Towards the Mobile Detection of Cervical Lesions: A Region-Based Approach for the Analysis of Microscopic Images
Given the current prevalence and impact of cervical cancer worldwide, many technological developments focused on automating the screening process have arisen recently. Nonetheless, there is still a clear need for affordable, portable and automated IoT-based solutions to expand the coverage of curren...
Guardado en:
Autores principales: | , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
IEEE
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/715fa823829840afbdd566281d3dd336 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:715fa823829840afbdd566281d3dd336 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:715fa823829840afbdd566281d3dd3362021-11-20T00:02:29ZTowards the Mobile Detection of Cervical Lesions: A Region-Based Approach for the Analysis of Microscopic Images2169-353610.1109/ACCESS.2021.3126486https://doaj.org/article/715fa823829840afbdd566281d3dd3362021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9606873/https://doaj.org/toc/2169-3536Given the current prevalence and impact of cervical cancer worldwide, many technological developments focused on automating the screening process have arisen recently. Nonetheless, there is still a clear need for affordable, portable and automated IoT-based solutions to expand the coverage of current cervical screening programs worldwide. This is particularly relevant for lower-resource countries, which account for 88% of all cervical cancer-related deaths. This work proposes a low-cost, smartphone-based microscopy device for the analysis of liquid-based cytology samples, through autonomous image acquisition and automated identification of cervical lesions. Different deep learning models for object detection were separately optimised and compared to select the most adequate network architecture. Transfer learning from a similar application domain - conventional cytology - was also investigated as a way of improving the robustness of the analysis pipeline, as well as overcoming the limitations of the mobile-acquired image dataset specifically collected and manually annotated by specialists under the scope of this work. In this process, a detection performance benchmark in the SIPAKMED dataset - test mean average precision (mAP) of 0.37798 and average recall (AR) of 0.63651 - was reported for the first time. Although further improvements are required for its integration in a computer-aided diagnosis system sufficiently reliable for deployment in a clinical context, the explored approach exhibits promising results (cross-validation mAP of 0.20315, AR of 0.46572 and analysis time of 4 minutes per cytological sample), corresponding to a step forward in the development of a cost-effective mobile IoT framework that supports cervical lesion screening.Ana Filipa SampaioLuis RosadoMaria Joao M. VasconcelosIEEEarticleArtificial intelligencecomputer aided diagnosisdeep learningInternet of Thingsknowledge transfermicroscopyElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152188-152205 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Artificial intelligence computer aided diagnosis deep learning Internet of Things knowledge transfer microscopy Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
spellingShingle |
Artificial intelligence computer aided diagnosis deep learning Internet of Things knowledge transfer microscopy Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ana Filipa Sampaio Luis Rosado Maria Joao M. Vasconcelos Towards the Mobile Detection of Cervical Lesions: A Region-Based Approach for the Analysis of Microscopic Images |
description |
Given the current prevalence and impact of cervical cancer worldwide, many technological developments focused on automating the screening process have arisen recently. Nonetheless, there is still a clear need for affordable, portable and automated IoT-based solutions to expand the coverage of current cervical screening programs worldwide. This is particularly relevant for lower-resource countries, which account for 88% of all cervical cancer-related deaths. This work proposes a low-cost, smartphone-based microscopy device for the analysis of liquid-based cytology samples, through autonomous image acquisition and automated identification of cervical lesions. Different deep learning models for object detection were separately optimised and compared to select the most adequate network architecture. Transfer learning from a similar application domain - conventional cytology - was also investigated as a way of improving the robustness of the analysis pipeline, as well as overcoming the limitations of the mobile-acquired image dataset specifically collected and manually annotated by specialists under the scope of this work. In this process, a detection performance benchmark in the SIPAKMED dataset - test mean average precision (mAP) of 0.37798 and average recall (AR) of 0.63651 - was reported for the first time. Although further improvements are required for its integration in a computer-aided diagnosis system sufficiently reliable for deployment in a clinical context, the explored approach exhibits promising results (cross-validation mAP of 0.20315, AR of 0.46572 and analysis time of 4 minutes per cytological sample), corresponding to a step forward in the development of a cost-effective mobile IoT framework that supports cervical lesion screening. |
format |
article |
author |
Ana Filipa Sampaio Luis Rosado Maria Joao M. Vasconcelos |
author_facet |
Ana Filipa Sampaio Luis Rosado Maria Joao M. Vasconcelos |
author_sort |
Ana Filipa Sampaio |
title |
Towards the Mobile Detection of Cervical Lesions: A Region-Based Approach for the Analysis of Microscopic Images |
title_short |
Towards the Mobile Detection of Cervical Lesions: A Region-Based Approach for the Analysis of Microscopic Images |
title_full |
Towards the Mobile Detection of Cervical Lesions: A Region-Based Approach for the Analysis of Microscopic Images |
title_fullStr |
Towards the Mobile Detection of Cervical Lesions: A Region-Based Approach for the Analysis of Microscopic Images |
title_full_unstemmed |
Towards the Mobile Detection of Cervical Lesions: A Region-Based Approach for the Analysis of Microscopic Images |
title_sort |
towards the mobile detection of cervical lesions: a region-based approach for the analysis of microscopic images |
publisher |
IEEE |
publishDate |
2021 |
url |
https://doaj.org/article/715fa823829840afbdd566281d3dd336 |
work_keys_str_mv |
AT anafilipasampaio towardsthemobiledetectionofcervicallesionsaregionbasedapproachfortheanalysisofmicroscopicimages AT luisrosado towardsthemobiledetectionofcervicallesionsaregionbasedapproachfortheanalysisofmicroscopicimages AT mariajoaomvasconcelos towardsthemobiledetectionofcervicallesionsaregionbasedapproachfortheanalysisofmicroscopicimages |
_version_ |
1718419840142671872 |