Deep-Learning-Based Automated Identification and Visualization of Oral Cancer in Optical Coherence Tomography Images
TL;DR: In this paper , three kinds of convolutional neural networks (CNNs) were trained and evaluated by using four metrics (accuracy, precision, sensitivity, and specificity) for OCT images to assist clinicians in oral cancer screening and diagnosis.
read more
Abstract: Early detection and diagnosis of oral cancer are critical for a better prognosis, but accurate and automatic identification is difficult using the available technologies. Optical coherence tomography (OCT) can be used as diagnostic aid due to the advantages of high resolution and non-invasion. We aim to evaluate deep-learning-based algorithms for OCT images to assist clinicians in oral cancer screening and diagnosis. An OCT data set was first established, including normal mucosa, precancerous lesion, and oral squamous cell carcinoma. Then, three kinds of convolutional neural networks (CNNs) were trained and evaluated by using four metrics (accuracy, precision, sensitivity, and specificity). Moreover, the CNN-based methods were compared against machine learning approaches through the same dataset. The results show the performance of CNNs, with a classification accuracy of up to 96.76%, is better than the machine-learning-based method with an accuracy of 92.52%. Moreover, visualization of lesions in OCT images was performed and the rationality and interpretability of the model for distinguishing different oral tissues were evaluated. It is proved that the automatic identification algorithm of OCT images based on deep learning has the potential to provide decision support for the effective screening and diagnosis of oral cancer.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Oral squamous cell carcinoma detection using EfficientNet on histopathological images
Eid Albalawi,Arastu Thakur,Mahesh Thyluru Ramakrishna,Surbhi Bhatia Khan,Suresh SankaraNarayanan,Badar Almarri,Theyazn Hassn Hadi +6 more
TL;DR: The promising potential of employing deep learning models to address the diagnostic challenges associated with OSCC is demonstrated, with a 99% accuracy rate signifies a considerable leap forward in earlier and more accurate detection of OSCC.
27
Deep learning in oral cancer- a systematic review
K. Warin,Siriwan Suebnukarn +1 more
TL;DR: The reported accuracy showed promising DL performance in studies of oral cancer and appeared to have potential utility in improving informed clinical decision-making of oral cancer.
13
Few-shot learning based oral cancer diagnosis using a dual feature extractor prototypical network.
Zijun Guo,Sha Ao,Bo Ao +2 more
TL;DR: This study proposes an oral cancer diagnosis approach based on a few-shot learning framework that circumvents the need for extensive training data and demonstrates the superior performance of the proposed approach over comparison methods.
4
Three-Dimension Epithelial Segmentation in Optical Coherence Tomography of the Oral Cavity Using Deep Learning
Chloe Hill,Jeanie Malone,Kelly H. Liu,Samson Ng,Calum MacAulay,Catherine Poh,Pierre Lane +6 more
TL;DR: Three-dimensional epithelial segmentation in OCT images of the oral cavity using deep learning enables accurate and automated analysis of large data volumes, simplifying the application of OCT for tissue examination and biopsy guidance.
3
A Comprehensive Study on Artificial Intelligence Techniques for Oral Cancer Diagnosis: Challenges and Opportunities
S. R,G. M. +1 more
- 17 Nov 2023
TL;DR: This study investigates several datasets, algorithms, modalities, and key findings used in ML and DL methodologies for the identification of oral cancer for the period of 2020 to 2023.
3
References
Optical coherence tomography
David Huang,Eric A. Swanson,Charles P. Lin,Joel S. Schuman,William G. Stinson,Warren Chang,Michael R. Hee,Thomas J. Flotte,Kenton W. Gregory,Carmen A. Puliafito,James G. Fujimoto +10 more
TL;DR: OCT as discussed by the authors uses low-coherence interferometry to produce a two-dimensional image of optical scattering from internal tissue microstructures in a way analogous to ultrasonic pulse-echo imaging.
Cancer statistics, 2023
TL;DR: The American Cancer Society estimates the number of new cancer cases and deaths in the United States and compiles the most recent data on population-based cancer occurrence and outcomes using incidence data collected by central cancer registries and mortality data collected from the National Center for Health Statistics as discussed by the authors .
10.9K
Optical Coherence Tomography
TL;DR: The optical coherence tomograph is a new, noninvasive technical device that can obtain cross-sectional, high-resolution images-optical coherencetomographs (OCT)-of the retina that permits an accurate evaluation of various macular and chorioretinal pathologies and the early detection of glaucomatous damage.
6.4K
A survey of transfer learning
TL;DR: This survey paper formally defines transfer learning, presents information on current solutions, and reviews applications applied toTransfer learning, which can be applied to big data environments.
Global epidemiology of oral and oropharyngeal cancer
TL;DR: This review presents data on incidence, mortality, survival and trends in cancers of the lip, oral cavity and oropharynx using available recent data sources around the world to gain insight into the geographic variations in the incidence of this cancer in the globe.
3.2K