Related Experiment Video
Updated: Jun 8, 2026
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.7K
Automated Detection of Oral Malignant Lesions Using Deep Learning: Scoping Review and Meta-Analysis.
Olga Di Fede1, Gaetano La Mantia1,2,3, Marco Parola4
1Department of Precision Medicine in Medical, Surgical and Critical Care (Me.Pre.C.C.), University of Palermo, Palermo, Italy.
Oral Diseases
|November 3, 2024
Summary
Deep learning (DL) shows promise for detecting oral lesions. This review found DL algorithms can improve oral lesion diagnosis, with pooled sensitivity of 0.86 and specificity of 0.67.
Area of Science:
- Oral pathology and digital health.
- Application of artificial intelligence in medical diagnostics.
Background:
- Oral diseases, particularly malignant lesions, pose significant global health challenges.
- Early detection is crucial for effective oral cancer treatment.
- Deep learning (DL) is increasingly recognized for its potential in automated medical image analysis.
Purpose of the Study:
- To conduct a scoping review and meta-analysis of automated oral lesion detection using DL.
- To provide an overview of advancements and achievements in this field.
- To assess the diagnostic performance of DL algorithms for oral lesions.
Main Methods:
- A scoping review identified studies from 2018-2023 using PubMed, Web of Science, and Scopus.
- Two independent reviewers screened studies for eligibility and extracted data.
- A meta-analysis synthesized findings from eligible studies.
Main Results:
- Fourteen studies on DL for oral lesion detection were included.
- Three studies were incorporated into the meta-analysis.
- Pooled sensitivity was 0.86 (95% CI: 0.80-0.91) and pooled specificity was 0.67 (95% CI: 0.58-0.75).
Conclusions:
- Deep learning algorithms demonstrate potential to enhance oral lesion diagnosis.
- Further research is needed to develop and validate automated diagnostic algorithms.
- Validated DL tools could improve early detection and management of oral diseases.
