Staff View: A Grad-CAM-based knowledge distillation method for the detection of tuberculosis

A Grad-CAM-based knowledge distillation method for the detection of tuberculosis

Automatic screening for tuberculosis (TB) from X-ray images using artificial intelligence techniques has attracted the attention of researchers in the fields of computing and medicine. However, existing models are computationally intensive and require high computer hardware, which limits the use of...

Full description

Saved in:

Bibliographic Details
Main Authors:	Ding, Zeyu, Yaakob, Razali, Azman, Azreen, Mohd Rum, Siti Nurulain, Zakaria, Norfadhlina, Ahmad Nazri, Azree Shahril
Format:	Conference or Workshop Item
Published:	IEEE 2023
Online Access:	http://psasir.upm.edu.my/id/eprint/37619/ https://ieeexplore.ieee.org/document/10145170
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.upm.eprints.37619
record_format	eprints
spelling	my.upm.eprints.376192023-09-28T05:02:53Z http://psasir.upm.edu.my/id/eprint/37619/ A Grad-CAM-based knowledge distillation method for the detection of tuberculosis Ding, Zeyu Yaakob, Razali Azman, Azreen Mohd Rum, Siti Nurulain Zakaria, Norfadhlina Ahmad Nazri, Azree Shahril Automatic screening for tuberculosis (TB) from X-ray images using artificial intelligence techniques has attracted the attention of researchers in the fields of computing and medicine. However, existing models are computationally intensive and require high computer hardware, which limits the use of people in areas where medical resources are scarce. Another problem with the existing model is poor interpretability. The model only provides the final result and lacks intuitive information about the location of the lesion. To solve these problems, this paper proposes a Grad-CAM-based knowledge distillation method for the detection of TB. Firstly, this study used Unet to extract the lung region, avoiding the influence of regions outside the lung on the detection results. Subsequently, five models (Densenet121, Inception V3, Resnet18, Mobilenet V3, VGG16) are applied to TB detection, and the attention maps of each model are visualized using Grad-CAM. These attention maps are applied to knowledge distillation to finally obtain a lightweight interpretable TB detection model. This model achieves 91.2% and 85.7% accuracy on Shenzhen and Montgomery datasets, which verifies the effectiveness of the model. IEEE 2023 Conference or Workshop Item PeerReviewed Ding, Zeyu and Yaakob, Razali and Azman, Azreen and Mohd Rum, Siti Nurulain and Zakaria, Norfadhlina and Ahmad Nazri, Azree Shahril (2023) A Grad-CAM-based knowledge distillation method for the detection of tuberculosis. In: 2023 9th International Conference on Information Management (ICIM 2023), 17-19 Mar. 2023, Oxford, United Kingdom. (pp. 72-77). https://ieeexplore.ieee.org/document/10145170 10.1109/ICIM58774.2023.00019
institution	Universiti Putra Malaysia
building	UPM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Putra Malaysia
content_source	UPM Institutional Repository
url_provider	http://psasir.upm.edu.my/
description	Automatic screening for tuberculosis (TB) from X-ray images using artificial intelligence techniques has attracted the attention of researchers in the fields of computing and medicine. However, existing models are computationally intensive and require high computer hardware, which limits the use of people in areas where medical resources are scarce. Another problem with the existing model is poor interpretability. The model only provides the final result and lacks intuitive information about the location of the lesion. To solve these problems, this paper proposes a Grad-CAM-based knowledge distillation method for the detection of TB. Firstly, this study used Unet to extract the lung region, avoiding the influence of regions outside the lung on the detection results. Subsequently, five models (Densenet121, Inception V3, Resnet18, Mobilenet V3, VGG16) are applied to TB detection, and the attention maps of each model are visualized using Grad-CAM. These attention maps are applied to knowledge distillation to finally obtain a lightweight interpretable TB detection model. This model achieves 91.2% and 85.7% accuracy on Shenzhen and Montgomery datasets, which verifies the effectiveness of the model.
format	Conference or Workshop Item
author	Ding, Zeyu Yaakob, Razali Azman, Azreen Mohd Rum, Siti Nurulain Zakaria, Norfadhlina Ahmad Nazri, Azree Shahril
spellingShingle	Ding, Zeyu Yaakob, Razali Azman, Azreen Mohd Rum, Siti Nurulain Zakaria, Norfadhlina Ahmad Nazri, Azree Shahril A Grad-CAM-based knowledge distillation method for the detection of tuberculosis
author_facet	Ding, Zeyu Yaakob, Razali Azman, Azreen Mohd Rum, Siti Nurulain Zakaria, Norfadhlina Ahmad Nazri, Azree Shahril
author_sort	Ding, Zeyu
title	A Grad-CAM-based knowledge distillation method for the detection of tuberculosis
title_short	A Grad-CAM-based knowledge distillation method for the detection of tuberculosis
title_full	A Grad-CAM-based knowledge distillation method for the detection of tuberculosis
title_fullStr	A Grad-CAM-based knowledge distillation method for the detection of tuberculosis
title_full_unstemmed	A Grad-CAM-based knowledge distillation method for the detection of tuberculosis
title_sort	grad-cam-based knowledge distillation method for the detection of tuberculosis
publisher	IEEE
publishDate	2023
url	http://psasir.upm.edu.my/id/eprint/37619/ https://ieeexplore.ieee.org/document/10145170
_version_	1781706632304001024
score	13.211869

A Grad-CAM-based knowledge distillation method for the detection of tuberculosis

Similar Items