standards. ADTA was training cohort (n = 80) cutoff...
Abstract Programmed death-ligand 1 (PD-L1) IHC is the most commonly used biomarker for immunotherapy response. However, quantification of PD-L1 status in pathology slides challenging. Neither manual nor a computer-based mimicking readouts perfectly reproducible, and predictive performance both approaches regarding response limited. In this study, we developed deep learning (DL) method to predict directly from raw image data, without explicit intermediary steps such as cell detection or...
SUMMARY Quantitative assessment of multiplex immunofluorescence (mIF) data represents a powerful tool for immunotherapy biomarker discovery in melanoma and other solid tumors. In addition to providing detailed phenotypic information immune cells the tumor microenvironment, these datasets contain spatial that can reveal biologically relevant interactions among cell types. To assess quantitative mIF analysis as platform discovery, we used 12-plex panel characterize samples collected from 50...
Background Artificial intelligence (AI) applications for cancer imaging conceptually begin with automated tumor detection, which can provide the foundation downstream AI tasks. However, supervised training requires many image annotations, and performing dedicated post hoc labeling is burdensome costly. Purpose To investigate whether clinically generated annotations be data mined from picture archiving communication system (PACS), automatically curated, used semisupervised of a brain MRI...