A1 Vertaisarvioitu alkuperäisartikkeli tieteellisessä lehdessä
Comparison of simple augmentation transformations for a convolutional neural network classifying medical images
Tekijät: Rainio Oona, Klen Riku
Kustantaja: Springer Nature
Julkaisuvuosi: 2024
Journal: Signal, Image and Video Processing
Tietokannassa oleva lehden nimi: SIGNAL IMAGE AND VIDEO PROCESSING
Lehden akronyymi: SIGNAL IMAGE VIDEO P
Vuosikerta: 18
Numero: 4
Aloitussivu: 3353
Lopetussivu: 3360
Sivujen määrä: 8
ISSN: 1863-1703
eISSN: 1863-1711
DOI: https://doi.org/10.1007/s11760-024-02998-5
Verkko-osoite: https://link.springer.com/article/10.1007/s11760-024-02998-5
Rinnakkaistallenteen osoite: https://research.utu.fi/converis/portal/detail/Publication/387054079
Simple image augmentation techniques, such as reflection, rotation, or translation, might work differently for medical images than they do for regular photographs due to the fundamental properties of medical imaging techniques and the bilateral symmetry of the human body. Here, we compare the predictions of a convolutional neural network (CNN) trained for binary classification by using either no augmentation or one of seven usual types augmentation. We have 11 different medical data sets, mostly related to lung infections or cancer, with X-rays, ultrasound (US) images, and images from positron emission tomography (PET) and magnetic resonance imaging (MRI). According to our results, the augmentation types do not produce statistically significant differences for US and PET data sets, but, for X-rays and MRI images, the best augmentation technique is adding Gaussian blur to images.
Ladattava julkaisu This is an electronic reprint of the original article. |  |
