Autor(es):
Kandel, Ibrahem ; Castelli, Mauro ; Popovič, Aleš
Data: 2021
Identificador Persistente: http://hdl.handle.net/10362/121082
Origem: Repositório Institucional da UNL
Projeto/bolsa:
info:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FDS%2F0022%2F2018/PT;
Assunto(s): Convolutional neural networks; Deep learning; Ensemble learning; Image classification; Medical images; Stacking; Transfer learning; Radiology Nuclear Medicine and imaging; Computer Vision and Pattern Recognition; Computer Graphics and Computer-Aided Design; Electrical and Electronic Engineering
Descrição
Kandel, I., Castelli, M., & Popovič, A. (2021). Comparing stacking ensemble techniques to improve musculoskeletal fracture image classification. Journal of Imaging, 7(6), 1-24. [100]. https://doi.org/10.3390/JIMAGING7060100
Bone fractures are among the main reasons for emergency room admittance and require a rapid response from doctors. Bone fractures can be severe and can lead to permanent disability if not treated correctly and rapidly. Using X-ray imaging in the emergency room to detect fractures is a challenging task that requires an experienced radiologist, a specialist who is not always available. The availability of an automatic tool for image classification can provide a second opinion for doctors operating in the emergency room and reduce the error rate in diagnosis. This study aims to increase the existing state-of-the-art convolutional neural networks’ performance by using various ensemble techniques. In this approach, different CNNs (Convolutional Neural Networks) are used to classify the images; rather than choosing the best one, a stacking ensemble provides a more reliable and robust classifier. The ensemble model outperforms the results of individual CNNs by an average of 10%.
