Malignant and non-malignant oral lesions classification and diagnosis with deep neural networks

Application of image enhancement in the auxiliary diagnosis of oral potentially malignant disorders

OBJECTIVES

The images of oral potentially malignant disorders (OPMDs) frequently encounter problems related to visual quality and image distortion, which may lead to serious misdiagnosis and missed diagnosis. This study is to explore the auxiliary effects of different optical image enhancement algorithms on the object detection of OPMDs lesions.

METHODS

Digital images of OPMDs were collected, including white plaques, white stripes, and erosive lesions. The dataset was divided into a training set (6,488 images) and a validation set (2,592 images). Original images were processed using multiscale retinex (MSR), adaptive histogram equalization (AHE), and adaptive contrast enhancement (ACE), respectively. Object detection models based on You Only Look Once version 8 (YOLOv8) were used for lesion detection, and the diagnostic performance was evaluated using 328 images taken at different times.

RESULTS

The model performance in the MSR-enhanced image set was superior to that in the original image set, with total accuracy increased for all three lesion types, and the sensitivity of complete correct recognition for complex multi-lesion images improved. Models trained with AHE and ACE preprocessing showed reduced diagnostic performance.

CONCLUSION

Image enhancement algorithms can enhance the visual quality of OPMDs images, and the MSR algorithm is capable of strengthening the object detection ability in the computer vision model.

CLINICAL RELEVANCE

This study provides an approach to reduce the misdiagnosis and missed diagnosis of OPMDs lesions in object detection model.

Automated Detection of Oral Malignant Lesions Using Deep Learning: Scoping Review and Meta-Analysis

OBJECTIVE

Oral diseases, specifically malignant lesions, are serious global health concerns requiring early diagnosis for effective treatment. In recent years, deep learning (DL) has emerged as a powerful tool for the automated detection and classification of oral lesions. This research, by conducting a scoping review and meta-analysis, aims to provide an overview of the progress and achievements in the field of automated detection of oral lesions using DL.

MATERIALS AND METHODS

A scoping review was conducted to identify relevant studies published in the last 5 years (2018-2023). A comprehensive search was conducted using several electronic databases, including PubMed, Web of Science, and Scopus. Two reviewers independently assessed the studies for eligibility and extracted data using a standardized form, and a meta-analysis was conducted to synthesize the findings.

RESULTS

Fourteen studies utilizing various DL algorithms were identified and included for the detection and classification of oral lesions from clinical images. Among these, three were included in the meta-analysis. The estimated pooled sensitivity and specificity were 0.86 (95% confidence interval [CI] = 0.80-0.91) and 0.67 (95% CI = 0.58-0.75), respectively.

CONCLUSIONS

The results of meta-analysis indicate that DL algorithms improve the diagnosis of oral lesions. Future research should develop validated algorithms for automated diagnosis.

TRIAL REGISTRATION

Open Science Framework (https://osf.io/4n8sm).

Artificial intelligence and the diagnosis of oral cavity cancer and oral potentially malignant disorders from clinical photographs: a narrative review

Oral cavity cancer is associated with high morbidity and mortality, particularly with advanced stage diagnosis. Oral cavity cancer, typically squamous cell carcinoma (OSCC), is often preceded by oral potentially malignant disorders (OPMDs), which comprise eleven disorders with variable risks for malignant transformation. While OPMDs are clinical diagnoses, conventional oral exam followed by biopsy and histopathological analysis is the gold standard for diagnosis of OSCC. There is vast heterogeneity in the clinical presentation of OPMDs, with possible visual similarities to early-stage OSCC or even to various benign oral mucosal abnormalities. The diagnostic challenge of OSCC/OPMDs is compounded in the non-specialist or primary care setting. There has been significant research interest in technology to assist in the diagnosis of OSCC/OPMDs. Artificial intelligence (AI), which enables machine performance of human tasks, has already shown promise in several domains of medical diagnostics. Computer vision, the field of AI dedicated to the analysis of visual data, has over the past decade been applied to clinical photographs for the diagnosis of OSCC/OPMDs. Various methodological concerns and limitations may be encountered in the literature on OSCC/OPMD image analysis. This narrative review delineates the current landscape of AI clinical photograph analysis in the diagnosis of OSCC/OPMDs and navigates the limitations, methodological issues, and clinical workflow implications of this field, providing context for future research considerations.

