Uso de la inteligencia artificial en el diagnóstico de alteraciones de la citología cervicouterina: estudio observacional en población universitaria.

Saved in:

Bibliographic Details
Title:	Uso de la inteligencia artificial en el diagnóstico de alteraciones de la citología cervicouterina: estudio observacional en población universitaria.
Alternate Title:	Use of artificial intelligence in the diagnosis of alterations in cervical cytology: A university population-based observational study.
Authors:	Said Manzano-Chaya, José¹, Mendoza-Herrera, Tania¹, García-Ayala, Ernesto¹
Source:	Biomédica: Revista del Instituto Nacional de Salud. 2025 Special Issue, Vol. 45, p24-36. 13p.
Subjects:	ARTIFICIAL intelligence, PAP test, DIAGNOSIS, EARLY detection of cancer, UNIVERSITY research, DEEP learning, SENSITIVITY & specificity (Statistics)
Geographic Terms:	COLOMBIA
Abstract (English):	Introduction. Conventional cervical cytology (Pap smear) remains a primary method for cervical cancer screening in Colombia, despite limitations in diagnostic yield and heavy workload. The potential of artificial intelligence to address these challenges is yet to be evaluated in our population. Objective. To evaluate and compare the discriminative ability of four artificial intelligencebased models for the detection of abnormalities in Pap smears. Materials and methods. A total of 650 images of Pap smear cells were obtained from a university cohort in northeastern Colombia. These images were subjected to diagnostic evaluation by an expert pathologist. Four artificial intelligence models (DenseNet, InceptionV3, MobileNet, and VGG19) were trained using data from a publicly available Pap smear database with digital image analysis and deep learning. The discriminative ability of the models was determined by calculating their sensitivity, specificity, and area under the curve. Results. MobileNet showed the highest discriminative ability (AUC = 0.97), with a specificity of 0.99 and sensitivity of 0.78 for the detection of altered cells in Pap smears. On the other hand, InceptionV3 had the best performance capabilities for screening, with a sensitivity of 0.93, specificity of 0.82, and AUC of 0.947. Conclusions. The results of this study illustrate the advantages and disadvantages of different artificial intelligence models and how their application could help improve the diagnostic performance of manual reading in cervical cancer screening or even serve as a primary screening method to rule out negative cases, by achieving a diagnostic performance comparable to that of manual reading. [ABSTRACT FROM AUTHOR]
Abstract (Spanish):	Introducción. La citología convencional (prueba de Papanicolaou) continúa siendo un pilar del tamizaje del cáncer cervicouterino en Colombia, pero su utilidad se ve opacada por una gran carga laboral y bajo rendimiento diagnóstico. El uso de la inteligencia artificial puede proveer una solución a este problema, sin embargo, no hay estudios que evalúen su utilidad en nuestra población. Objetivo. Evaluar y comparar la capacidad discriminativa de cuatro modelos de inteligencia artificial para detectar anormalidades en la citología cervicouterina. Materiales y métodos. Se obtuvieron 650 imágenes de células de citología cervicouterina convencional de una población universitaria del nororiente colombiano, las cuales fueron sometidas a evaluación diagnóstica por un patólogo experto. Mediante el análisis de imágenes digitales y aprendizaje profundo, se entrenaron cuatro modelos de inteligencia artificial (DenseNet, InceptionV3, MobileNet y VGG19) con los datos de una base de citología de acceso público, determinando la capacidad discriminativa de los modelos con su respectiva sensibilidad, especificidad y área bajo la curva. Resultados. MobileNet tuvo la mejor capacidad discriminativa [área bajo la curva (AUC) de 0,97) con una especificidad del 0,99 y sensibilidad de 0,78 para la detección de alteraciones en la citología cervicouterina. Por otro lado, InceptionV3 tuvo un mejor desempeño en el tamizaje, con sensibilidad del 0,93, especificidad de 0,82 y área bajo la curva de 0,947. Conclusiones. Nuestros resultados ilustran las ventajas y desventajas de diferentes modelos de inteligencia artificial y la forma como podrían ayudar a mejorar el rendimiento del tamizaje con citología convencional o, incluso, servir como método de tamizaje primario para descartar los casos negativos, lográndose un desempeño diagnóstico comparable con el de la lectura convencional. [ABSTRACT FROM AUTHOR]
	Copyright of Biomédica: Revista del Instituto Nacional de Salud is the property of Instituto Nacional de Salud of Colombia and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	MedicLatina

Description
Abstract:	Introduction. Conventional cervical cytology (Pap smear) remains a primary method for cervical cancer screening in Colombia, despite limitations in diagnostic yield and heavy workload. The potential of artificial intelligence to address these challenges is yet to be evaluated in our population. Objective. To evaluate and compare the discriminative ability of four artificial intelligencebased models for the detection of abnormalities in Pap smears. Materials and methods. A total of 650 images of Pap smear cells were obtained from a university cohort in northeastern Colombia. These images were subjected to diagnostic evaluation by an expert pathologist. Four artificial intelligence models (DenseNet, InceptionV3, MobileNet, and VGG19) were trained using data from a publicly available Pap smear database with digital image analysis and deep learning. The discriminative ability of the models was determined by calculating their sensitivity, specificity, and area under the curve. Results. MobileNet showed the highest discriminative ability (AUC = 0.97), with a specificity of 0.99 and sensitivity of 0.78 for the detection of altered cells in Pap smears. On the other hand, InceptionV3 had the best performance capabilities for screening, with a sensitivity of 0.93, specificity of 0.82, and AUC of 0.947. Conclusions. The results of this study illustrate the advantages and disadvantages of different artificial intelligence models and how their application could help improve the diagnostic performance of manual reading in cervical cancer screening or even serve as a primary screening method to rule out negative cases, by achieving a diagnostic performance comparable to that of manual reading. [ABSTRACT FROM AUTHOR]
ISSN:	01204157
DOI:	10.7705/biomedica.7651