Real‐time classification on oral ulcer images with residual network and image enhancement

Guo, Jun; Wang, Haolin; Xue, Xingsi; Li, Mengting; Ma, Zhenzhen

doi:10.1049/ipr2.12144

Cited by 10 publications

(10 citation statements)

References 34 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of CNN models is highly influenced by the quality of the images and the sample number [25]. The oral cavity represents an anatomical region difficult to access for image capture because it does not present natural lighting, it requires the removal of mucous membranes to visualize certain regions and there is the difficulty of standardization in angulation, distancing, framing and sharpness.…”

Section: Discussionmentioning

confidence: 99%

“…Recent studies have investigated the feasibility of using AI to classify oral lesion images. Using residual networks, Guo et al achieved an accuracy of 98.79% for distinguishing normal mucosa from oral ulcerative lesions [25]. Satisfactory performances were also shown via means of deep learning technologies on confocal laser endomicroscopy images [7] and deep neural networks [16,26] to discriminate between benign lesions, oral potentially malignant disorders, and squamous cell carcinoma.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Use of Artificial Intelligence in the Classification of Elementary Oral Lesions from Clinical Images

Gomes

Schmith

Figueiredo

et al. 2023

IJERPH

View full text Add to dashboard Cite

Objectives: Artificial intelligence has generated a significant impact in the health field. The aim of this study was to perform the training and validation of a convolutional neural network (CNN)-based model to automatically classify six clinical representation categories of oral lesion images. Method: The CNN model was developed with the objective of automatically classifying the images into six categories of elementary lesions: (1) papule/nodule; (2) macule/spot; (3) vesicle/bullous; (4) erosion; (5) ulcer and (6) plaque. We selected four architectures and using our dataset we decided to test the following architectures: ResNet-50, VGG16, InceptionV3 and Xception. We used the confusion matrix as the main metric for the CNN evaluation and discussion. Results: A total of 5069 images of oral mucosa lesions were used. The oral elementary lesions classification reached the best result using an architecture based on InceptionV3. After hyperparameter optimization, we reached more than 71% correct predictions in all six lesion classes. The classification achieved an average accuracy of 95.09% in our dataset. Conclusions: We reported the development of an artificial intelligence model for the automated classification of elementary lesions from oral clinical images, achieving satisfactory performance. Future directions include the study of including trained layers to establish patterns of characteristics that determine benign, potentially malignant and malignant lesions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Use of Artificial Intelligence in the Classification of Elementary Oral Lesions from Clinical Images

Gomes

Schmith

Figueiredo

et al. 2023

IJERPH

View full text Add to dashboard Cite

show abstract

“…The performance of CNN models is highly in uenced by the quality of the images and the sample number [22]. The oral cavity represents an anatomical region di cult to access for image capture because it does not present natural lighting, requires removal of mucous membranes to visualise certain regions, di culty of standardisation in angulation, distancing, framing, sharpness.…”

Section: Discussionmentioning

confidence: 99%

“…Recent studies have investigated the feasibility of using AI to classify oral lesions images. Using residual networks, Guo et al achieved an accuracy of 98.79% for distinguishing normal mucosa from oral ulcerative lesions [22]. Satisfactory performances were also shown by means deep learning technologies on confocal laser endomicroscopy images [6] and deep neural networks [13,23] to discriminate benign lesion, oral potentially malignant disorders, and squamous cell carcinoma.…”

Section: Introductionmentioning

confidence: 99%

Use of artificial intelligence in the classification of elementary orallesions from clinical images

