A5069650424- AI in cancer detection
- Image Retrieval and Classification Techniques
- Pancreatic and Hepatic Oncology Research
- Radiomics and Machine Learning in Medical Imaging
- Advanced Image and Video Retrieval Techniques
- Liver Disease Diagnosis and Treatment
- COVID-19 diagnosis using AI
- Data Mining Algorithms and Applications
- Rough Sets and Fuzzy Logic
- Thyroid Cancer Diagnosis and Treatment
- Lung Cancer Diagnosis and Treatment
- Video Analysis and Summarization
- Biomedical Text Mining and Ontologies
- Soft Robotics and Applications
- Colorectal Cancer Screening and Detection
- Game Theory and Applications
- Antibiotic Resistance in Bacteria
- Economic theories and models
- Auction Theory and Applications
- Bacterial biofilms and quorum sensing
- Image Processing and 3D Reconstruction
- Hepatocellular Carcinoma Treatment and Prognosis
- Hepatitis C virus research
- Imbalanced Data Classification Techniques
- Hepatitis B Virus Studies
University of Craiova
2011-2024
Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, remains highly operator dependent. To address this problem, machine learning algorithms (MLA) can generate an automatic computer-aided (CAD) by analyzing a large number clinical images in real-time. We aimed...
CTX-M betalactamases have shown a rapid spread in the recent years among Enterobacteriaceae and become most prevalent Extended Spectrum Beta-Lactamases (ESBLs) many parts of world. The introduction dissemination antibiotic-resistant genes limits options for treatment, increases mortality morbidity patients, leads to longer hospitalization expensive costs. We aimed identify beta-lactamases circulating encoded by blaCTX-M-15, blaSHV-1 blaTEM-1 Escherichia coli (E. coli) Klebsiella pneumoniae...
Background and Objectives: At present, thyroid disorders have a great incidence in the worldwide population, so development of alternative methods for improving diagnosis process is necessary. Materials Methods: For this purpose, we developed an ensemble method that fused two deep learning models, one based on convolutional neural network other transfer learning. first model, called 5-CNN, efficient end-to-end trained model with five layers, while second pre-trained VGG-19 architecture was...
In this paper we proposed different architectures of convolutional neural network (CNN) to classify fatty liver disease in images using only pixels and diagnosis labels as input. We trained validated our models a dataset 629 consisting 2 types images, normal steatosis.We assessed two pre-trained networks, Inception-v3 VGG-16 fine-tuning. Both were on ImageNet extract features from B-mode ultrasound images. The results obtained through these methods compared for selecting the predictive model...
The study evaluated the evolution of incidence infections with Klebsiella in County Clinical Emergency Hospital Craiova (SCJUC), Romania. Also, we monitored antibiotic resistance over more than two years and detected changes to various antimicrobial agents. Our included 2062 patients (823 women 1239 men) hospitalised SCJUC during period 1st September 2017 30 June 2019. In 458 (22.21%) from total patients, collected samples (1116) were positive those, isolated 251 strains spp. We conducted a...
Background and Aims: Mucosal healing (MH) is associated with a stable course of Crohn’s disease (CD) which can be assessed by confocal laser endomicroscopy (CLE). To minimize the operator’s errors automate assessment CLE images, we used deep learning (DL) model for image analysis. We hypothesized that DL combined convolutional neural networks (CNNs) long short-term memory (LSTM) distinguish between normal inflamed colonic mucosa from images.
 Methods: The study included 54 patients, 32...
(1) Background: The new SARS-COV-2 pandemic overwhelmed intensive care units, clinicians, and radiologists, so the development of methods to forecast diagnosis’ severity became a necessity helpful tool. (2) Methods: In this paper, we proposed an artificial intelligence-based multimodal approach future patients with laboratory-confirmed cases SARS-CoV-2 infection. At hospital admission, collected 46 clinical biological variables chest X-ray scans from 475 COVID-19 positively tested patients....
Aims Detection and differentiation of cystic versus solid pancreatic lesions prior to performance EUS-guided fine needle aspiration biopsy (EUS-FNA/B) can be automated by use artificial intelligence (AI) techniques based on convolutional neural networks (CNN). We aimed test the technical feasibility a novel real-time AI-powered EUS imaging analysis software for detection segmentation pancreas, and/or masses (PANC-AI).
(
Currently early diagnosis of malignant lesions at the periphery lung parenchyma requires guidance biopsy needle catheter from bronchoscope into smaller peripheral airways via harmful X-ray radiation. Previously, we developed an image-guided system, iMTECH which uses electromagnetic tracking and although it increases precision collection minimizes use radiation during interventional procedures, only traces tip leaving remaining untraceable in real time therefore increasing image registration...
Our goal is to organize the image contents semantically. In this paper, we propose a method classify images semantically, using C-fuzzy algorithm segment natural scenes into perceptually uniform regions. The low-level characteristics that are taken account are: color, texture, shape, absolute spatial arrangement, coherency, and dimension. Since humans ultimate users of most retrieval systems, it important according meaningful categories. This requires an understanding semantic categories use...
Due to complex interplay between host and viral factors, pathogenesis of chronic hepatitis C (CHC) is considered a challenging issue.Infection with virus (HCV) not confined only liver but can induce disturbances in many other organs systems.Our primary aim for this study was evaluate biological response rates sustained virological (SVR) patients diagnosed CHC, treated Interferon-alpha (IFN-α), Pegylated (PEG)-IFN-α2a or -α2b plus Ribavirin.The second the identification predictive factors...
Background and Objectives: Hepatitis B virus infection remains a major public health concern. The interaction between hepatitis (HBV) the host inflammatory response is an important contributing factor driving liver damage diseases outcomes. management of chronic area massive unmet clinical need worldwide. Our primary aim for this study was to evaluate biological rates sustained virological in patients with treated Peg-IFN α-2a/b. second identification metabolic changes insulin resistance....
Aims Endoscopic ultrasound (EUS) guided fine needle biopsy (FNB) is the procedure of choice for diagnosis pancreatic ductal adenocarcinoma (PDAC). The samples obtained are small and require expertise in pathology, whilst difficult view scarcity malignant cells important desmoplastic reaction these tumors. Moreover, limited availability publicly accessible datasets containing histopathological images has resulted a research on automated detection PDAC, especially based whole slide imaging...
ABSTRACT The integration of medical robots is revolutionizing clinical medicine, especially in procedures requiring precision instrument manipulation and navigation within the body using imaging techniques like fluoroscopy, CT, MRI. This particularly challenging peripheral lung lesion examinations, where guiding long, flexible instruments through airways to target exposes professionals patients harmful X-ray radiation. Several robotic approaches exist but there are still shortcomings terms...
ABSTRACT Background EUS-guided fine-needle biopsy is the procedure of choice for diagnosis pancreatic ductal adenocarcinoma (PDAC). Nevertheless, samples obtained are small and require expertise in pathology, whereas difficult view scarcity malignant cells important desmoplastic reaction these tumors. With help artificial intelligence, deep learning architectures produce a fast, accurate, automated approach PDAC image segmentation based on whole-slide imaging. Given effectiveness U-Net...
The modeling of multimedia and especially the semantic gap between visual features concepts become an important domain due to quantity digital content, which speedily grows. In this paper, analysis annotation images are studied. development methods for colour image annotations based on learning represents main contribution paper. developed algorithms generate pattern rules that identify high-level concepts. A rule is a combination images' region patterns identifies Our not limited any...