Deep learning and explainable machine learning on hair disease detection
Deep learning algorithms have been widely used for various healthcare research because it helps eliminate the need for manual feature extraction which requires specialist expertise and is time-consuming. However, deep learning models have low interpretability in their classification results and henc...
Saved in:
Main Authors: | , |
---|---|
Format: | Conference or Workshop Item |
Published: |
2023
|
Subjects: | |
Online Access: | http://eprints.utm.my/107664/ http://dx.doi.org/10.1109/ECBIOS57802.2023.10218472 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Teknologi Malaysia |
id |
my.utm.107664 |
---|---|
record_format |
eprints |
spelling |
my.utm.1076642024-09-25T07:45:56Z http://eprints.utm.my/107664/ Deep learning and explainable machine learning on hair disease detection Heng, Wei Wei Abdul-Kadir, N. A. TK Electrical engineering. Electronics Nuclear engineering Deep learning algorithms have been widely used for various healthcare research because it helps eliminate the need for manual feature extraction which requires specialist expertise and is time-consuming. However, deep learning models have low interpretability in their classification results and hence low trust and practical usage in clinical settings. To overcome this reliability issue, explainable machine learning (XAI) can be used to understand the effect of the different networks and the extracted features on the classification results. In this study, multiple convolutional neural networks were trained and tested on hairy scalp images for the detection of hair diseases. In addition to standard performance metrics including accuracy, sensitivity, and specificity, we further investigated the models' interpretability using three XAI techniques including Local Interpretable Model-Agnostic Explanations, Gradient-weighted Class Activation Mapping, and occlusion sensitivity. The result of using XAI techniques revealed that the model's high classification accuracy did not necessarily coincide with its applicability or practicality. The application of XAI techniques in this study provided valuable insights into the contributions made by different groups of pixels to the model's decision-making process. This method helped identify potential model biases, which could then be utilized to facilitate informed adjustments for the improvement of the model's robustness. 2023 Conference or Workshop Item PeerReviewed Heng, Wei Wei and Abdul-Kadir, N. A. (2023) Deep learning and explainable machine learning on hair disease detection. In: 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS), 2 June 2023-4 June 2023, Tainan, Taiwan. http://dx.doi.org/10.1109/ECBIOS57802.2023.10218472 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Heng, Wei Wei Abdul-Kadir, N. A. Deep learning and explainable machine learning on hair disease detection |
description |
Deep learning algorithms have been widely used for various healthcare research because it helps eliminate the need for manual feature extraction which requires specialist expertise and is time-consuming. However, deep learning models have low interpretability in their classification results and hence low trust and practical usage in clinical settings. To overcome this reliability issue, explainable machine learning (XAI) can be used to understand the effect of the different networks and the extracted features on the classification results. In this study, multiple convolutional neural networks were trained and tested on hairy scalp images for the detection of hair diseases. In addition to standard performance metrics including accuracy, sensitivity, and specificity, we further investigated the models' interpretability using three XAI techniques including Local Interpretable Model-Agnostic Explanations, Gradient-weighted Class Activation Mapping, and occlusion sensitivity. The result of using XAI techniques revealed that the model's high classification accuracy did not necessarily coincide with its applicability or practicality. The application of XAI techniques in this study provided valuable insights into the contributions made by different groups of pixels to the model's decision-making process. This method helped identify potential model biases, which could then be utilized to facilitate informed adjustments for the improvement of the model's robustness. |
format |
Conference or Workshop Item |
author |
Heng, Wei Wei Abdul-Kadir, N. A. |
author_facet |
Heng, Wei Wei Abdul-Kadir, N. A. |
author_sort |
Heng, Wei Wei |
title |
Deep learning and explainable machine learning on hair disease detection |
title_short |
Deep learning and explainable machine learning on hair disease detection |
title_full |
Deep learning and explainable machine learning on hair disease detection |
title_fullStr |
Deep learning and explainable machine learning on hair disease detection |
title_full_unstemmed |
Deep learning and explainable machine learning on hair disease detection |
title_sort |
deep learning and explainable machine learning on hair disease detection |
publishDate |
2023 |
url |
http://eprints.utm.my/107664/ http://dx.doi.org/10.1109/ECBIOS57802.2023.10218472 |
_version_ |
1811681242246021120 |