Tesis y Trabajos de Investigación PUCP

URI permanente para esta comunidadhttp://54.81.141.168/handle/123456789/6

El Repositorio Digital de Tesis y Trabajos de Investigación PUCP aporta al Repositorio Institucional con todos sus registros, organizados por grado: Doctorado, Maestría, Licenciatura y Bachillerato. Se actualiza permanentemente con las nuevas tesis y trabajos de investigación sustentados y autorizados, así como también con los que que fueron sustentados años atrás.
Ingresa a su web: Repositorio Digital de Tesis y Trabajos de Investigación PUCP

Explorar

Filtros

20241

Ajustes

Autorsearch.filters.applied.operator.equals: search.filters.author.Romero Gutierrez, Stefano EnriqueFecha de inicio: 2020

Resultados de búsqueda

Mostrando 1 - 1 de 1
  • No hay miniatura disponible
    ÍtemTexto completo enlazado
    Advances in artificial intelligence applied to ultrasound imaging
    (Pontificia Universidad Católica del Perú, 2024-05-28) Romero Gutierrez, Stefano Enrique; Castañeda Aphan, Benjamin
    Ultrasound imaging in rural areas often faces challenges due to the scarcity of skilled radiologists or sonographers. This research explores enhancing ultrasound imaging focused in resource-scarce settings via external anatomical landmarks for asynchronous ultrasound acquisition using artificial intelligence (AI) and computer vision algorithms based on the nature of the acquisition. First, it addresses lung ultrasound health status by generating one single image by sweeping the transducer in a sagittal position along the chest. The validation was performed using normal and abnormal cases. Second, a multi-camera system for ultrasound probe tracking with AI is proposed. The results were evaluated by quantitative measurements of speeds, angles, and simulation of lung VSI protocol. Third, a 3D segmentation of breast tumors using ultrasound videos acquired by asynchronous protocols was realized. A representative frame of the videos is extracted to analyze the nature and determine if is a benign or malignant case. Fourth, a set of obstetric data acquired by asynchronous protocols for the assessment of fetal head presentation and placenta position was realized. Fetal biometry such as head circumference and biparietal diameter were calculated and compared with physician measurements. Finally, an elastography approach was tested for plantar soft tissue assessment by a test-retest experiment for biomechanical characterization. An automatic calcaneus segmentation was employed in the B-mode as an aid in the visualization and for an immediate region of interest selection. The results were compared with the manual selection of the region of interest and the respective calcaneus segmentation. The findings of this work demonstrate a substantial advancement in the field of ultrasound imaging, especially tailored for resource-limited settings.