LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications

This study presents a comprehensive analysis of utilizing TensorFlow Lite on mobile phones for the on-edge medical diagnosis of lung diseases. This paper focuses on the technical deployment of various deep learning architectures to classify nine respiratory system diseases using X-ray imagery. We pr...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Aldamani, Raghad (author)
مؤلفون آخرون: Abuhani, Diaa Addeen (author), Shanableh, Tamer (author)
التنسيق: article
منشور في: 2024
الموضوعات:
الوصول للمادة أونلاين:https://hdl.handle.net/11073/25544
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513432400691200
author Aldamani, Raghad
author2 Abuhani, Diaa Addeen
Shanableh, Tamer
author2_role author
author
author_facet Aldamani, Raghad
Abuhani, Diaa Addeen
Shanableh, Tamer
author_role author
dc.creator.none.fl_str_mv Aldamani, Raghad
Abuhani, Diaa Addeen
Shanableh, Tamer
dc.date.none.fl_str_mv 2024-07-01T05:34:10Z
2024-07-01T05:34:10Z
2024
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Aldamani, R.; Abuhani, D.A.; Shanableh, T. LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications. Algorithms 2024, 17, 280. https://doi.org/10.3390/a17070280
1999-4893
https://hdl.handle.net/11073/25544
10.3390/a17070280
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv MDPI
dc.relation.none.fl_str_mv https://doi.org/10.3390/a17070280
dc.subject.none.fl_str_mv Medical diagnosis
CNN image classification
Model quantization
On-edge image classification
dc.title.none.fl_str_mv LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description This study presents a comprehensive analysis of utilizing TensorFlow Lite on mobile phones for the on-edge medical diagnosis of lung diseases. This paper focuses on the technical deployment of various deep learning architectures to classify nine respiratory system diseases using X-ray imagery. We propose a simple deep learning architecture that experiments with six different convolutional neural networks. Various quantization techniques are employed to convert the classification models into TensorFlow Lite, including post-classification quantization with floating point 16 bit representation, integer quantization with representative data, and quantization-aware training. This results in a total of 18 models suitable for on-edge deployment for the classification of lung diseases. We then examine the generated models in terms of model size reduction, accuracy, and inference time. Our findings indicate that the quantization-aware training approach demonstrates superior optimization results, achieving an average model size reduction of 75.59%. Among many CNNs, MobileNetV2 exhibited the highest performance-to-size ratio, with an average accuracy loss of 4.1% across all models using the quantization-aware training approach. In terms of inference time, TensorFlow Lite with integer quantization emerged as the most efficient technique, with an average improvement of 1.4 s over other conversion approaches. Our best model, which used EfficientNetB2, achieved an F1-Score of approximately 98.58%, surpassing state-of-the-art performance on the X-ray lung diseases dataset in terms of accuracy, specificity, and sensitivity. The model experienced an F1 loss of around 1% using quantization-aware optimization. The study culminated in the development of a consumer-ready app, with TensorFlow Lite models tailored to mobile devices.
format article
id aus_f10d772b9c997f722d339b6b8ca64798
identifier_str_mv Aldamani, R.; Abuhani, D.A.; Shanableh, T. LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications. Algorithms 2024, 17, 280. https://doi.org/10.3390/a17070280
1999-4893
10.3390/a17070280
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/25544
publishDate 2024
publisher.none.fl_str_mv MDPI
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling LungVision: X-ray Imagery Classification for On-Edge Diagnosis ApplicationsAldamani, RaghadAbuhani, Diaa AddeenShanableh, TamerMedical diagnosisCNN image classificationModel quantizationOn-edge image classificationThis study presents a comprehensive analysis of utilizing TensorFlow Lite on mobile phones for the on-edge medical diagnosis of lung diseases. This paper focuses on the technical deployment of various deep learning architectures to classify nine respiratory system diseases using X-ray imagery. We propose a simple deep learning architecture that experiments with six different convolutional neural networks. Various quantization techniques are employed to convert the classification models into TensorFlow Lite, including post-classification quantization with floating point 16 bit representation, integer quantization with representative data, and quantization-aware training. This results in a total of 18 models suitable for on-edge deployment for the classification of lung diseases. We then examine the generated models in terms of model size reduction, accuracy, and inference time. Our findings indicate that the quantization-aware training approach demonstrates superior optimization results, achieving an average model size reduction of 75.59%. Among many CNNs, MobileNetV2 exhibited the highest performance-to-size ratio, with an average accuracy loss of 4.1% across all models using the quantization-aware training approach. In terms of inference time, TensorFlow Lite with integer quantization emerged as the most efficient technique, with an average improvement of 1.4 s over other conversion approaches. Our best model, which used EfficientNetB2, achieved an F1-Score of approximately 98.58%, surpassing state-of-the-art performance on the X-ray lung diseases dataset in terms of accuracy, specificity, and sensitivity. The model experienced an F1 loss of around 1% using quantization-aware optimization. The study culminated in the development of a consumer-ready app, with TensorFlow Lite models tailored to mobile devices.MDPI2024-07-01T05:34:10Z2024-07-01T05:34:10Z2024Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfAldamani, R.; Abuhani, D.A.; Shanableh, T. LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications. Algorithms 2024, 17, 280. https://doi.org/10.3390/a170702801999-4893https://hdl.handle.net/11073/2554410.3390/a17070280en_UShttps://doi.org/10.3390/a17070280oai:repository.aus.edu:11073/255442024-08-22T12:07:10Z
spellingShingle LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications
Aldamani, Raghad
Medical diagnosis
CNN image classification
Model quantization
On-edge image classification
status_str publishedVersion
title LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications
title_full LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications
title_fullStr LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications
title_full_unstemmed LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications
title_short LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications
title_sort LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications
topic Medical diagnosis
CNN image classification
Model quantization
On-edge image classification
url https://hdl.handle.net/11073/25544