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

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinyu (Freddie) Liu, Gizem Karagoz, Nirvana Meratnia
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Machine Learning and Knowledge Extraction
Subjects:
Online Access:https://www.mdpi.com/2504-4990/7/1/1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204452437360640
author Xinyu (Freddie) Liu
Gizem Karagoz
Nirvana Meratnia
author_facet Xinyu (Freddie) Liu
Gizem Karagoz
Nirvana Meratnia
author_sort Xinyu (Freddie) Liu
collection DOAJ
description 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.
format Article
id doaj-art-b5a1ea5e2dab4f9e942125bfd3c93a18
institution OA Journals
issn 2504-4990
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Machine Learning and Knowledge Extraction
spelling doaj-art-b5a1ea5e2dab4f9e942125bfd3c93a182025-08-20T02:11:17ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902024-12-0171110.3390/make7010001Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image ClassificationXinyu (Freddie) Liu0Gizem Karagoz1Nirvana Meratnia2Department of Mathematics and Computer Science, Eindhoven University of Technology, 5612 AZ Eindhoven, The NetherlandsDepartment of Mathematics and Computer Science, Eindhoven University of Technology, 5612 AZ Eindhoven, The NetherlandsDepartment of Mathematics and Computer Science, Eindhoven University of Technology, 5612 AZ Eindhoven, The NetherlandsDeep 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.https://www.mdpi.com/2504-4990/7/1/1explainable AImedical image analysisdata augmentation
spellingShingle Xinyu (Freddie) Liu
Gizem Karagoz
Nirvana Meratnia
Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification
Machine Learning and Knowledge Extraction
explainable AI
medical image analysis
data augmentation
title Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification
title_full Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification
title_fullStr Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification
title_full_unstemmed Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification
title_short Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification
title_sort analyzing the impact of data augmentation on the explainability of deep learning based medical image classification
topic explainable AI
medical image analysis
data augmentation
url https://www.mdpi.com/2504-4990/7/1/1
work_keys_str_mv AT xinyufreddieliu analyzingtheimpactofdataaugmentationontheexplainabilityofdeeplearningbasedmedicalimageclassification
AT gizemkaragoz analyzingtheimpactofdataaugmentationontheexplainabilityofdeeplearningbasedmedicalimageclassification
AT nirvanameratnia analyzingtheimpactofdataaugmentationontheexplainabilityofdeeplearningbasedmedicalimageclassification