Authors:
Nina Hosseini-Kivanani
1
;
Inês Oliveira
1
;
Sena Kilinç
2
and
Luis Leiva
1
Affiliations:
1
Department of Computer Science, University of Luxembourg, Esch-sur-Alzette, Luxembourg
;
2
Faculty of Science and Engineering, Sorbonne Universite, Paris, France
Keyword(s):
Drawing, Handwriting, Cognitive Impairments, Data Augmentation, Neural Networks.
Abstract:
We investigate the effectiveness of learnable and non-learnable automatic data augmentation (AutoDA) techniques in enhancing Deep Learning (DL) models for classifying Clock Drawing Test (CDT) images used in cognitive dysfunction screening. The classification is between healthy controls (HCs) and individuals with mild cognitive impairment (MCI). Specifically, we evaluate TrivialAugment (TA) and UniformAugment (UA), adapted for clinical image classification to address data scarcity and class imbalance. Our experiments across three public datasets demonstrate significant improvements in model performance and generalization. Notably, TA increased classification accuracy by up to 15 points, while UA achieved a 12-point improvement. These techniques offer a computationally efficient alternative to learnable methods like RandAugment (RA), which we also compare against, delivering comparable (and sometimes better) results with a much lower computational overhead. Our findings indicate that A
utoDA techniques, particularly TA and UA, can be effectively applied in clinical settings, providing robust tools for the early detection of cognitive disorders, including Alzheimer’s disease and dementia.
(More)