Gomes

Schmith

Figueiredo

et al. 2022

Preprint

View full text Add to dashboard Cite

Objectives: The Artificial Intelligence has generated a significant impact in health´s field. The aim of this study was to perform the training and validation of a convolutional neural network (CNN) based model to automatically classify six clinical representations categories of oral lesions images. Method: The CNN model was developed with the objective of automatically classifying the images into six categories of elementary lesions, which are: 1) papule/nodule; 2) macule/spot; 3) vesicle/bullae; 4) erosion; 5) ulcer and 6) plaque. We selected four architectures and using our dataset, we decided to test the following ones: ResNet-50, VGG16, InceptionV3 and Xception. We used the confusion matrix as the main metric for the CNN evaluation and discussion. Results: A total of 5069 images of oral mucosa lesions were used. The oral elementary lesions classification reached the best result using an architecture based on InceptionV3. After the hyperparameters optimisation, we reached more than 71% of correct predictions in all the six lesion classes. The classification achieved 95.09% as average accuracy on our dataset. Conclusions: We reported the development of an artificial intelligence model for the automated classification of elementar lesions from oral clinical images, achieving satisfactory performance. Future directions is the study of including trained layers to establish patterns of characteristics that determine benign, potentially malignant and malignant lesions. Clinical Relevance: Clinical Relevance: Its application in the classification of disease-related images for diagnostic purposes have achieved promising results, capable of recognising patterns in images, supporting the clinician’s decision at the time of evaluation.

show abstract

“…The earliest AI program was called Logic Theorist, created in 1955 by Allen Newell along with Herbert Simon [ 2 , 3 ]. AI has an important subset called ML [ 4 ], which was first used by Simon Cowell in 1959 [ 5 ]. Using tools such as artificial neural networks (ANN), ML makes predictions according to the information that is provided to it.…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence’s Use in the Diagnosis of Mouth Ulcers: A Systematic Review

Tiwari,

Gupta,

Singla

et al. 2023

Cureus

View full text Add to dashboard Cite

Artificial intelligence (AI) has been cited as being helpful in the diagnosis of diseases, the prediction of prognoses, and the development of patient-specific therapeutic strategies. AI can help dentists, in particular, when they need to make important judgments quickly. It can eliminate human mistakes in making decisions, resulting in superior and consistent medical treatment while lowering the workload on dentists. The existing studies relevant to the study and application of AI in the diagnosis of various forms of mouth ulcers are reviewed in this work. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards were followed in the preparation of the review. There were no rule violations, with the significant exception of the use of a better search method that led to more accurate findings. Using search terms mainly such as AI, oral health, oral ulcers, oral herpes simplex, oral lichen planus, pemphigus vulgaris, recurrent aphthous ulcer (RAU), oral cancer, premalignant and malignant disorders, etc., a comprehensive search was carried out in the reliable sources of literature, namely PubMed, Scopus, Embase, Web of Science, Ovid, Global Health, and PsycINFO. For all papers, exhaustive searches were done using inclusion criteria as well as exclusion criteria between June 28, 2018, and June 28, 2023. An AI framework for the automatic categorization of oral ulcers from oral clinical photographs was developed by the authors, and it performed satisfactorily. The newly designed AI model works better than the current convolutional neural network image categorization techniques and shows a fair level of precision in the classification of oral ulcers. However, despite being useful for identifying oral ulcers, the suggested technique needs a broader set of data for validation and training purposes before being used in clinical settings. Automated OCSCC identification using a deep learning-based technique is a quick, harmless, affordable, and practical approach to evaluating the effectiveness of cancer treatment. The categorization and identification of RAU lesions through the use of non-intrusive oral pictures using the previously developed ResNet50 and YOLOV algorithms demonstrated better accuracy as well as adequate potential for the future, which could be helpful in clinical practice. Moreover, the most reliable projections for the likelihood of the presence or absence of RAU were made by the optimized neural network. The authors also discovered variables associated with RAU that might be used as input information to build artificial neural networks that anticipate RAU.

show abstract

Real‐time classification on oral ulcer images with residual network and image enhancement

Cited by 10 publications

References 34 publications

Use of Artificial Intelligence in the Classification of Elementary Oral Lesions from Clinical Images

Use of Artificial Intelligence in the Classification of Elementary Oral Lesions from Clinical Images

Use of artificial intelligence in the classification of elementary orallesions from clinical images

Artificial Intelligence’s Use in the Diagnosis of Mouth Ulcers: A Systematic Review

Contact Info

Product

Resources

About