Cargando…
Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification
Artificial intelligence (AI) technologies have resulted in remarkable achievements and conferred massive benefits to computer-aided systems in medical imaging. However, the worldwide usage of AI-based automation-assisted cervical cancer screening systems is hindered by computational cost and resourc...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9101629/ https://www.ncbi.nlm.nih.gov/pubmed/35590961 http://dx.doi.org/10.3390/s22093272 |
_version_ | 1784707133533585408 |
---|---|
author | Chen, Wen Shen, Weiming Gao, Liang Li, Xinyu |
author_facet | Chen, Wen Shen, Weiming Gao, Liang Li, Xinyu |
author_sort | Chen, Wen |
collection | PubMed |
description | Artificial intelligence (AI) technologies have resulted in remarkable achievements and conferred massive benefits to computer-aided systems in medical imaging. However, the worldwide usage of AI-based automation-assisted cervical cancer screening systems is hindered by computational cost and resource limitations. Thus, a highly economical and efficient model with enhanced classification ability is much more desirable. This paper proposes a hybrid loss function with label smoothing to improve the distinguishing power of lightweight convolutional neural networks (CNNs) for cervical cell classification. The results strengthen our confidence in hybrid loss-constrained lightweight CNNs, which can achieve satisfactory accuracy with much lower computational cost for the SIPakMeD dataset. In particular, ShufflenetV2 obtained a comparable classification result (96.18% in accuracy, 96.30% in precision, 96.23% in recall, and 99.08% in specificity) with only one-seventh of the memory usage, one-sixth of the number of parameters, and one-fiftieth of total flops compared with Densenet-121 (96.79% in accuracy). GhostNet achieved an improved classification result (96.39% accuracy, 96.42% precision, 96.39% recall, and 99.09% specificity) with one-half of the memory usage, one-quarter of the number of parameters, and one-fiftieth of total flops compared with Densenet-121 (96.79% in accuracy). The proposed lightweight CNNs are likely to lead to an easily-applicable and cost-efficient automation-assisted system for cervical cancer diagnosis and prevention. |
format | Online Article Text |
id | pubmed-9101629 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-91016292022-05-14 Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification Chen, Wen Shen, Weiming Gao, Liang Li, Xinyu Sensors (Basel) Article Artificial intelligence (AI) technologies have resulted in remarkable achievements and conferred massive benefits to computer-aided systems in medical imaging. However, the worldwide usage of AI-based automation-assisted cervical cancer screening systems is hindered by computational cost and resource limitations. Thus, a highly economical and efficient model with enhanced classification ability is much more desirable. This paper proposes a hybrid loss function with label smoothing to improve the distinguishing power of lightweight convolutional neural networks (CNNs) for cervical cell classification. The results strengthen our confidence in hybrid loss-constrained lightweight CNNs, which can achieve satisfactory accuracy with much lower computational cost for the SIPakMeD dataset. In particular, ShufflenetV2 obtained a comparable classification result (96.18% in accuracy, 96.30% in precision, 96.23% in recall, and 99.08% in specificity) with only one-seventh of the memory usage, one-sixth of the number of parameters, and one-fiftieth of total flops compared with Densenet-121 (96.79% in accuracy). GhostNet achieved an improved classification result (96.39% accuracy, 96.42% precision, 96.39% recall, and 99.09% specificity) with one-half of the memory usage, one-quarter of the number of parameters, and one-fiftieth of total flops compared with Densenet-121 (96.79% in accuracy). The proposed lightweight CNNs are likely to lead to an easily-applicable and cost-efficient automation-assisted system for cervical cancer diagnosis and prevention. MDPI 2022-04-24 /pmc/articles/PMC9101629/ /pubmed/35590961 http://dx.doi.org/10.3390/s22093272 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Chen, Wen Shen, Weiming Gao, Liang Li, Xinyu Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification |
title | Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification |
title_full | Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification |
title_fullStr | Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification |
title_full_unstemmed | Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification |
title_short | Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification |
title_sort | hybrid loss-constrained lightweight convolutional neural networks for cervical cell classification |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9101629/ https://www.ncbi.nlm.nih.gov/pubmed/35590961 http://dx.doi.org/10.3390/s22093272 |
work_keys_str_mv | AT chenwen hybridlossconstrainedlightweightconvolutionalneuralnetworksforcervicalcellclassification AT shenweiming hybridlossconstrainedlightweightconvolutionalneuralnetworksforcervicalcellclassification AT gaoliang hybridlossconstrainedlightweightconvolutionalneuralnetworksforcervicalcellclassification AT lixinyu hybridlossconstrainedlightweightconvolutionalneuralnetworksforcervicalcellclassification |