TY - JOUR
T1 - Multiscale Optical Imaging Fusion for Cervical Precancer Diagnosis
T2 - Integrating Widefield Colposcopy and High-Resolution Endomicroscopy
AU - Brenes, David
AU - Salcedo, Mila P.
AU - Coole, Jackson B.
AU - Maker, Yajur
AU - Kortum, Alex
AU - Schwarz, Richard A.
AU - Carns, Jennifer
AU - Vohra, Imran S.
AU - Possati-Resende, Julio C.
AU - Antoniazzi, Marcio
AU - Fonseca, Bruno de Oliveira
AU - Souza, Karen C.Borba
AU - Santana, Iara V.Vidigal
AU - Barbin, Flavia Fazzio
AU - Kreitchmann, Regis
AU - Ramanujam, Nirmala
AU - Schmeler, Kathleen M.
AU - Richards-Kortum, Rebecca
N1 - Publisher Copyright:
Authors
PY - 2024
Y1 - 2024
N2 - Objective: Early detection and treatment of cervical precancers can prevent disease progression. However, in low-resource communities with a high incidence of cervical cancer, high equipment costs and a shortage of specialists hinder preventative strategies. This manuscript presents a low-cost multiscale in vivo optical imaging system coupled with a computer-aided diagnostic system that could enable accurate, real-time diagnosis of high-grade cervical precancers. Methods: The system combines portable colposcopy and high-resolution endomicroscopy (HRME) to acquire spatially registered widefield and microscopy videos. A multiscale imaging fusion network (MSFN) was developed to identify cervical intraepithelial neoplasia grade 2 or more severe (CIN 2+). The MSFN automatically identifies and segments the ectocervix and lesions from colposcopy images, extracts nuclear morphology features from HRME videos, and integrates the colposcopy and HRME information. Results: With a threshold value set to achieve sensitivity equal to clinical impression (0.98 [p = 1.0]), the MSFN achieved a significantly higher specificity than clinical impression (0.75 vs. 0.43, p = 0.000006). Conclusion: Our findings show that multiscale optical imaging of the cervix allows the highly sensitive and specific detection of high-grade precancers. Significance: The multiscale imaging system and MSFN could facilitate the accurate, real-time diagnosis of cervical precancers in low-resource settings.
AB - Objective: Early detection and treatment of cervical precancers can prevent disease progression. However, in low-resource communities with a high incidence of cervical cancer, high equipment costs and a shortage of specialists hinder preventative strategies. This manuscript presents a low-cost multiscale in vivo optical imaging system coupled with a computer-aided diagnostic system that could enable accurate, real-time diagnosis of high-grade cervical precancers. Methods: The system combines portable colposcopy and high-resolution endomicroscopy (HRME) to acquire spatially registered widefield and microscopy videos. A multiscale imaging fusion network (MSFN) was developed to identify cervical intraepithelial neoplasia grade 2 or more severe (CIN 2+). The MSFN automatically identifies and segments the ectocervix and lesions from colposcopy images, extracts nuclear morphology features from HRME videos, and integrates the colposcopy and HRME information. Results: With a threshold value set to achieve sensitivity equal to clinical impression (0.98 [p = 1.0]), the MSFN achieved a significantly higher specificity than clinical impression (0.75 vs. 0.43, p = 0.000006). Conclusion: Our findings show that multiscale optical imaging of the cervix allows the highly sensitive and specific detection of high-grade precancers. Significance: The multiscale imaging system and MSFN could facilitate the accurate, real-time diagnosis of cervical precancers in low-resource settings.
KW - Biopsy
KW - Cervical cancer
KW - cervical cancer
KW - deep learning
KW - Image segmentation
KW - Imaging
KW - Lesions
KW - machine learning
KW - multi-modality fusion
KW - Optical imaging
KW - Optical imaging
KW - Videos
UR - http://www.scopus.com/inward/record.url?scp=85188424707&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85188424707&partnerID=8YFLogxK
U2 - 10.1109/TBME.2024.3379898
DO - 10.1109/TBME.2024.3379898
M3 - Article
C2 - 38507389
AN - SCOPUS:85188424707
SN - 0018-9294
SP - 1
EP - 10
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
ER -