A5091389599- Prostate Cancer Treatment and Research
- Radiomics and Machine Learning in Medical Imaging
- Molecular Biology Techniques and Applications
- AI in cancer detection
- Cancer Genomics and Diagnostics
- Glutathione Transferases and Polymorphisms
- Cancer, Lipids, and Metabolism
- Nutrition, Genetics, and Disease
- Cell Image Analysis Techniques
- Cancer, Hypoxia, and Metabolism
- Ferroptosis and cancer prognosis
- Cancer Cells and Metastasis
- Biomedical Text Mining and Ontologies
- Animal Genetics and Reproduction
- Cancer-related molecular mechanisms research
- Extracellular vesicles in disease
- CAR-T cell therapy research
- Virus-based gene therapy research
- Gene expression and cancer classification
- Vascular Malformations and Hemangiomas
- Prostate Cancer Diagnosis and Treatment
- Testicular diseases and treatments
- Single-cell and spatial transcriptomics
- Genetics, Bioinformatics, and Biomedical Research
- Cervical Cancer and HPV Research
Cairo University
2018-2023
Children Cancer Hospital
2020-2022
Weatherford College
2021
Dana-Farber Cancer Institute
2018-2020
Harvard University
2020
While deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due the effort and experience required carefully delineate tissue structures, difficulties related sharing markup whole-slide images.We recruited 25 participants, ranging from senior pathologists medical students, regions 151 breast cancer slides using Digital Slide Archive....
Abstract Systemic metabolic alterations associated with increased consumption of saturated fat and obesity are linked risk prostate cancer progression mortality, but the molecular underpinnings this association poorly understood. Here, we demonstrate in a murine model, that high-fat diet (HFD) enhances MYC transcriptional program through favour histone H4K20 hypomethylation at promoter regions regulated genes, leading to cellular proliferation tumour burden. Saturated intake (SFI) is also an...
High-resolution mapping of cells and tissue structures provides a foundation for developing interpretable machine-learning models computational pathology. Deep learning algorithms can provide accurate mappings given large numbers labeled instances training validation. Generating adequate volume quality labels has emerged as critical barrier in pathology the time effort required from pathologists. In this paper we describe an approach engaging crowds medical students pathologists that was...
Objective: Fine needle aspiration cytology has higher sensitivity and predictive value for diagnosis of thyroid nodules than any other single diagnostic methods. In the Bethesda system reporting thyroid, category IV, encompasses both adenoma carcinoma, but it is not possible to differentiate lesions in practice can be only differentiated after resection. this work, we aim at exploring ability a convolutional neural network (CNN) model sub-classifying cytological images IV into follicular...
Among prostate cancers containing Gleason pattern 4, cribriform morphology is associated with unfavorable clinicopathologic factors, but its genetic features and association long-term outcomes are incompletely understood. In this study, genetic, transcriptional, epigenetic of invasive carcinoma (ICC) tumors were compared non-cribriform 4 (NC4) in The Cancer Genome Atlas (TCGA) cohort. ICC (
Whole-slide histology images contain information that is valuable for clinical and basic science investigations of cancer but extracting quantitative measurements from these challenging researchers who are not image analysis specialists. In this article, we describe HistomicsML2, a software tool learn-by-example training machine learning classifiers histologic patterns in whole-slide images. This improves efficiency classifier performance by guiding users to the most informative examples...
High-resolution mapping of cells and tissue structures provides a foundation for developing interpretable machine-learning models computational pathology. Deep learning algorithms can provide accurate mappings given large numbers labeled instances training validation. Generating adequate volume quality labels has emerged as critical barrier in pathology the time effort required from pathologists. In this paper we describe an approach engaging crowds medical students pathologists that was...
Nucleus detection, segmentation and classification are fundamental to high-resolution mapping of the tumor microenvironment using whole-slide histopathology images. The growing interest in leveraging power deep learning achieve state-of-the-art performance often comes at cost explainability, yet there is general consensus that explainability critical for trustworthiness widespread clinical adoption. Unfortunately, current paradigms rely on pixel saliency heatmaps or superpixel importance...
Extracting quantitative phenotypic information from whole-slide images presents significant challenges for investigators who are not experienced in developing image analysis algorithms. We present new software that enables rapid learn-by-example training of machine learning classifiers detection histologic patterns imaging datasets. HistomicsML2.0 uses convolutional networks to be readily adaptable a variety applications, provides web-based user interface, and is available as container...
Abstract Purpose: Identifying cancers with high PI3K pathway activity is critical for treatment selection and eligibility into clinical trials of inhibitors. Assessments tumor signaling need to consider intratumoral heterogeneity multiple regulatory nodes. Experimental Design: We established a novel, mechanistically informed approach assessing pathways by quantifying single-cell–level multiplex immunofluorescence using custom algorithms. In proof-of-concept study, we stained archival...
This study aimed to evaluate management and prognosis in children with pheochromocytoma who were treated at an Egyptian tertiary center.The authors conducted 8-year retrospective analysis for 17 patients presented from January 2013 2021. Clinical criteria, operative details, follow-up data assessed. Overall (OS) event-free survival (EFS) estimated by the Kaplan-Meier method. An event was assigned occurrence of recurrence or metachronous disease, death.Median age diagnosis 14 years (range:...
<div>Abstract<p>Whole-slide histology images contain information that is valuable for clinical and basic science investigations of cancer but extracting quantitative measurements from these challenging researchers who are not image analysis specialists. In this article, we describe HistomicsML2, a software tool learn-by-example training machine learning classifiers histologic patterns in whole-slide images. This improves efficiency classifier performance by guiding users to the...
<p>Software preview video.</p>
<p>All supplementary tables and figures</p>
<div>AbstractPurpose:<p>Identifying cancers with high PI3K pathway activity is critical for treatment selection and eligibility into clinical trials of inhibitors. Assessments tumor signaling need to consider intratumoral heterogeneity multiple regulatory nodes.</p>Experimental Design:<p>We established a novel, mechanistically informed approach assessing pathways by quantifying single-cell–level multiplex immunofluorescence using custom algorithms. In proof-of-concept...
<div>AbstractPurpose:<p>Identifying cancers with high PI3K pathway activity is critical for treatment selection and eligibility into clinical trials of inhibitors. Assessments tumor signaling need to consider intratumoral heterogeneity multiple regulatory nodes.</p>Experimental Design:<p>We established a novel, mechanistically informed approach assessing pathways by quantifying single-cell–level multiplex immunofluorescence using custom algorithms. In proof-of-concept...
<p>Supplementary figures and table legends.</p>
<p>Software preview video.</p>
<p>Supplementary figures and table legends.</p>
<p>All supplementary tables and figures</p>
<p>(A) Cribriform carcinoma, (B) Noncribriform carcinoma.</p>