Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jan 29:10:1349336.
doi: 10.3389/fmed.2023.1349336. eCollection 2023.

Oral squamous cell carcinoma detection using EfficientNet on histopathological images

Eid Albalawi  1 , Arastu Thakur  2 , Mahesh Thyluru Ramakrishna  2 , Surbhi Bhatia Khan  3   4 , Suresh SankaraNarayanan  1 , Badar Almarri  1 , Theyazn Hassn Hadi  5
Affiliations

Oral squamous cell carcinoma detection using EfficientNet on histopathological images

Eid Albalawi et al. Front Med (Lausanne). .

Abstract

Introduction: Oral Squamous Cell Carcinoma (OSCC) poses a significant challenge in oncology due to the absence of precise diagnostic tools, leading to delays in identifying the condition. Current diagnostic methods for OSCC have limitations in accuracy and efficiency, highlighting the need for more reliable approaches. This study aims to explore the discriminative potential of histopathological images of oral epithelium and OSCC. By utilizing a database containing 1224 images from 230 patients, captured at varying magnifications and publicly available, a customized deep learning model based on EfficientNetB3 was developed. The model's objective was to differentiate between normal epithelium and OSCC tissues by employing advanced techniques such as data augmentation, regularization, and optimization.

Methods: The research utilized a histopathological imaging database for Oral Cancer analysis, incorporating 1224 images from 230 patients. These images, taken at various magnifications, formed the basis for training a specialized deep learning model built upon the EfficientNetB3 architecture. The model underwent training to distinguish between normal epithelium and OSCC tissues, employing sophisticated methodologies including data augmentation, regularization techniques, and optimization strategies.

Results: The customized deep learning model achieved significant success, showcasing a remarkable 99% accuracy when tested on the dataset. This high accuracy underscores the model's efficacy in effectively discerning between normal epithelium and OSCC tissues. Furthermore, the model exhibited impressive precision, recall, and F1-score metrics, reinforcing its potential as a robust diagnostic tool for OSCC.

Discussion: This research demonstrates the promising potential of employing deep learning models to address the diagnostic challenges associated with OSCC. The model's ability to achieve a 99% accuracy rate on the test dataset signifies a considerable leap forward in earlier and more accurate detection of OSCC. Leveraging advanced techniques in machine learning, such as data augmentation and optimization, has shown promising results in improving patient outcomes through timely and precise identification of OSCC.

Keywords: EfficientNet; Oral Squamous Cell Carcinoma; cancer identification; diagnostic precision; histopathological images; microscopic imaging.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Model architecture.
Figure 2
Figure 2
Dataset distribution.
Figure 3
Figure 3
Sample images from dataset under different magnification.
Figure 4
Figure 4
Original and preprocessed image.
Figure 5
Figure 5
Annotated images with labels.
Figure 6
Figure 6
Augmented image.
Figure 7
Figure 7
Model training and compilation.
Figure 8
Figure 8
Confusion matrix.
Figure 9
Figure 9
Precision, recall and F1-score.
Figure 10
Figure 10
Training and validation loss and accuracy.
Figure 11
Figure 11
Accuracy with different sets.
See this image and copyright information in PMC

References

    1. Welikala S, Rajapakse J, Karunathilaka S, Abeywickrama P. Automated detection and classification of oral lesions using deep learning for early detection of oral cancer. Sci Rep. (2020) 10:1–10. doi: 10.1109/ACCESS.2020.3010180 - DOI
    1. Rahman MS, Hossain MA, Khan MSR, Kaiser MS. Histopathologic oral cancer prediction using oral squamous cell carcinoma biopsy empowered with transfer learning. Comput Methods Prog Biomed. (2022) 22:107143. doi: 10.3390/s22103833 - DOI - PMC - PubMed
    1. Ibrar MW, Khan MSR, Kaiser MS. Early diagnosis of oral squamous cell carcinoma is based on histopathological images using deep and hybrid learning approaches. Comput Methods Prog Biomed. (2023) 252:107372 doi: 10.3390/diagnostics12081899 - DOI
    1. Rahman TY, Mahanta LB, Chakraborty C. Textural pattern classification for OSCC. J Microsc. (2018) 269:85–93. doi: 10.1111/jmi.12611, PMID: - DOI - PubMed
    1. Fu Q, Chen Y, Li Z, Jing Q, Hu C, Liu H, et al. A deep learning algorithm for detection of oral cavity squamous cell carcinoma from photographic images: a retrospective study. EClinicalMedicine. (2020) 27:100558. doi: 10.1016/j.eclinm.2020.100558 - DOI - PMC - PubMed

LinkOut - more resources