Lightweight Networks for COVID-19 Detection from Chest X-Ray Images inside a Low-Tier Android Device
The efforts to inoculate majority of the population have been slower than expected and this is especially true for lower income countries. This problem has caused a lot of worries and further accentuates the importance of timely and effective mass testing considering the emergence of newer variants....
Saved in:
Main Authors: | , |
---|---|
Format: | text |
Published: |
Archīum Ateneo
2022
|
Subjects: | |
Online Access: | https://archium.ateneo.edu/discs-faculty-pubs/357 https://doi.org/10.1109/TENCON55691.2022.9978124 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Ateneo De Manila University |
id |
ph-ateneo-arc.discs-faculty-pubs-1357 |
---|---|
record_format |
eprints |
spelling |
ph-ateneo-arc.discs-faculty-pubs-13572023-01-26T06:26:31Z Lightweight Networks for COVID-19 Detection from Chest X-Ray Images inside a Low-Tier Android Device Bacad, Dave Jammin A Abu, Patricia Angela R The efforts to inoculate majority of the population have been slower than expected and this is especially true for lower income countries. This problem has caused a lot of worries and further accentuates the importance of timely and effective mass testing considering the emergence of newer variants. The RT-PCR is still the gold standard diagnostic test for COVID-19 detection, but its limitations has led researchers and scientists to explore supplementary screening methods. One effective tool to consider is Chest X-Ray (CXR) imaging and combining it with deep learning has piqued attention from the artificial intelligence (AI) community. To further contribute to this research area, this work focuses on creating, evaluating, and comparing lightweight and mobile-phone-suitable COVID-detecting models. These transfer learning models together with their corresponding dynamic-range quantized versions are first tested according to their classification performance. Afterwards, the models are pushed in a low-tier phone to measure their resource consumption and inference timings. Results show that the utilization of EfficientNetB0 and MobileNetV3 (Small & Large) architectures for transfer learning without any quantization can produce at least 91 % overall average accuracy for 3-class classification scheme. For systems requiring more efficient models, using the quantized versions of the transfer learning models particularly with EfficientNetB0 and MobileNetV3Large as foundation can render at most 0.79 % accuracy loss but still show more than 95% f1-scores for the COVID-19 class. 2022-01-01T08:00:00Z text https://archium.ateneo.edu/discs-faculty-pubs/357 https://doi.org/10.1109/TENCON55691.2022.9978124 Department of Information Systems & Computer Science Faculty Publications Archīum Ateneo Chest X-Ray Imaging COVID-19 Deep Transfer Learning On-Device Machine Learning Quantization Analytical, Diagnostic and Therapeutic Techniques and Equipment Artificial Intelligence and Robotics Computer Sciences Diagnosis Medicine and Health Sciences |
institution |
Ateneo De Manila University |
building |
Ateneo De Manila University Library |
continent |
Asia |
country |
Philippines Philippines |
content_provider |
Ateneo De Manila University Library |
collection |
archium.Ateneo Institutional Repository |
topic |
Chest X-Ray Imaging COVID-19 Deep Transfer Learning On-Device Machine Learning Quantization Analytical, Diagnostic and Therapeutic Techniques and Equipment Artificial Intelligence and Robotics Computer Sciences Diagnosis Medicine and Health Sciences |
spellingShingle |
Chest X-Ray Imaging COVID-19 Deep Transfer Learning On-Device Machine Learning Quantization Analytical, Diagnostic and Therapeutic Techniques and Equipment Artificial Intelligence and Robotics Computer Sciences Diagnosis Medicine and Health Sciences Bacad, Dave Jammin A Abu, Patricia Angela R Lightweight Networks for COVID-19 Detection from Chest X-Ray Images inside a Low-Tier Android Device |
description |
The efforts to inoculate majority of the population have been slower than expected and this is especially true for lower income countries. This problem has caused a lot of worries and further accentuates the importance of timely and effective mass testing considering the emergence of newer variants. The RT-PCR is still the gold standard diagnostic test for COVID-19 detection, but its limitations has led researchers and scientists to explore supplementary screening methods. One effective tool to consider is Chest X-Ray (CXR) imaging and combining it with deep learning has piqued attention from the artificial intelligence (AI) community. To further contribute to this research area, this work focuses on creating, evaluating, and comparing lightweight and mobile-phone-suitable COVID-detecting models. These transfer learning models together with their corresponding dynamic-range quantized versions are first tested according to their classification performance. Afterwards, the models are pushed in a low-tier phone to measure their resource consumption and inference timings. Results show that the utilization of EfficientNetB0 and MobileNetV3 (Small & Large) architectures for transfer learning without any quantization can produce at least 91 % overall average accuracy for 3-class classification scheme. For systems requiring more efficient models, using the quantized versions of the transfer learning models particularly with EfficientNetB0 and MobileNetV3Large as foundation can render at most 0.79 % accuracy loss but still show more than 95% f1-scores for the COVID-19 class. |
format |
text |
author |
Bacad, Dave Jammin A Abu, Patricia Angela R |
author_facet |
Bacad, Dave Jammin A Abu, Patricia Angela R |
author_sort |
Bacad, Dave Jammin A |
title |
Lightweight Networks for COVID-19 Detection from Chest X-Ray Images inside a Low-Tier Android Device |
title_short |
Lightweight Networks for COVID-19 Detection from Chest X-Ray Images inside a Low-Tier Android Device |
title_full |
Lightweight Networks for COVID-19 Detection from Chest X-Ray Images inside a Low-Tier Android Device |
title_fullStr |
Lightweight Networks for COVID-19 Detection from Chest X-Ray Images inside a Low-Tier Android Device |
title_full_unstemmed |
Lightweight Networks for COVID-19 Detection from Chest X-Ray Images inside a Low-Tier Android Device |
title_sort |
lightweight networks for covid-19 detection from chest x-ray images inside a low-tier android device |
publisher |
Archīum Ateneo |
publishDate |
2022 |
url |
https://archium.ateneo.edu/discs-faculty-pubs/357 https://doi.org/10.1109/TENCON55691.2022.9978124 |
_version_ |
1756432702648614912 |