Towards dental diagnostic systems: Synergizing wavelet transform with generative adversarial networks for enhanced image data fusion

The advent of precision diagnostics in pediatric dentistry is shifting towards ensuring early detection of dental diseases, a critical factor in safeguarding the oral health of the younger population. In this study, an innovative approach is introduced, wherein Discrete Wavelet Transform (DWT) and Generative Adversarial Networks (GANs) are synergized within an Image Data Fusion (IDF) framework to enhance the accuracy of dental disease diagnosis through dental diagnostic systems. Dental panoramic radiographs from pediatric patients were utilized to demonstrate how the integration of DWT and GANs can significantly improve the informativeness of dental images. In the IDF process, the original images, GAN-augmented images, and wavelet-transformed images are combined to create a comprehensive dataset. DWT was employed for the decomposition of images into frequency components to enhance the visibility of subtle pathological features. Simultaneously, GANs were used to augment the dataset with high-quality, synthetic radiographic images indistinguishable from real ones, to provide robust data training. These integrated images are then fed into an Artificial Neural Network (ANN) for the classification of dental diseases. The utilization of the ANN in this context demonstrates the system's robustness and culminates in achieving an unprecedented accuracy rate of 0.897, 0.905 precision, recall of 0.897, and specificity of 0.968. Additionally, this study explores the feasibility of embedding the diagnostic system into dental X-ray scanners by leveraging lightweight models and cloud-based solutions to minimize resource constraints. Such integration is posited to revolutionize dental care by providing real-time, accurate disease detection capabilities, which significantly reduces diagnostical delays and enhances treatment outcomes.

A Deep Learning System to Predict Epithelial Dysplasia in Oral Leukoplakia

Oral leukoplakia (OL) has an inherent disposition to develop oral cancer. OL with epithelial dysplasia (OED) is significantly likely to undergo malignant transformation; however, routine OED assessment is invasive and challenging. This study investigated whether a deep learning (DL) model can predict dysplasia probability among patients with leukoplakia using oral photographs. In addition, we assessed the performance of the DL model in comparison with clinicians' ratings and in providing decision support on dysplasia assessment. Retrospective images of leukoplakia taken before biopsy/histopathology were obtained to construct the DL model (n = 2,073). OED status following histopathology was used as the gold standard for all images. We first developed, fine-tuned, and internally validated a DL architecture with an EfficientNet-B2 backbone that outputs the predicted probability of OED, OED status, and regions-of-interest heat maps. Then, we tested the performance of the DL model on a temporal cohort before geographical validation. We also assessed the model's performance at external validation with opinions provided by human raters on OED status. Performance evaluation included discrimination, calibration, and potential net benefit. The DL model achieved good Brier scores, areas under the curve, and balanced accuracies of 0.124 (0.079-0.169), 0.882 (0.838-0.926), and 81.8% (76.5-87.1) at testing and 0.146 (0.112-0.18), 0.828 (0.792-0.864), and 76.4% (72.3-80.5) at external validation, respectively. In addition, the model had a higher potential net benefit in selecting patients with OL for biopsy/histopathology during OED assessment than when biopsies were performed for all patients. External validation also showed that the DL model had better accuracy than 92.3% (24/26) of human raters in classifying the OED status of leukoplakia from oral images (balanced accuracy: 54.8%-79.7%). Overall, the photograph-based intelligent model can predict OED probability and status in leukoplakia with good calibration and discrimination, which shows potential for decision support to select patients for biopsy/histopathology, obviate unnecessary biopsy, and assist in patient self-monitoring.

Application of artificial intelligence in dental implant prognosis: A scoping review

OBJECTIVES

The purpose of this scoping review was to evaluate the performance of artificial intelligence (AI) in the prognosis of dental implants.

DATA

Studies that analyzed the performance of AI models in the prediction of implant prognosis based on medical records or radiographic images. Quality assessment was conducted using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Quasi-Experimental Studies.

SOURCES

This scoping review included studies published in English up to October 2023 in MEDLINE/PubMed, Embase, Cochrane Library, and Scopus. A manual search was also performed.

STUDY SELECTION

Of 892 studies, full-text analysis was conducted in 36 studies. Twelve studies met the inclusion criteria. Eight used deep learning models, 3 applied traditional machine learning algorithms, and 1 study combined both types. The performance was quantified using accuracy, sensitivity, specificity, precision, F1 score, and receiver operating characteristic area under curves (ROC AUC). The prognostic accuracy was analyzed and ranged from 70 % to 96.13 %.

CONCLUSIONS

AI is a promising tool in evaluating implant prognosis, but further enhancements are required. Additional radiographic and clinical data are needed to improve AI performance in implant prognosis.

CLINICAL SIGNIFICANCE

AI can predict the prognosis of dental implants based on radiographic images or medical records. As a result, clinicians can receive predicted implant prognosis with the assistance of AI before implant placement and make informed decisions.

Dental education and practice: past, present, and future trends

This position paper explores the historical transitions and current trends in dental education and practice and attempts to predict the future. Dental education and practice landscape, especially after the COVID-19 epidemic, are at a crossroads. Four fundamental forces are shaping the future: the escalating cost of education, the laicization of dental care, the corporatization of dental care, and technological advances. Dental education will likely include individualized, competency-based, asynchronous, hybrid, face-to-face, and virtual education with different start and end points for students. Dental practice, similarly, will be hybrid, with both face-to-face and virtual opportunities for patient care. Artificial intelligence will drive efficiencies in diagnosis, treatment, and office management.