Cargando…

Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy

Precancerous screening using visual inspection with acetic acid (VIA) is suggested by the World Health Organization (WHO) for low–middle-income countries (LMICs). However, because of the limited number of gynecological oncologist clinicians in LMICs, VIA screening is primarily performed by general c...

Descripción completa

Detalles Bibliográficos
Autores principales: Agustiansyah, Patiyus, Nurmaini, Siti, Nuranna, Laila, Irfannuddin, Irfannuddin, Sanif, Rizal, Legiran, Legiran, Rachmatullah, Muhammad Naufal, Florina, Gavira Olipa, Sapitri, Ade Iriani, Darmawahyuni, Annisa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9332449/
https://www.ncbi.nlm.nih.gov/pubmed/35897993
http://dx.doi.org/10.3390/s22155489
_version_ 1784758649775718400
author Agustiansyah, Patiyus
Nurmaini, Siti
Nuranna, Laila
Irfannuddin, Irfannuddin
Sanif, Rizal
Legiran, Legiran
Rachmatullah, Muhammad Naufal
Florina, Gavira Olipa
Sapitri, Ade Iriani
Darmawahyuni, Annisa
author_facet Agustiansyah, Patiyus
Nurmaini, Siti
Nuranna, Laila
Irfannuddin, Irfannuddin
Sanif, Rizal
Legiran, Legiran
Rachmatullah, Muhammad Naufal
Florina, Gavira Olipa
Sapitri, Ade Iriani
Darmawahyuni, Annisa
author_sort Agustiansyah, Patiyus
collection PubMed
description Precancerous screening using visual inspection with acetic acid (VIA) is suggested by the World Health Organization (WHO) for low–middle-income countries (LMICs). However, because of the limited number of gynecological oncologist clinicians in LMICs, VIA screening is primarily performed by general clinicians, nurses, or midwives (called medical workers). However, not being able to recognize the significant pathophysiology of human papilloma virus (HPV) infection in terms of the columnar epithelial-cell, squamous epithelial-cell, and white-spot regions with abnormal blood vessels may be further aggravated by VIA screening, which achieves a wide range of sensitivity (49–98%) and specificity (75–91%); this might lead to a false result and high interobserver variances. Hence, the automated detection of the columnar area (CA), subepithelial region of the squamocolumnar junction (SCJ), and acetowhite (AW) lesions is needed to support an accurate diagnosis. This study proposes a mask-RCNN architecture to simultaneously segment, classify, and detect CA and AW lesions. We conducted several experiments using 262 images of VIA+ cervicograms, and 222 images of VIA−cervicograms. The proposed model provided a satisfactory intersection over union performance for the CA of about 63.60%, and AW lesions of about 73.98%. The dice similarity coefficient performance was about 75.67% for the CA and about 80.49% for the AW lesion. It also performed well in cervical-cancer precursor-lesion detection, with a mean average precision of about 86.90% for the CA and of about 100% for the AW lesion, while also achieving 100% sensitivity and 92% specificity. Our proposed model with the instance segmentation approach can segment, detect, and classify cervical-cancer precursor lesions with satisfying performance only from a VIA cervicogram.
format Online
Article
Text
id pubmed-9332449
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93324492022-07-29 Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy Agustiansyah, Patiyus Nurmaini, Siti Nuranna, Laila Irfannuddin, Irfannuddin Sanif, Rizal Legiran, Legiran Rachmatullah, Muhammad Naufal Florina, Gavira Olipa Sapitri, Ade Iriani Darmawahyuni, Annisa Sensors (Basel) Article Precancerous screening using visual inspection with acetic acid (VIA) is suggested by the World Health Organization (WHO) for low–middle-income countries (LMICs). However, because of the limited number of gynecological oncologist clinicians in LMICs, VIA screening is primarily performed by general clinicians, nurses, or midwives (called medical workers). However, not being able to recognize the significant pathophysiology of human papilloma virus (HPV) infection in terms of the columnar epithelial-cell, squamous epithelial-cell, and white-spot regions with abnormal blood vessels may be further aggravated by VIA screening, which achieves a wide range of sensitivity (49–98%) and specificity (75–91%); this might lead to a false result and high interobserver variances. Hence, the automated detection of the columnar area (CA), subepithelial region of the squamocolumnar junction (SCJ), and acetowhite (AW) lesions is needed to support an accurate diagnosis. This study proposes a mask-RCNN architecture to simultaneously segment, classify, and detect CA and AW lesions. We conducted several experiments using 262 images of VIA+ cervicograms, and 222 images of VIA−cervicograms. The proposed model provided a satisfactory intersection over union performance for the CA of about 63.60%, and AW lesions of about 73.98%. The dice similarity coefficient performance was about 75.67% for the CA and about 80.49% for the AW lesion. It also performed well in cervical-cancer precursor-lesion detection, with a mean average precision of about 86.90% for the CA and of about 100% for the AW lesion, while also achieving 100% sensitivity and 92% specificity. Our proposed model with the instance segmentation approach can segment, detect, and classify cervical-cancer precursor lesions with satisfying performance only from a VIA cervicogram. MDPI 2022-07-22 /pmc/articles/PMC9332449/ /pubmed/35897993 http://dx.doi.org/10.3390/s22155489 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
Agustiansyah, Patiyus
Nurmaini, Siti
Nuranna, Laila
Irfannuddin, Irfannuddin
Sanif, Rizal
Legiran, Legiran
Rachmatullah, Muhammad Naufal
Florina, Gavira Olipa
Sapitri, Ade Iriani
Darmawahyuni, Annisa
Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy
title Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy
title_full Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy
title_fullStr Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy
title_full_unstemmed Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy
title_short Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy
title_sort automated precancerous lesion screening using an instance segmentation technique for improving accuracy
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9332449/
https://www.ncbi.nlm.nih.gov/pubmed/35897993
http://dx.doi.org/10.3390/s22155489
work_keys_str_mv AT agustiansyahpatiyus automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy
AT nurmainisiti automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy
AT nurannalaila automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy
AT irfannuddinirfannuddin automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy
AT sanifrizal automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy
AT legiranlegiran automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy
AT rachmatullahmuhammadnaufal automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy
AT florinagaviraolipa automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy
AT sapitriadeiriani automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy
AT darmawahyuniannisa automatedprecancerouslesionscreeningusinganinstancesegmentationtechniqueforimprovingaccuracy