A5011843422- Cell Image Analysis Techniques
- AI in cancer detection
- Single-cell and spatial transcriptomics
- Immunotherapy and Immune Responses
- Radiomics and Machine Learning in Medical Imaging
- Molecular Biology Techniques and Applications
- Image Processing Techniques and Applications
- Brain Tumor Detection and Classification
- Gene expression and cancer classification
- Advanced Fluorescence Microscopy Techniques
- Anatomy and Medical Technology
- Gastrointestinal Bleeding Diagnosis and Treatment
- Gene Regulatory Network Analysis
- Eosinophilic Disorders and Syndromes
- vaccines and immunoinformatics approaches
- HER2/EGFR in Cancer Research
- Digital Imaging in Medicine
- Generative Adversarial Networks and Image Synthesis
- Digestive system and related health
- Poisoning and overdose treatments
- Vascular Anomalies and Treatments
- Cardiovascular Effects of Exercise
- Pain Management and Opioid Use
- Cardiac tumors and thrombi
- Stoma care and complications
Hadassah Medical Center
2019-2025
Weizmann Institute of Science
2023-2025
Hebrew University of Jerusalem
2022-2024
University Medical Center
2019
Gelre Hospitals
2019
Abstract Traditional histochemical staining of post-mortem samples often confronts inferior quality due to autolysis caused by delayed fixation cadaver tissue, and such chemical procedures covering large tissue areas demand substantial labor, cost time. Here, we demonstrate virtual autopsy using a trained neural network rapidly transform autofluorescence images label-free sections into brightfield equivalent images, matching hematoxylin eosin (H&E) stained versions the same samples. The...
Human epidermal growth factor receptor 2 (HER2) is a critical protein in cancer cell that signifies the aggressiveness of breast (BC) and helps predict its prognosis. Accurate assessment immunohistochemically (IHC) stained tissue slides for HER2 expression levels essential both treatment guidance understanding mechanisms. Nevertheless, traditional workflow manual examination by board-certified pathologists encounters challenges, including inter- intra-observer inconsistency extended...
Cellular plasticity mediates tissue development as well cancer growth and progression. In breast cancer, a shift to more epithelial phenotype (epithelialization) underlies state of reversible cell arrest called tumor dormancy, which enables drug resistance, recurrence, metastasis. Here, we explored the mechanisms driving epithelialization dormancy in aggressive mesenchymal-like cells three-dimensional cultures. Overexpressing either lineage-associated transcription factors OVOL1 or OVOL2...
Spatial proteomics measures multiple proteins in situ, capturing tissue complexity. However, cell classification densely packed tissues remains challenging due to the lack of efficient algorithms, annotation tools, and high-quality labeled datasets benchmark computational methods. We introduce CellTune, an integrated software for analysis large spatial datasets, which streamlines precise through optimized human-in-the-loop active learning workflow. It advances core capabilities across within...
Objective and Impact Statement: Human epidermal growth factor receptor 2 (HER2) is a critical protein in cancer cell that signifies the aggressiveness of breast (BC) helps predict its prognosis. Here, we introduce deep learning-based approach utilizing pyramid sampling for automated classification HER2 status immunohistochemically (IHC) stained BC tissue images. Introduction: Accurate assessment IHC-stained slides expression levels essential both treatment guidance understanding mechanisms....
Abstract Acute graft-versus-host disease (aGVHD) is a significant complication of allogeneic hematopoietic stem cell transplantation (aHSCT), driven by alloreactive donor T cells in the gut. However, roles additional and host this process are not fully understood. We conducted multiplexed imaging on 59 biopsies from patients with gastrointestinal GVHD 10 healthy controls, revealing key pathological changes, including fibrosis, crypt alterations, loss Paneth cells, accumulation endocrine...
Abstract Sentinel lymph node (sLN) biopsy is part of melanoma staging, as involved LNs indicate a higher risk recurrence. However, how the sLN shaped by tumor and reciprocally affects metastatic progression poorly understood. Here, we mapped immune organization in non-involved sLNs 69 patients using high-resolution spatial proteomics, transcriptomics deep learning, leveraging data for prognostic evaluation. In with LNs, robust T cell response correlated absence protection from metastases was...
Abstract Understanding tissue structure and function requires tools that quantify the expression of multiple proteins at single-cell resolution while preserving spatial information. Current imaging technologies use a separate channel for each individual protein, inherently limiting their throughput scalability. Here, we present CombPlex (COMBinatorial multiPLEXing), combinatorial staining platform coupled with an algorithmic framework to exponentially increase number can be measured from C...
e15573 Background: HER2 is a well-established biomarker and target in multiple tumor types, including metastatic colorectal cancer (mCRC). Despite the lack of amplification, certain HER2-low tumors were recently found to respond novel HER2-directed antibody-drug conjugates, warranting an exploration clinical molecular features these entities. Yet, real-world prevalence clinicopathologic characteristics mCRC are largely unknown. Here, we aim describe compare them HER2-0 tumors. Methods: We...
Concerns have been mounting regarding the underdiagnosis of HIV among respiratory co-infections associated with COVID-19 pandemic. The delay in recognizing HIV/AIDS may be attributed to similarities clinical, laboratory (lymphopenia) and imaging presentations, which are typical for advanced AIDS but could also indicative a infection.Herein, we present case 38-year-old ultraorthodox Jew late diagnosis context infection. This occurred after several months recurrent infections compounded by...
Abstract Understanding tissue structure and function requires tools that quantify the expression of multiple proteins at single-cell resolution while preserving spatial information. Current imaging technologies use a separate channel for each individual protein, inherently limiting their throughput scalability. Here, we present CombPlex (COMBinatorial multiPLEXing), combinatorial staining platform coupled with an algorithmic framework to exponentially increase number can be measured from C...
Histopathological staining of human tissue is essential in the diagnosis various diseases. The recent advances virtual technologies using AI alleviate some costly and tedious steps involved traditional histochemical process, permitting multiplexed rapid label-free without reagents, while also preserving tissue. However, potential hallucinations artifacts these virtually stained images pose concerns, especially for clinical utility approaches. Quality assessment histology generally performed...
We present deep learning-based virtual staining of label-free autopsy tissue sections, eliminating severe autolysis-induced artifacts caused by delayed fixation inherent in traditional histochemical H&E staining.
We present an automated, deep learning-based method for HER2 score classification in breast cancer, achieving 85.47% accuracy on tissue microarrays from 300 patients. This can significantly improve the evaluation process, saving diagnostician time.