DSpace Collection: LIM/13 - Laboratório de Genética e Cardiologia Molecular
https://observatorio.fm.usp.br/handle/OPI/3648
LIM/13 - Laboratório de Genética e Cardiologia Molecular2024-03-28T14:51:49ZDEEP LEARNING BASED UV FACIAL IMAGING GENERATION
https://observatorio.fm.usp.br/handle/OPI/57150
Title: DEEP LEARNING BASED UV FACIAL IMAGING GENERATION
Authors: MARGALEF, Pablo Toledo; NAVARRO, Pablo; HUNEMEIER, Tabita; PEREIRA, Alexandre C.; GONZALEZ-JOSE, Rolando; DELRIEUX, Claudio
Abstract: Skin health has become a topic of interest in the recent years. To ensure a better diagnosis and treatment, the analysis of high-quality skin databases is crucial. In this regard, UV imaging is a valuable tool in detecting melanoma and other skin conditions. However, UV images present some challenges both in availability and processing. For this reason, in this work we present UVnet, a method to generate opticalto-UV facial images based on autoencoder architectures. The proposed UVnet is validated across an extension of the Baependi Heart Study and other state of the art method [1]. Our proposal successfully generates pseudo-UV samples with an average RMSE of 0.0040 and a structural similarity index against the actual samples of 0.2984. These results show that UVnet consistently achieves higher sample quality than existing methods and provides new capabilities regarding generation of large areas of the facial epidermis. This can be regarded as an initial effort to provide affordable access to high-quality skin databases.2023-01-01T00:00:00ZCARDIORENAL DYSFUNCTION IN MICE SUBMITTED TO AORTIC STENOSIS AND TREATED WITH SODIUM OXALATE
https://observatorio.fm.usp.br/handle/OPI/57116
Title: CARDIORENAL DYSFUNCTION IN MICE SUBMITTED TO AORTIC STENOSIS AND TREATED WITH SODIUM OXALATE
Authors: SILVA, Amanda; MARQUES, Juliana; NASCIMENTO, Bruno; SOUZA, Leandro; SILVA, Maikon; BENETTI, Acaris; IRIGOYEN, Maria Claudia2023-01-01T00:00:00ZRAPID PROGRESSION OF CORONARY ATHEROSCLEROSIS IN A PATIENT WITH AUTOSSOMAL RECESSIVE HYPERCHOLESTEROLEMIA
https://observatorio.fm.usp.br/handle/OPI/56997
Title: RAPID PROGRESSION OF CORONARY ATHEROSCLEROSIS IN A PATIENT WITH AUTOSSOMAL RECESSIVE HYPERCHOLESTEROLEMIA
Authors: MIZUTA, Marjorie Hayashida; AMORIM, Matheus; ROCHA, Viviane Zorzanelli; MINAME, Marcio Hiroshi; JANNES, Cinthia Elim; PEREIRA, Alexandre Costa; KRIEGER, Jose Eduardo; SANTOS, Raul; CHACRA, Ana Paula Marte2023-01-01T00:00:00ZCardioBERTpt: Transformer-based Models for Cardiology Language Representation in Portuguese
https://observatorio.fm.usp.br/handle/OPI/56999
Title: CardioBERTpt: Transformer-based Models for Cardiology Language Representation in Portuguese
Authors: SCHNEIDER, Elisa Terumi Rubel; GUMIEL, Yohan Bonescki; SOUZA, Joao Vitor Andrioli de; MUKAI, Lilian Mie; OLIVEIRA, Lucas Emanuel Silva e; REBELO, Marina de Sa; GUTIERREZ, Marco Antonio; KRIEGER, Jose Eduardo; TEODORO, Douglas; MORO, Claudia; PARAISO, Emerson Cabrera
Abstract: Contextual word embeddings and the Transformers architecture have reached state-of-the-art results in many natural language processing (NLP) tasks and improved the adaptation of models for multiple domains. Despite the improvement in the reuse and construction of models, few resources are still developed for the Portuguese language, especially in the health domain. Furthermore, the clinical models available for the language are not representative enough for all medical specialties. This work explores deep contextual embedding models for the Portuguese language to support clinical NLP tasks. We transferred learned information from electronic health records of a Brazilian tertiary hospital specialized in cardiology diseases and pre-trained multiple clinical BERT-based models. We evaluated the performance of these models in named entity recognition experiments, fine-tuning them in two annotated corpora containing clinical narratives. Our pre-trained models outperformed previous multilingual and Portuguese BERT-based models for cardiology and multi-specialty environments, reaching the state-of-the-art for analyzed corpora, with 5.5% F1 score improvement in TempClinBr (all entities) and 1.7% in SemClinBr (Disorder entity) corpora. Hence, we demonstrate that data representativeness and a high volume of training data can improve the results for clinical tasks, aligned with results for other languages.2023-01-01T00:00:00Z