Classification of Computed Tomography Images with Pleural Effusion Disease Using Convolutional Neural Networks

David Benavente, Gustavo Gatica, Ivan Derpich

Resultado de la investigación: Contribución a los tipos de informe/libroContribución a la conferenciarevisión exhaustiva

Resumen

On the present work we use two different convolutional neural nets architectures for the classification of computed tomography images with pleural effusion disease. We decided to use the convolutional neural networks due to the great advances achieved by this kind of nets in image classification problems. We work with a real-world data anonymized and provided by an Imagenology Department of public hospital from Chile. The data was classified by medics of the hospital. Due to the limitations on graphics resource, we decided training the algorithms from scratch, avoiding overfitting with regularization techniques and optimizing the training process programming callbacks. For testing, we used a set of 1,000 images and evaluate with classification metrics like True positive rate, True negative rate and Accuracy. Results achieved were not optimal due to overfitting of algorithms. For future works, we will use other architectures of convolutional neural networks and with Transfer learning technique on the architectures.

Idioma originalInglés
Título de la publicación alojadaIntelligent Systems and Applications - Proceedings of the 2021 Intelligent Systems Conference, IntelliSys
EditoresKohei Arai
EditorialSpringer Science and Business Media Deutschland GmbH
Páginas559-565
Número de páginas7
ISBN (versión impresa)9783030821982
DOI
EstadoPublicada - 2022
Evento Intelligent Systems Conference, IntelliSys 2021 - Virtual, Online
Duración: 1 sep 20212 sep 2021

Serie de la publicación

NombreLecture Notes in Networks and Systems
Volumen296
ISSN (versión impresa)2367-3370
ISSN (versión digital)2367-3389

Conferencia

Conferencia Intelligent Systems Conference, IntelliSys 2021
CiudadVirtual, Online
Período1/09/212/09/21

Áreas temáticas de ASJC Scopus

  • Ingeniería de control y sistemas
  • Procesamiento de senales
  • Redes de ordenadores y comunicaciones

Huella

Profundice en los temas de investigación de 'Classification of Computed Tomography Images with Pleural Effusion Disease Using Convolutional Neural Networks'. En conjunto forman una huella única.

Citar esto