TY - GEN
T1 - Measuring the Impact of Data Augmentation Techniques in Lung Radiograph Classification Using a Fractional Factorial Design
T2 - 2022 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2022
AU - Davila, Mateo Hidalgo
AU - Jose Murillo, Juan
AU - Calisto, Maria Baldeon
AU - Puente-Mejia, Bernardo
AU - Navarrete, Danny
AU - Riofrio, Daniel
AU - Perez, Noel
AU - Benitez, Diego
AU - Moyano, Ricardo Flores
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Convolutional neural networks (CNNs) have become dominant in various computer vision tasks, obtaining state-of-the-art results in medical image analysis. Nevertheless, CNNs require large datasets to achieve high performance, which might not always be available in medical settings. Hence, different data augmentation strategies have been proposed to synthetically increase the size and diversity of a dataset. According to the state of the art, the relationship between data augmentation operations and the classification accuracy of a neural network has not been fully explored. In this work, the effect that basic augmentation techniques have in the detection of COVID-19 on chest X-Ray images is analyzed using a 2(7-1) fractional factorial experimental design. The experimental results show that zoom in and height shift operations have a significant positive effect on the accuracy, while horizontal flip operation hinders the performance. Moreover, by applying a cube plot analysis, the data augmentation operations and values that maximize the accuracy of the CNN are found. A 97% accuracy, 93% precision, and 97.7% recall scores are attained on a publicly available COVID-19 dataset using these data augmentation operations.
AB - Convolutional neural networks (CNNs) have become dominant in various computer vision tasks, obtaining state-of-the-art results in medical image analysis. Nevertheless, CNNs require large datasets to achieve high performance, which might not always be available in medical settings. Hence, different data augmentation strategies have been proposed to synthetically increase the size and diversity of a dataset. According to the state of the art, the relationship between data augmentation operations and the classification accuracy of a neural network has not been fully explored. In this work, the effect that basic augmentation techniques have in the detection of COVID-19 on chest X-Ray images is analyzed using a 2(7-1) fractional factorial experimental design. The experimental results show that zoom in and height shift operations have a significant positive effect on the accuracy, while horizontal flip operation hinders the performance. Moreover, by applying a cube plot analysis, the data augmentation operations and values that maximize the accuracy of the CNN are found. A 97% accuracy, 93% precision, and 97.7% recall scores are attained on a publicly available COVID-19 dataset using these data augmentation operations.
KW - COVID-19 Detection
KW - Convolutional Neural Networks
KW - Design of Experiments
KW - Fractional Factorial Design
KW - Image Data Augmentation
KW - Medical Image Classification
UR - https://www.scopus.com/pages/publications/85141388589
U2 - 10.1109/ColCACI56938.2022.9905303
DO - 10.1109/ColCACI56938.2022.9905303
M3 - Contribución a la conferencia
AN - SCOPUS:85141388589
T3 - 2022 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2022 - Proceedings
BT - 2022 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2022 - Proceedings
A2 - Orjuela-Canon, Alvaro David
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 27 July 2022 through 29 July 2022
ER -