Real-time cervical cancer risk assessment via mobile colposcopy and AI integration

Darwin Castillo Malla; Yuliana Jiménez Gaona; Bernardo José Vega Crespo; Veronique Verhoeven

doi:10.1117/12.3065644

Real-time cervical cancer risk assessment via mobile colposcopy and AI integration

Darwin Castillo Malla (First Author)
, Yuliana Jiménez Gaona
, Bernardo José Vega Crespo
, Veronique Verhoeven (Last Author)

Universidad de Cuenca

Universidad Técnica Particular de Loja
University of Antwerp

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Cervical cancer is one of the most common and dangerous cancers in women, especially in countries with limited resources. In this context, the principal aim of this project is to develop a tool that allows clinicians to screen for cervical cancer through the screening and processing of colposcopy images captured with a smartphone-based colposcope, Cervix app. The mobile application for cervical cancer diagnosis was developed using React Native and Firebase, enabling compatibility with iOS and Android devices. The application features a user-friendly and intuitive interface that facilitates the capture and analysis of colposcopy images. The classification and processing of images (benign and malignant) were conducted using the UNET model for segmentation, GANs for data augmentation, and ResNet models for classification. Several tests were conducted to evaluate the performance of the mobile application to predict and diagnose, ensuring its functionality was accurate and reliable at 90%.

Original language	English
Title of host publication	Applications of Digital Image Processing XLVIII
Subtitle of host publication	At Optical Engineering + Applications
Editors	Andrew G. Tescher, Touradj Ebrahimi
Place of Publication	San Diego, California
Publisher	SPIE
Pages	1-9
Number of pages	9
Volume	13605
ISBN (Electronic)	9781510691186
ISBN (Print)	9781510691186
DOIs	https://doi.org/10.1117/12.3065644
State	Published - 17 Sep 2025
Event	SPIE Optical Enginneering + Applications - San Diego, United States Duration: 3 Aug 2025 → 8 Aug 2025

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	13605
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	SPIE Optical Enginneering + Applications
Abbreviated title	SPIE
Country/Territory	United States
City	San Diego
Period	3/08/25 → 8/08/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

cervical cancer
cervix
deep learning
early detection
healthcare technology
medical image processing
mobile application

Access to Document

10.1117/12.3065644

Cite this

Castillo Malla, D., Jiménez Gaona, Y., Vega Crespo, B. J., & Verhoeven, V. (2025). Real-time cervical cancer risk assessment via mobile colposcopy and AI integration. In A. G. Tescher, & T. Ebrahimi (Eds.), Applications of Digital Image Processing XLVIII: At Optical Engineering + Applications (Vol. 13605, pp. 1-9). Article 1360506 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13605). SPIE. https://doi.org/10.1117/12.3065644

Castillo Malla, Darwin ; Jiménez Gaona, Yuliana ; Vega Crespo, Bernardo José et al. / Real-time cervical cancer risk assessment via mobile colposcopy and AI integration. Applications of Digital Image Processing XLVIII: At Optical Engineering + Applications. editor / Andrew G. Tescher ; Touradj Ebrahimi. Vol. 13605 San Diego, California : SPIE, 2025. pp. 1-9 (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{22fc444521ff4e8fb6d0a3190c3e4d63,

title = "Real-time cervical cancer risk assessment via mobile colposcopy and AI integration",

abstract = "Cervical cancer is one of the most common and dangerous cancers in women, especially in countries with limited resources. In this context, the principal aim of this project is to develop a tool that allows clinicians to screen for cervical cancer through the screening and processing of colposcopy images captured with a smartphone-based colposcope, Cervix app. The mobile application for cervical cancer diagnosis was developed using React Native and Firebase, enabling compatibility with iOS and Android devices. The application features a user-friendly and intuitive interface that facilitates the capture and analysis of colposcopy images. The classification and processing of images (benign and malignant) were conducted using the UNET model for segmentation, GANs for data augmentation, and ResNet models for classification. Several tests were conducted to evaluate the performance of the mobile application to predict and diagnose, ensuring its functionality was accurate and reliable at 90\%. ",

keywords = "Cervical cancer, Mobile application, Deep learning, cervical cancer, cervix, deep learning, early detection, healthcare technology, medical image processing, mobile application",

author = "\{Castillo Malla\}, Darwin and \{Jim{\'e}nez Gaona\}, Yuliana and \{Vega Crespo\}, \{Bernardo Jos{\'e}\} and Veronique Verhoeven",

