Related Experiment Video
Updated: May 16, 2025
Multi-photon Imaging of Tumor Cell Invasion in an Orthotopic Mouse Model of Oral Squamous Cell Carcinoma
Published on: July 25, 2011
Cytopathological quantification of NORs using artificial intelligence to oral cancer screening
Tatiana Wannmacher Lepper1, Luara Nascimento do Amaral1, Ana Laura Ferrares Espinosa1
1Universidade Federal do Rio Grande do Sul - UFRGS, School of Dentistry, Department of Oral Pathology, Porto Alegre, RS, Brazil.
Abstract:
Oral squamous cell carcinoma (OSCC) remains the most prevalent neoplasm of the head and neck. In recent decades, the incidence and prevalence of OSCC have not significantly changed, highlighting the critical need to develop and implement new risk assessment measures. The present study aimed to define argyrophilic proteins of the nucleolar organizer region (AgNOR) cut-off risk points by oral exfoliative cytological smears comparing specialized humans with a convolutional neural network (CNN) system AgNOR Slide-Image Examiner. This study included four experimental groups: control, exposure to carcinogens (alcohol and tobacco), oral potentially malignant disorders, and OSCC. In the first phase, 50 cells were used for AgNOR quantification. In the second phase, AgNOR quantification was established in an automated manner using an AgNOR System - Slide Examiner (captured - bounding-boxed - CNN analysis). In phase 1, the cut-off point for considering a smear as suspicious was established at 3.69 AgNORs/nucleus with sensitivity of 86%, specificity of 93%, and accuracy of 90%. In phase 2, the analysis of the intraclass correlation coefficient of AgNORs attributed to the system and human was 0.896 (95% confidence interval = 0.875-0.915; p < 0.0001), and this quantification with the CNN was 20 min compared to 67 h, considering human analysis. The AgNOR Slide-Image Examiner successfully differentiated the nuclei and accurately quantified the number of NORs in oral cytological smears. The cut-off risk point of 3.69 AgNOR/nucleus indicates a suspicious sample may contribute to improvements in oral cancer screening.
Insights
New research defines argyrophilic proteins of the nucleolar organizer region (AgNOR) cut-off points for oral cancer screening. A convolutional neural network (CNN) system achieved high accuracy, significantly reducing analysis time for oral exfoliative cytological smears.
Area of Science:
- Oncology
- Biotechnology
- Computational Biology
Background:
- Oral squamous cell carcinoma (OSCC) is a prevalent head and neck cancer with stagnant incidence rates, necessitating improved risk assessment tools.
- Current diagnostic methods require enhancement to effectively identify high-risk individuals and facilitate early intervention.
- Argyrophilic proteins of the nucleolar organizer region (AgNOR) are potential biomarkers for cellular proliferation and malignancy.
Purpose of the Study:
- To establish reliable cut-off risk points for AgNOR quantification in oral exfoliative cytological smears.
- To compare the diagnostic accuracy and efficiency of human analysis versus an automated convolutional neural network (CNN) system for AgNOR assessment.
- To validate the utility of the AgNOR Slide-Image Examiner as a tool for oral cancer screening.
Main Methods:
- Oral cytological smears were analyzed from four groups: control, carcinogen exposure, potentially malignant disorders, and OSCC.
- AgNOR quantification was performed manually (Phase 1) and via an automated CNN system (Phase 2).
- Statistical analysis included sensitivity, specificity, accuracy, and intraclass correlation coefficient (ICC) to compare methods.
Main Results:
- A cut-off point of 3.69 AgNORs/nucleus was established with 86% sensitivity, 93% specificity, and 90% accuracy in Phase 1.
- The CNN system demonstrated high agreement with human analysis (ICC = 0.896).
- Automated AgNOR quantification using the CNN system reduced analysis time from 67 hours to 20 minutes.
Conclusions:
- The established AgNOR cut-off risk point of 3.69 AgNORs/nucleus can aid in identifying suspicious oral cytological smears.
- The AgNOR Slide-Image Examiner, powered by CNN, offers a rapid and accurate automated method for AgNOR quantification.
- This automated approach holds significant promise for improving the efficiency and effectiveness of oral cancer screening programs.
