Imatge de la portada

Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification

Guardat en:
Publicat a:Machine Learning and Knowledge Extraction vol. 7, no. 1 (2025), p. 1
Autor principal: Xinyu (Freddie) Liu
Altres autors: Karagoz, Gizem, Meratnia, Nirvana
Publicat:
MDPI AG
Matèries:
Machine learning
Datasets
Data augmentation
Performance enhancement
Image analysis
Deep learning
Investigations
Artificial intelligence
Computer vision
Neural networks
Decision making
Medical imaging
Classification
Impact analysis
Image classification
Quantitative analysis
Trust
Coherence
Accés en línia:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
Resum:Deep learning models are widely used for medical image analysis and require large datasets, while sufficient high-quality medical data for training are scarce. Data augmentation has been used to improve the performance of these models. The lack of transparency of complex deep-learning models raises ethical and judicial concerns inducing a lack of trust by both medical experts and patients. In this paper, we focus on evaluating the impact of different data augmentation methods on the explainability of deep learning models used for medical image classification. We investigated the performance of different traditional, mixing-based, and search-based data augmentation techniques with DenseNet121 trained on chest X-ray datasets. We evaluated how the explainability of the model through correctness and coherence can be impacted by these data augmentation techniques. Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) methods were used. Sanity checks and overlapping scores were applied to confirm the correctness and coherence of explainability. The results indicate that both LIME and SHAP passed the sanity check regardless of the type of data augmentation method used. Overall, TrivialAugment performs the best on completeness and coherence. Flipping + cropping performs better on coherence using LIME. Generally, the overlapping scores for SHAP were lower than those for LIME, indicating that LIME has a better performance in terms of coherence.
ISSN:2504-4990
DOI:10.3390/make7010001
Font:Advanced Technologies & Aerospace Database