A tailored deep learning approach for early detection of oral cancer using a 19-layer CNN on clinical lip and tongue images
Abstract Early and accurate detection of oral cancer plays a pivotal role in improving patient outcomes. This research introduces a custom-designed, 19-layer convolutional neural network (CNN) for the automated diagnosis of oral cancer using clinical images of the lips and tongue. The methodology in...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-07957-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849334796179734528 |
|---|---|
| author | Pinjie Liu Kambiz Bagi |
| author_facet | Pinjie Liu Kambiz Bagi |
| author_sort | Pinjie Liu |
| collection | DOAJ |
| description | Abstract Early and accurate detection of oral cancer plays a pivotal role in improving patient outcomes. This research introduces a custom-designed, 19-layer convolutional neural network (CNN) for the automated diagnosis of oral cancer using clinical images of the lips and tongue. The methodology integrates advanced preprocessing steps, including min-max normalization and histogram-based contrast enhancement, to optimize image features critical for reliable classification. The model is extensively validated on the publicly available Oral Cancer (Lips and Tongue) Images (OCI) dataset, which is divided into 80% training and 20% testing subsets. Comprehensive performance evaluation employs established metrics—accuracy, sensitivity, specificity, precision, and F1-score. Our CNN architecture achieved an accuracy of 99.54%, sensitivity of 95.73%, specificity of 96.21%, precision of 96.34%, and F1-score of 96.03%, demonstrating substantial improvements over prominent transfer learning benchmarks, including SqueezeNet, AlexNet, Inception, VGG19, and ResNet50, all tested under identical experimental protocols. The model’s robust performance, efficient computation, and high reliability underline its practicality for clinical application and support its superiority over existing approaches. This study provides a reproducible pipeline and a new reference point for deep learning-based oral cancer detection, facilitating translation into real-world healthcare environments and promising enhanced diagnostic confidence. |
| format | Article |
| id | doaj-art-ade2c52c9cdd4b68b2c9be9e378aff1a |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-ade2c52c9cdd4b68b2c9be9e378aff1a2025-08-20T03:45:28ZengNature PortfolioScientific Reports2045-23222025-07-0115111910.1038/s41598-025-07957-9A tailored deep learning approach for early detection of oral cancer using a 19-layer CNN on clinical lip and tongue imagesPinjie Liu0Kambiz Bagi1School of Computer Engineering, Guangzhou Huali CollegeShiraz University of TechnologyAbstract Early and accurate detection of oral cancer plays a pivotal role in improving patient outcomes. This research introduces a custom-designed, 19-layer convolutional neural network (CNN) for the automated diagnosis of oral cancer using clinical images of the lips and tongue. The methodology integrates advanced preprocessing steps, including min-max normalization and histogram-based contrast enhancement, to optimize image features critical for reliable classification. The model is extensively validated on the publicly available Oral Cancer (Lips and Tongue) Images (OCI) dataset, which is divided into 80% training and 20% testing subsets. Comprehensive performance evaluation employs established metrics—accuracy, sensitivity, specificity, precision, and F1-score. Our CNN architecture achieved an accuracy of 99.54%, sensitivity of 95.73%, specificity of 96.21%, precision of 96.34%, and F1-score of 96.03%, demonstrating substantial improvements over prominent transfer learning benchmarks, including SqueezeNet, AlexNet, Inception, VGG19, and ResNet50, all tested under identical experimental protocols. The model’s robust performance, efficient computation, and high reliability underline its practicality for clinical application and support its superiority over existing approaches. This study provides a reproducible pipeline and a new reference point for deep learning-based oral cancer detection, facilitating translation into real-world healthcare environments and promising enhanced diagnostic confidence.https://doi.org/10.1038/s41598-025-07957-9Oral Cancer detectionConvolutional neural networkMedical image analysisComputer-Aided diagnosisClinical imagingEarly Cancer screening |
| spellingShingle | Pinjie Liu Kambiz Bagi A tailored deep learning approach for early detection of oral cancer using a 19-layer CNN on clinical lip and tongue images Scientific Reports Oral Cancer detection Convolutional neural network Medical image analysis Computer-Aided diagnosis Clinical imaging Early Cancer screening |
| title | A tailored deep learning approach for early detection of oral cancer using a 19-layer CNN on clinical lip and tongue images |
| title_full | A tailored deep learning approach for early detection of oral cancer using a 19-layer CNN on clinical lip and tongue images |
| title_fullStr | A tailored deep learning approach for early detection of oral cancer using a 19-layer CNN on clinical lip and tongue images |
| title_full_unstemmed | A tailored deep learning approach for early detection of oral cancer using a 19-layer CNN on clinical lip and tongue images |
| title_short | A tailored deep learning approach for early detection of oral cancer using a 19-layer CNN on clinical lip and tongue images |
| title_sort | tailored deep learning approach for early detection of oral cancer using a 19 layer cnn on clinical lip and tongue images |
| topic | Oral Cancer detection Convolutional neural network Medical image analysis Computer-Aided diagnosis Clinical imaging Early Cancer screening |
| url | https://doi.org/10.1038/s41598-025-07957-9 |
| work_keys_str_mv | AT pinjieliu atailoreddeeplearningapproachforearlydetectionoforalcancerusinga19layercnnonclinicallipandtongueimages AT kambizbagi atailoreddeeplearningapproachforearlydetectionoforalcancerusinga19layercnnonclinicallipandtongueimages AT pinjieliu tailoreddeeplearningapproachforearlydetectionoforalcancerusinga19layercnnonclinicallipandtongueimages AT kambizbagi tailoreddeeplearningapproachforearlydetectionoforalcancerusinga19layercnnonclinicallipandtongueimages |