A5037516343- COVID-19 diagnosis using AI
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Artificial Intelligence in Healthcare and Education
- Advanced X-ray and CT Imaging
- Health Sciences Research and Education
- Health Policy Implementation Science
- Medical Imaging Techniques and Applications
- Radiology practices and education
- Medical Imaging and Analysis
- Clinical Reasoning and Diagnostic Skills
- Privacy-Preserving Technologies in Data
Polytechnic University of Timişoara
2020-2023
The following topics are dealt with: data analysis; learning (artificial intelligence); unsupervised learning; feature extraction; pattern clustering; diseases; educational institutions; convolutional neural nets; and health care.
Lung nodule detection remains one of the most common and painstaking tasks in radiology. Efforts to aid overworked radiologists are made using artificial intelligence (AI), although computed tomography (CT) makes it a hard computational task practical scenarios. This study analyses translation weight-averaging ensemble technique, from natural image classification small object on CT. A dataset 1050 patients is used fine-tune models under diverse configurations compare different types...
Classification and object detection are computer vision tasks with successful, clinical applications in medical imaging. Yet, the increased effort required of expert readers order to annotate bounding boxes on images has yet be quantitatively justified terms added value identifying pathologies. In this study, we show preliminary results classification localization 17 most common chest pathologies a private dataset 15,000 radiographs from two Romanian public hospitals. Next, compare extra box...
Chest x-rays are a widely used diagnostic imaging technique in the medical field, but expert interpretation can be time-consuming and subjective, leading to potential errors. To overcome these limitations, computer-aided (CAD) systems using artificial intelligence (AI) have been developed, with transformer-based object detectors showing promising results. This study explores rib fracture detection power of an out-of-the-box transformer detector examines its adaptability imaging. A private...
Lung nodule segmentation on computed tomography (CT) is at the same time one of most common and laborious tasks in oncological radiology. Fortunately, artificial intelligence agents have been showing promising results streamlining process. We study some challenges training an AI model for lung segmentation, including degradation performance due to distribution shift, privacy concerns limited bandwidth cloud data transmission. The article explores different federated learning strategies, over...
Medical imaging plays a critical role in patient diagnosis, with CT scans being an essential modality that provides fine-grained, 3-dimensional insight into patients' bodies. The large amount of information generated by can lead to long interpretation times and increased errors, particularly when compounded radiologist fatigue. One solution is the use Computer Aided Diagnostic (CAD) tools, which studies have shown improve accuracy reduce diagnosis time used radiologists. However, CAD tools...
Computer-aided-diagnosis (CAD) systems have become an important utensil in today's radiologist's toolbox. The new age of computer vision transformers could further increase their value, although domain-specific limitations and adaptations should be studied first. Here we show that with the adoption set prediction paradigm transformer-based object detection, Hungarian loss' applicability to medical imaging benefit from specialized modifications. A dataset 50,000 chest radiographs was used...