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

Guardat en:
Dades bibliogràfiques
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:
Accés en línia:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3181640315
003 UK-CbPIL
022 |a 2504-4990 
024 7 |a 10.3390/make7010001  |2 doi 
035 |a 3181640315 
045 2 |b d20250101  |b d20250331 
100 1 |a Xinyu (Freddie) Liu 
245 1 |a Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a 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. 
653 |a Machine learning 
653 |a Datasets 
653 |a Data augmentation 
653 |a Performance enhancement 
653 |a Image analysis 
653 |a Deep learning 
653 |a Investigations 
653 |a Artificial intelligence 
653 |a Computer vision 
653 |a Neural networks 
653 |a Decision making 
653 |a Medical imaging 
653 |a Classification 
653 |a Impact analysis 
653 |a Image classification 
653 |a Quantitative analysis 
653 |a Trust 
653 |a Coherence 
700 1 |a Karagoz, Gizem 
700 1 |a Meratnia, Nirvana 
773 0 |t Machine Learning and Knowledge Extraction  |g vol. 7, no. 1 (2025), p. 1 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3181640315/abstract/embedded/H09TXR3UUZB2ISDL?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3181640315/fulltextwithgraphics/embedded/H09TXR3UUZB2ISDL?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3181640315/fulltextPDF/embedded/H09TXR3UUZB2ISDL?source=fedsrch