A5071531364- AI in cancer detection
- Cervical Cancer and HPV Research
- Endometrial and Cervical Cancer Treatments
- Radiomics and Machine Learning in Medical Imaging
- Thyroid Cancer Diagnosis and Treatment
- Genital Health and Disease
- Gynecological conditions and treatments
- Hepatitis B Virus Studies
- Mobile Health and mHealth Applications
- Biomedical Text Mining and Ontologies
- Ovarian cancer diagnosis and treatment
- Gene expression and cancer classification
- Breast Lesions and Carcinomas
- Reproductive tract infections research
- Bone health and treatments
- Pituitary Gland Disorders and Treatments
- Head and Neck Anomalies
- Colorectal Cancer Screening and Detection
- Growth Hormone and Insulin-like Growth Factors
- Breast Cancer Treatment Studies
- Clinical Laboratory Practices and Quality Control
- Adrenal and Paraganglionic Tumors
- Teratomas and Epidermoid Cysts
- Epigenetics and DNA Methylation
- Management of metastatic bone disease
University College Hospital
2025
University College London
2025
National and Kapodistrian University of Athens
2013-2022
University General Hospital Attikon
2009-2018
Zero to Three
2018
Rush University Medical Center
2018
Columbia College - Missouri
2018
General-Maternity District Hospital Helena Venizelou
2017
Barts Health NHS Trust
2016
Royal London Hospital
2016
Background This study aims to investigate the efficacy of an Artificial Neural Network based on Multi‐Layer Perceptron (ANN–MPL) discriminate between benign and malignant endometrial nuclei lesions in cytological specimens. Methods We collected 416 histologically confirmed liquid‐based smears from 168 healthy patients, 152 patients with malignancy, 52 hyperplasia without atypia, 20 24 polyps. The morphometric characteristics 90 per case were analyzed using a custom image analysis system;...
Background The main purpose of directly sampled endometrial cytology is to detect invasive malignancies. With this principle in mind, Yokohama System (TYS) Working Group, composed cytopathologists, surgical pathologists, and gynecologic oncologists met at the 2016 International Congress Cytology, Yokohama, with aim publish a standardized reporting system inclusive specific diagnostic categories cytomorphologic criteria for uniform reliable diagnosis malignancies on samples. Methods...
Abstract Background/Aims Giant cell arteritis (GCA) is a medical emergency, requiring early recognition and treatment to prevent irreversible ischaemic vascular events. Corticosteroids are the first-line management of GCA, with patients often prolonged courses. Recognition glucocorticoid toxicity vital reduce risk complications, including glucocorticoid-induced diabetes mellitus (GIDM). The British Society Rheumatology (BSR) GCA guidelines suggest measuring baseline HbA1c within two weeks...
‘The objective of this study is to investigate the potential classification and regression trees (CARTs) in discriminating benign from malignant endometrial nuclei lesions. The was performed on 222 histologically confirmed liquid based cytological smears, specifically: 117 cases, 62 cases 43 hyperplasias with or without atypia. About 100 were measured each case using an image analysis system; total, we collected 22783 nuclei. 50% (the training set) used construct a CART model that for...
Nowadays, there are molecular biology techniques providing information related to cervical cancer and its cause: the human Papillomavirus (HPV), including DNA microarrays identifying HPV subtypes, mRNA such as nucleic acid based amplification or flow cytometry E6/E7 oncogenes, immunocytochemistry overexpression of p16. Each one these has own performance, limitations advantages, thus a combinatorial approach via computational intelligence methods could exploit benefits each method produce...
Medical laboratories are complex systems composed of specialized personnel and medical modalities. Despite complexity, they well-organized with standardized workflow. Especially for cytopathology the human factor is extremely important, because examination glass slides majority workflow from experts (cytopathologists). Recently there an increasing need to ensure quality by applying standards, such as ISO 15189:2012 which proposed many organizations in countries enforced law. ISO15189 does...
