Repository logo

Escola Superior de Tecnologia e Gestão

Permanent URI for this community

http://hdl.handle.net/10198/5

Browse

Browsing Escola Superior de Tecnologia e Gestão by Field of Science and Technology (FOS) "Ciências Médicas::Medicina Clínica"

Now showing 1 - 3 of 3
  • Colorectal Polyp Segmentation: Impact of Combining Different Datasets on Deep Learning Model Performance
    Publication . Araujo, Sandro Luis de; Scheeren, Michel Hanzen; Aguiar, Rubens Miguel Gomes; Mendes, Eduardo; Franco, Ricardo Augusto Pereira; Paula Filho, Pedro Luiz de
    Colorectal cancer is a major health concern, ranking as one of the most common and deadly forms of cancer. It typically begins as polyps, which are abnormal growths in the intestinal mucosa. Identifying and removing these polyps through colonoscopy is a crucial preventative measure. However, even experienced professionals can overlook some polyps during examinations. In this context, segmentation algorithms can assist medical professionals by identifying areas in an image that correspond to a polyp. These algorithms, which rely on deep learning, require extensive image datasets to effectively learn how to identify and segment polyps. This study aimed to identify public colonoscopy image datasets that contain polyps and to examine how combining these datasets might affect the performance of a deep learning-based segmentation algorithm. After selecting the datasets and defining their combinations, we trained a segmentation algorithm on each combination. The evaluation of the trained models showed that merging datasets can enhance model generalization, with increases of up to 0.242 in the dice coefficient and 0.256 in the Intersection over Union (IoU). These improvements could lead to higher diagnostic accuracy in clinical settings, enhancing efforts to prevent colorectal cancer.
    2024Conference paper Restricted access Show more
  • Portable system and user interface for ECG and EMG acquisition, conditioning, and parameters extraction
    Publication . Luiz, Luiz E.; Silva, Wilson J. da; Soares, Salviano; Leitão, Paulo; Teixeira, João Paulo
    Electrical signals from the human body are constantly the focus of research, searching for a better understanding of physiological events, discovering early signs of disease, and improving life quality. Developing devices that allow research beyond the usual requirements and allow easy adaptation regarding the system's acquisition, conditioning, and processing parts could be a step toward better understanding some behaviours. Therefore, this work focused on designing a system that goes from the discrete components to a graphical interface, allowing user control of parameters to set the acquisition in a way that favours the specific signal of interest. The resulting system allows the user to change parameters regarding the analogue and digital filtering, sampling frequency and events detection, namely R-peaks, in the electrocardiogram, to estimate heart rate and its frequency fluctuation, and muscle contraction in electromyogram, to analyse contraction strength and muscle fatigue. The system also allows the data to be stored, aiming to generate datasets to further process the data in AI-based algorithms.
    2025Conference paper Open access Show more
  • Solubility enhancement of antimalarial drugs through eutectic formation
    Publication . Araújo, Nathalie Ladares de; Martins, Mónia A. R.; Pinho, Simão; Ferreira, Olga; Lima, Mirela Vanin dos Santos
    2025Master thesis Embargoed access Show more