A5013765768- Ultrasound in Clinical Applications
- Phonocardiography and Auscultation Techniques
- COVID-19 diagnosis using AI
- Atomic and Subatomic Physics Research
- Radiology practices and education
- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Flow Measurement and Analysis
- Ultrasound and Hyperthermia Applications
- Hate Speech and Cyberbullying Detection
- Internet Traffic Analysis and Secure E-voting
- Artificial Intelligence in Healthcare
- Radiation Dose and Imaging
- Respiratory viral infections research
- Advanced Malware Detection Techniques
- Social Media and Politics
- Digital Radiography and Breast Imaging
- Privacy-Preserving Technologies in Data
- Retinal Imaging and Analysis
- Privacy, Security, and Data Protection
- Spam and Phishing Detection
University of Trento
2022-2024
COMSATS University Islamabad
2022-2024
Augusta University
2024
Boston University
2024
Boston Medical Center
2024
Air University
2023
It is an undeniable fact that people excessively rely on social media for effective communication. However, there no appropriate barrier as to who becomes a part of the Therefore, unknown ruin fundamental purpose communication with irrelevant—and sometimes aggressive—messages. As its popularity increases, impact society also from primarily being positive negative. Cyber aggression negative impact; it defined willful use information technology harm, threaten, slander, defame, or harass...
Automated ultrasound imaging assessment of the effect CoronaVirus disease 2019 (COVID-19) on lungs has been investigated in various studies using artificial intelligence-based (AI) methods. However, an extensive analysis state-of-the-art Convolutional Neural Network-based (CNN) models for frame-level scoring, a comparative aggregation techniques video-level together with thorough evaluation capability these methodologies to provide clinically valuable prognostic-level score is yet missing...
The application of lung ultrasound (LUS) imaging for the diagnosis diseases has recently captured significant interest within research community. With ongoing COVID-19 pandemic, many efforts have been made to evaluate LUS data. A four-level scoring system introduced semiquantitatively assess state lung, classifying patients. Various deep learning (DL) algorithms supported with clinical validations proposed automate stratification process. However, no work done impact on automated decision by...
See also the commentary by Sitek in this issue. Supplemental material is available for article.
Since the outbreak of COVID-19, efforts have been made towards semi-quantitative analysis lung ultrasound (LUS) data to assess patient's condition. Several methods proposed in this regard, with a focus on frame-level analysis, which was then used condition at video and prognostic levels. However, no extensive work has done analyze conditions directly level. This study proposes novel method for video-level scoring based compression LUS into single image automatic classification The utilizes...
Cyberbullying has emerged as a pervasive issue in the digital age, necessitating advanced techniques for effective detection and mitigation. This research explores integration of word embeddings, emotional features, federated learning to address challenges centralized data processing user privacy concerns prevalent previous methods. Word embeddings capture semantic relationships contextual information, enabling more nuanced understanding text data, while features derived from extend analysis...
Pneumonia is the leading cause of death among children around world. According to WHO, a total 740,180 lives under age five were lost due pneumonia in 2019. Lung ultrasound (LUS) has been shown be particularly useful for supporting diagnosis and reducing mortality resource-limited settings. The wide application point-of-care at bedside limited mainly lack training data acquisition interpretation. Artificial Intelligence can serve as potential tool automate improve LUS interpretation process,...
With the outbreak of COVID-19, remote diagnosis, patient monitoring, collection, and transmission data from electronic devices is rapidly taking share in health sector. These are however limited on resources like energy, memory processing power. Consequently, it highly relevant to investigate minimizing data, keeping intact information content. The objective this study thus observe impact pixel, intensity, & temporal resolution automated scoring LUS data. First, 448 videos 20 patients were...
In the last years, efforts have been made towards automating semi-quantitative analysis of lung ultrasound (LUS) data. To this end, several methods proposed with a focus on frame-level classification. However, no extensive work has done to evaluate LUS data directly at video level. This study proposes an effective compression and classification technique for assessing is based maximum, mean, minimum intensity projection (with respect temporal dimension) allows preserving hyper- hypo-echoic...
Hand-held ultrasound devices are emerging as a promising intervention to aid in diagnosing deadly early childhood pneumonia the developing world. Lung (LUS) data, however, can be difficult read and interpret accurately, thus require trained professionals. A variety of deep learning (DL) models have been developed professionals this task, but difficulty curating quality training datasets limits generalization capabilities these models. To combat data scarcity, we utilized DL on LUS collected...
Automated assessment of LUS data from adult population is an ongoing research over the last few years. To this extent, various deep learning DL-based methods have been proposed to assess lung alterations caused by pneumonia. However, no work has done in regard evaluate children for presence/absence consolidations due Pediatric healthcare acquisition a resource constraint environment challenging task. As result which limited acquired. This prevents effective training DL models development...
The emergence of COVID-19 has encouraged researchers to seek a method detect and monitor patients infected with SARS-CoV 2. use lung ultrasound (LUS) in this setting is rapidly spreading because its portability, cost-effectiveness, real-time imaging, safety. LUS demonstrated the potential be widely used assess condition lungs patients. Given frame-level labels provided by pre-trained deep neural network (DNN), our goal identify an aggregation strategy that allows move from video-level, which...
Low-cost and ultra-portable point-of-care ultrasound (POCUS) devices can now be used to aid in diagnosis testing limited resource settings. However, interpretation of data is one the key barriers POCUS adoption implementation. Artificial intelligence potentially address this issue, by reducing impact poor confidence interpretation. Interpreting lung (LUS) mainly includes analysis hyper-echoic horizontal vertical artifacts, hypo-echoic small large consolidations. Our aim design a...
Towards automating semi-quantitative analysis of lung ultrasound (LUS) data, various deep learning-based (DL) classification models have been developed to detect LUS patterns among pneumonia patients. These include horizontal artifacts, vertical and small large consolidations. showed overall promising results, however, did struggle obtain satisfactory performance in classifying all these correctly. In this paper, we propose an ensemble framework which multiple are employed their...
Domain shift refers to change of data distribution between training and testing datasets. In case medical imaging, domain is extensive, specifically for multi-center studies. Different centers may use different scanners, imaging protocols, subject populations, etc. To mitigate this effect, generalization (DG) has been used over the time. regard, our focus analyze if a pre-trained model can generalize lung ultrasound (LUS) pattern classification among pneumonia patients. Furthermore, LUS from...
With the outbreak of COVID-19 pandemic, remote diagnosis, patient monitoring, collection, and transmission health data from electronic devices are rapidly taking its share in sector. These are, however, limited on resources like energy, memory, processing power. Consequently, it is highly relevant to investigate how minimize size data, keeping intact information content. The objective this study to, thus, observe impact pixel resolution automated scoring by DL algorithms for LUS videos....