Objective. This study investigates the potential of an artificial intelligence (AI) methodology, radial basis function (RBF) neural network (ANN), in evaluation thyroid lesions. Study Design. The was performed on 447 patients who had both cytological and histological agreement. Cytological specimens were prepared using liquid-based cytology, result based subsequent surgical samples. Each specimen digitized; these images, nuclear morphology features measured by use image analysis system....
This study evaluated the accuracy and reproducibility of telecytological diagnoses proffered on basis digitized images from cervical smears prepared by means liquid-based cytology.Representative digital cytological a total 404 (benign, 135; atypical squamous cells undetermined significance, 92; low-grade intraepithelial lesion, 62; high-grade 87; cell carcinoma, 26; adenocarcinoma, 2) were uploaded to CytoTrainer e-learning telecytology platform (developed in Department Cytopathology,...
Abstract Objective Thyroid fine needle aspiration ( FNA ) contributes to the appropriate management of nodular thyroid lesions. The introduced categories in Bethesda system for reporting cytopathology TBSRTC are associated with an implied cancer risk, providing a clinical guideline. This study aims evaluate reproducibility this risk and compare results from two different departments. Methods Five hundred histologically confirmed s, studied since introduction , were obtained 4208 3587 s...
There have been various attempts to assess endometrial lesions on cytological material obtained via direct sampling. The majority of efforts focus the description criteria that lead classification systems resembling histological reporting formats. These low reproducibility, especially in cases atypical hyperplasia and well differentiated carcinomas. Moreover, they are not linked implied risk malignancy.The was collected from women examined at outpatient department four participating...
Prevalent cervical HPV infection and high-risk persistence consequences have been extensively investigated in the literature; nevertheless, any causative interrelations of other sexually transmitted bacterial infections (STIs) with not yet fully elucidated. This study aimed to investigate possible association STIs cytology aberrations genotyping results a representative sample predominantly young Greek women. Liquid-based molecular detection for as well extended were simultaneously assessed...
Nucleic acids of human papillomavirus (HPV) isolated by manual extraction method (AmpliLute) and automated MagNA pure system were compared evaluated with cytohistological findings in 253 women. The concordance level between AmpliLute was very good 93.3% (<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>κ</mml:mi><mml:mo>=</mml:mo><mml:mn>0.864</mml:mn></mml:math>,<mml:math...
<b><i>Objective:</i></b> To investigate the potential of Classification and Regression Trees (CARTs) for diagnosis thyroid lesions based on cell block immunocytochemistry cytological outcome. <b><i>Study Design:</i></b> A total 956 histologically confirmed cases (673 benign 283 malignant) from patients with nodules were prepared via liquid-based cytology evaluated; 4 additional slides stained cytokeratin 19 (CK-19), galectin 3 (Gal-3), Hector...
Background This study investigates the potential of classification and regression trees (CARTs) for evaluation thyroid lesions. Methods The was performed on 521, histologically confirmed cytological specimens prepared via liquid based cytology. For each specimen, contextual cellular morphology features were recorded by experienced cytopathologists, as described in everyday practice Bethesda System (TBS); these subsequently used to construct two CART models, viz. CART‐C prediction diagnosis...
Occurrence of malignancy in a thyroglossal duct cyst (TDC) children and adolescents is very rare, preoperative diagnosis challenge, appropriate management still debated. We report 19-year-old male patient referred for midline neck mass diagnosed as an atypical TDC after initial subsequent investigations. Ultrasound-guided fine-needle aspiration (FNA) the was diagnostic papillary thyroid carcinoma. Sistrunk procedure total thyroidectomy were performed. Histologic analysis confirmed presence...
Aim of this article is to investigate the potential Artificial Intelligence (AI) in discrimination between benign and malignant endometrial nuclei lesions. For purpose, 416 histologically confirmed liquid-based cytological smears were collected morphometric characteristics cell measured via image analysis. Then, 50% cases used train an AI system, specifically a learning vector quantization (LVQ) neural network. As result, classified as or malignant. Data from remaining evaluate system...