The computer-aided analysis is poised to play an increasingly prominent role in medicine and healthcare. Benefiting from the increasing computing power, various machine learning frameworks have been developed in the biomedical field, bringing significant improvements in real-world clinical applications. However, for many diseases, the development of these life-supporting algorithms is still in its infancy. To bridge this gap: This thesis is dedicated to the development of efficient algorithms for better image intervention and addressing data quality challenges in machine learning algorithms to provide direct guidance for real-world clinical applications. With the above goals, three topics are explored in depth. First, we develop a novel tissue analysis framework for cardiac substrate identification and tissue heterogeneity assessment. In particular, we creatively used model uncertainty to measure tissue structure information, offering a means of extracting the tissue heterogeneity information in a non-invasive way for real-time imaging and processing. The tissue analysis framework in the first aim is based on the fully supervised technique, which relies heavily on the availability of large-scale datasets with accurate annotations. Such high-quality datasets are extremely time-consuming to acquire, especially for biomedical segmentation tasks. To lessen the need for the labeling process, we further develop three weakly supervised learning frameworks to address data and labeling challenges caused by limited data resources. Finally, we develop an in-vivo tissue analysis framework on cardiac datasets, aiming to provide real-time guidance for clinical ablation procedures. Our models could contribute to the improvement of ablation treatment by identifying the ablation targets and avoiding critical structures within the hearts.

The current study is an empirical study of preference for campus open space around the drill field on Mississippi State University (MSU) campus. 83 students at Mississippi State University were selected as research objects. Based on the literature review, a research process was designed to employ VEP, content analysis and multivariate analysis---Biplot to explore the interested research problems. The study identified two most preferred landscape scene types - "Legibility" and "Coherence" using Kaplan?s "information processing model". A statistical analysis tool for multivariate analysis-Biplot was used to reveal the landscape preference patterns for campus open space as well as how certain landscape features can contribute these patterns. The study found factors such as gender, educational and cultural background can heavily affect these patterns. The result indicated that "vegetations" including tree, seasonal flowers and open grassland, were the most preferred landscape feature on campus open space. Finally, the limitations of this study were discussed and some recommendations for future landscape preference study were provided.

Bakgrund: Livslängden i världen ökar kontinuerligt och även den äldre populationen. Covid-19 pandemin innebar stor påverkan på samhället och restriktioner, bland annat social isolering, infördes för att begränsa smittspridningen. Dessa restriktioner riktades främst mot riskgrupper vilket innebar begränsningar i deras livsstil. Teorin känslan av sammanhang kan användas inom vården för att belysa vikten av sammanhang hos äldre och hur det påverkar välbefinnandet.Syfte: Att belysa hur äldre personer i enskilt boende upplevde den sociala isoleringen under covid-19 pandemin.  Metod: En kvalitativ litteraturöversikt genomfördes med induktiv ansats. Totalt 10 kvalitetsgranskade artiklar analyserades enligt Fribergs fem steg.Resultat: Det framkom två övergripande kategorier ”påverkan av emotionellt mående” med underkategorierna ”rädsla att insjukna”, ”isolering”, ”ekonomiska oro” och ”tankar om framtiden” samt ”socialt nätverks betydelse” med underkategorierna ”förändring av platsen i samhället”, ”påverkan av sociala interaktioner”, ”teknologins betydelse” och ”inverkan på vården”.Slutsats: Deltagarna upplevde bristande sociala kontakter, ensamhet, stigmatisering, problematik med teknik och rädsla för att drabbas av sjukdom vilket lett till minskat välbefinnande. Det framkom också att äldre besitter hög personlig styrka för att hantera motgångar vilket bidragit till att de till och med kunnat ta med sig något gott från den social isoleringen. / Background: Life expectancy and the elderly population in the world is increasing. The covid-19 pandemic had a major impact on society and restrictions, including social isolation, were established to limit the spread of infection. The theory sense of coherence can be used within the care of elderly to improve their wellbeing.Aim: To shed light on how community-dwelling older persons experienced the social isolation during the covid-19 pandemic.Method: A qualitative literature review with inductive approach was made. 10 articles were analyzed using Friberg's five steps.Results: Two overarching categories emerged: "impact of emotional well-being" with subcategories: "fear of become ill", "isolation", "financial worries" and "thoughts about the future" and "social networks importance" with subcategories: "change of place in society", "impact of social interactions”, “importance of technology” and “impact on care”.Conclusion: The participants experienced a lack of social contacts, loneliness, stigmatization, problems with technology and fear of illness which led to reduced well-being. It also emerged that the elderly possesses high personal strength to deal with setbacks, which contributed them to be able to take some benefits from the social isolation.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.