EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial Intelligence and Colposcopy: Automatic Identification of Cervical Squamous Cell Carcinoma Precursors

Miguel Mascarenhas iD, Inês Alencoão, Maria João Carinhas, Miguel Martins iD, Pedro Cardoso iD, Francisco Mendes iD, Joana Fernandes iD, João Ferreira, Guilherme Macedo iD, Rosa Zulmira Macedo

Journal of Clinical Medicine · 20.05.2024 · 13 (10) · 3003

DOI: 10.3390/jcm13103003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 20.05.2024. Verfasst von Miguel Mascarenhas und 9 weiteren Autor:innen. Beteiligte Einrichtung: Precision Medicine Unit, Department of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427 Porto, Portugal. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Proficient colposcopy is crucial for the adequate management of cervical cancer precursor lesions; nonetheless its limitations may impact its cost-effectiveness. The development of artificial intelligence models is experiencing an exponential growth, particularly in image-based specialties. The aim of this study is to develop and validate a Convolutional Neural Network (CNN) for the automatic differentiation of high-grade (HSIL) from low-grade dysplasia (LSIL) in colposcopy.

Methods

A unicentric retrospective study was conducted based on 70 colposcopy exams, comprising a total of 22,693 frames. Among these, 8729 were categorized as HSIL based on histopathology. The total dataset was divided into a training (90%, n = 20,423) and a testing set (10%, n = 2270), the latter being used to evaluate the model’s performance. The main outcome measures included sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and the area under the receiving operating curve (AUC-ROC).

Results

The sensitivity was 99.7% and the specificity was 98.6%. The PPV and NPV were 97.8% and 99.8%, respectively. The overall accuracy was 99.0%. The AUC-ROC was 0.98. The CNN processed 112 frames per second.

Conclusions

We developed a CNN capable of differentiating cervical cancer precursors in colposcopy frames. The high levels of accuracy for the differentiation of HSIL from LSIL may improve the diagnostic yield of this exam

Schlagwörter

Stichwörter der Autor:innen

HSILLSILartificial intelligencecervical squamous cell carcinomacolposcopy

Autor:innen und Institutionen

  • Precision Medicine Unit, Department of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427 Porto, Portugal.
  • Faculty of Medicine, University of Porto, Alameda Professor Hernâni Monteiro, 4200-427 Porto, Portugal.
  • Department of Gynecology, Centro Materno-Infantil do Norte Dr. Albino Aroso (CMIN), Santo António University Hospital, Largo da Maternidade Júlio Dinis, 4050-061 Porto, Portugal.
  • Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-065 Porto, Portugal.

ORCID-Profile: Miguel Mascarenhas, Miguel Martins, Pedro Cardoso, Francisco Mendes, Joana Fernandes, Guilherme Macedo

Zitieren

APA

Mascarenhas, M., Alencoão, I., Carinhas, M. J., Martins, M., Cardoso, P., Mendes, F., Fernandes, J., Ferreira, J., Macedo, G., & Zulmira Macedo, R. (2024). Artificial Intelligence and Colposcopy: Automatic Identification of Cervical Squamous Cell Carcinoma Precursors. Journal of Clinical Medicine, 13(10), 3003. https://doi.org/10.3390/jcm13103003

Vancouver

Mascarenhas M, Alencoão I, Carinhas MJ, Martins M, Cardoso P, Mendes F, et al. Artificial Intelligence and Colposcopy: Automatic Identification of Cervical Squamous Cell Carcinoma Precursors. Journal of Clinical Medicine. 2024;13(10):3003. doi:10.3390/jcm13103003

BibTeX
@article{Mascarenhas2024,
  author = {Mascarenhas, Miguel and Alencoão, Inês and Carinhas, Maria João and Martins, Miguel and Cardoso, Pedro and Mendes, Francisco and Fernandes, Joana and Ferreira, João and Macedo, Guilherme and Zulmira Macedo, Rosa},
  title = {Artificial Intelligence and Colposcopy: Automatic Identification of Cervical Squamous Cell Carcinoma Precursors},
  journal = {Journal of Clinical Medicine},
  year = {2024},
  volume = {13},
  number = {10},
  pages = {3003},
  doi = {10.3390/jcm13103003}
}
Kostenlos starten →