year = "2025",

month = sep,

day = "17",

doi = "10.1117/12.3065644",

language = "Ingl{\'e}s",

isbn = "9781510691186",

volume = "13605",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

pages = "1--9",

editor = "Tescher, \{Andrew G.\} and Touradj Ebrahimi",

booktitle = "Applications of Digital Image Processing XLVIII",

}

Castillo Malla, D, Jiménez Gaona, Y, Vega Crespo, BJ & Verhoeven, V 2025, Real-time cervical cancer risk assessment via mobile colposcopy and AI integration. in AG Tescher & T Ebrahimi (eds), Applications of Digital Image Processing XLVIII: At Optical Engineering + Applications. vol. 13605, 1360506, Proceedings of SPIE - The International Society for Optical Engineering, vol. 13605, SPIE, San Diego, California, pp. 1-9, SPIE Optical Enginneering + Applications, San Diego, California, United States, 3/08/25. https://doi.org/10.1117/12.3065644

Real-time cervical cancer risk assessment via mobile colposcopy and AI integration. / Castillo Malla, Darwin (First Author); Jiménez Gaona, Yuliana; Vega Crespo, Bernardo José et al.
Applications of Digital Image Processing XLVIII: At Optical Engineering + Applications. ed. / Andrew G. Tescher; Touradj Ebrahimi. Vol. 13605 San Diego, California: SPIE, 2025. p. 1-9 1360506 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13605).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Real-time cervical cancer risk assessment via mobile colposcopy and AI integration

AU - Castillo Malla, Darwin

AU - Jiménez Gaona, Yuliana

AU - Vega Crespo, Bernardo José

AU - Verhoeven, Veronique

PY - 2025/9/17

Y1 - 2025/9/17

N2 - Cervical cancer is one of the most common and dangerous cancers in women, especially in countries with limited resources. In this context, the principal aim of this project is to develop a tool that allows clinicians to screen for cervical cancer through the screening and processing of colposcopy images captured with a smartphone-based colposcope, Cervix app. The mobile application for cervical cancer diagnosis was developed using React Native and Firebase, enabling compatibility with iOS and Android devices. The application features a user-friendly and intuitive interface that facilitates the capture and analysis of colposcopy images. The classification and processing of images (benign and malignant) were conducted using the UNET model for segmentation, GANs for data augmentation, and ResNet models for classification. Several tests were conducted to evaluate the performance of the mobile application to predict and diagnose, ensuring its functionality was accurate and reliable at 90%.

AB - Cervical cancer is one of the most common and dangerous cancers in women, especially in countries with limited resources. In this context, the principal aim of this project is to develop a tool that allows clinicians to screen for cervical cancer through the screening and processing of colposcopy images captured with a smartphone-based colposcope, Cervix app. The mobile application for cervical cancer diagnosis was developed using React Native and Firebase, enabling compatibility with iOS and Android devices. The application features a user-friendly and intuitive interface that facilitates the capture and analysis of colposcopy images. The classification and processing of images (benign and malignant) were conducted using the UNET model for segmentation, GANs for data augmentation, and ResNet models for classification. Several tests were conducted to evaluate the performance of the mobile application to predict and diagnose, ensuring its functionality was accurate and reliable at 90%.

KW - Cervical cancer

KW - Mobile application

KW - Deep learning

KW - cervical cancer

KW - cervix

KW - deep learning

KW - early detection

KW - healthcare technology

KW - medical image processing

KW - mobile application

UR - https://www.scopus.com/pages/publications/105023711466

UR - https://spie.org/Publications/Proceedings/Volume/13605

U2 - 10.1117/12.3065644

DO - 10.1117/12.3065644

M3 - Contribución a la conferencia

SN - 9781510691186

VL - 13605

T3 - Proceedings of SPIE - The International Society for Optical Engineering

SP - 1

EP - 9

BT - Applications of Digital Image Processing XLVIII

A2 - Tescher, Andrew G.

A2 - Ebrahimi, Touradj

PB - SPIE

CY - San Diego, California

T2 - SPIE Optical Enginneering + Applications

Y2 - 3 August 2025 through 8 August 2025

ER -

Castillo Malla D, Jiménez Gaona Y, Vega Crespo BJ, Verhoeven V. Real-time cervical cancer risk assessment via mobile colposcopy and AI integration. In Tescher AG, Ebrahimi T, editors, Applications of Digital Image Processing XLVIII: At Optical Engineering + Applications. Vol. 13605. San Diego, California: SPIE. 2025. p. 1-9. 1360506. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.3065644

Real-time cervical cancer risk assessment via mobile colposcopy and AI integration

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Cite this