Artificial Intelligence-Based Decision Support Models for COVID-19 Detection
Guardado en:
| Publicado en: | PQDT - Global (2024) |
|---|---|
| Autor principal: | |
| Publicado: |
ProQuest Dissertations & Theses
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text - PDF |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3168218521 | ||
| 003 | UK-CbPIL | ||
| 020 | |a 9798304926744 | ||
| 035 | |a 3168218521 | ||
| 045 | 2 | |b d20240101 |b d20241231 | |
| 084 | |a 189128 |2 nlm | ||
| 100 | 1 | |a de Vasconcelos Cardoso Pereira, Sofia Perestrelo | |
| 245 | 1 | |a Artificial Intelligence-Based Decision Support Models for COVID-19 Detection | |
| 260 | |b ProQuest Dissertations & Theses |c 2024 | ||
| 513 | |a Dissertation/Thesis | ||
| 520 | 3 | |a The integration of artificial intelligence into medical imaging can enhance diagnostic practices by improving accuracy and efficiency. In thoracic radiology, automated systems assist doctors in interpreting complex imaging data and identifying patterns indicative of lung diseases, aiding in their diagnosis, stratification, and prognosis. The COVID-19 pandemic has highlighted the importance of such technologies, presenting both challenges and opportunities. This thesis explores the development and application of artificial intelligence-based decision support models for detecting and managing lung diseases, with an emphasis on COVID-19. It explores methodologies to enhance the interpretation of thoracic imaging, including diagnostic accuracy, lesion quantification, bias mitigation, and disease monitoring. The results herein presented include enhancements through multi-scale approaches that address variations in lung abnormality sizes, alongside techniques developed to mitigate projection bias for consistently accurate diagnostics across different imaging projections. The thesis also highlights the effectiveness of distribution-based detection methods in identifying COVID-19 outbreaks, leveraging statistical distributions to differentiate it from other types of pneumonia, as well as approaches for the quantification of COVID-19-related lung lesions that offer valuable insights into the extent of lung damage. Finally, recognizing the labor-intensive and time-consuming nature of manual image annotation, this work reviews techniques for the automatic extraction of image labels from radiology reports, emphasizing the role of natural language processing in medical image analysis workflows. This work aims to contribute to medical artificial intelligence research by comprehensively analyzing various proposed methodologies, ultimately improving healthcare outcomes. The findings underscore the potential of automated systems to meet current demands and advance medical diagnostics, emphasizing the importance of artificial intelligence in transforming healthcare. | |
| 653 | |a Pneumonia | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Radiology | ||
| 653 | |a Neural networks | ||
| 653 | |a Chronic illnesses | ||
| 653 | |a Lung diseases | ||
| 653 | |a Natural language processing | ||
| 653 | |a Medical imaging | ||
| 653 | |a Chronic obstructive pulmonary disease | ||
| 653 | |a Lungs | ||
| 653 | |a COVID-19 | ||
| 653 | |a Biomedical engineering | ||
| 773 | 0 | |t PQDT - Global |g (2024) | |
| 786 | 0 | |d ProQuest |t ProQuest Dissertations & Theses Global | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3168218521/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3168218521/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |