TY - JOUR
T1 - Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy
AU - Agustiansyah, Patiyus
AU - Nurmaini, Siti
AU - Nuranna, Laila
AU - Irfannuddin, Irfannuddin
AU - Sanif, Rizal
AU - Legiran, Legiran
AU - Rachmatullah, Muhammad Naufal
AU - Florina, Gavira Olipa
AU - Sapitri, Ade Iriani
AU - Darmawahyuni, Annisa
N1 - Funding Information:
This work was supported by a National Competitive Basic Research Grant from the Ministry of Education, Culture, Research, and Technology, Indonesia, no. 142/E5/PG.02.00.PT/2022 and the Faculty of Medicine, Universitas Sriwijaya, Indonesia.
Publisher Copyright:
© 2022 by the authors.
PY - 2022/8
Y1 - 2022/8
N2 - 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.
AB - 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.
KW - acetowhite lesions
KW - columnar area
KW - instance segmentation
KW - squamocolumnar junction
KW - visual inspection of acetic acid
UR - http://www.scopus.com/inward/record.url?scp=85135371861&partnerID=8YFLogxK
U2 - 10.3390/s22155489
DO - 10.3390/s22155489
M3 - Article
C2 - 35897993
AN - SCOPUS:85135371861
SN - 1424-8220
VL - 22
JO - Sensors
JF - Sensors
IS - 15
M1 - 5489
ER -