Artificial intelligence and radiomics in the diagnosis of intraosseous lesions of the gnathic bones: A systematic review.

BACKGROUND: The purpose of this systematic review (SR) is to gather evidence on the use of machine learning (ML) models in the diagnosis of intraosseous lesions in gnathic bones and to analyze the reliability, impact, and usefulness of such models. This SR was performed in accordance with the PRISMA 2022 guidelines and was registered in the PROSPERO database (CRD42022379298). METHODS: The acronym PICOS was used to structure the inquiry-focused review question "Is Artificial Intelligence reliable for the diagnosis of intraosseous lesions in gnathic bones?" The literature search was conducted in various electronic databases, including PubMed, Embase, Scopus, Cochrane Library, Web of Science, Lilacs, IEEE Xplore, and Gray Literature (Google Scholar and ProQuest). Risk of bias assessment was performed using PROBAST, and the results were synthesized by considering the task and sampling strategy of the dataset. RESULTS: Twenty-six studies were included (21 146 radiographic images). Ameloblastomas, odontogenic keratocysts, dentigerous cysts, and periapical cysts were the most frequently investigated lesions. According to TRIPOD, most studies were classified as type 2 (randomly divided). The F1 score was presented in only 13 studies, which provided the metrics for 20 trials, with a mean of 0.71 (±0.25). CONCLUSION: There is no conclusive evidence to support the usefulness of ML-based models in the detection, segmentation, and classification of intraosseous lesions in gnathic bones for routine clinical application. The lack of detail about data sampling, the lack of a comprehensive set of metrics for training and validation, and the absence of external testing limit experiments and hinder proper evaluation of model performance.

Barriers to early diagnosis and management of oral cancer in Latin America and the Caribbean.

OBJECTIVE: This study aimed to explore perceived barriers to early diagnosis and management of oral cancer, as well as potential pathways for improvement in Latin America and the Caribbean (LAC). METHODS: This cross-sectional study used a self-administered online questionnaire created via the Research Electronic Data Capture platform. The survey was distributed to health professionals trained in Oral Medicine, Oral Pathology, Oral and Maxillofacial Surgery, and Dentists with clinical and academic expertise in oral potentially malignant disorder (OPMD) and oral cancer. Data obtained were systematically organized and analyzed descriptively using Microsoft Excel. RESULTS: Twenty-three professionals from 21 LAC countries participated. Major barriers included the limited implementation of OPMD and oral cancer control plans (17.4%), low compulsory reporting for OPMD (8.7%) and oral cancer (34.8%), unclear referral pathways for OPMD (34.8%) and oral cancer (43.5%), and a shortage of trained professionals (8.7%). Participants endorsed the utility of online education (100%) and telemedicine (91.3%). CONCLUSION: The survey highlights major perceived barriers to early diagnosis and management of OPMD and oral cancer in LAC, as well as potential avenues for improvement.

Oral squamous cell carcinomas and oral potentially malignant disorders: A Latin American study.

OBJECTIVE: To determine the frequency of oral squamous cell carcinoma (OSCC) associated or not with oral potentially malignant disorders (OPMD), and the epidemiological profile and traditional risk factors in Latin America. METHODS: A retrospective observational study was conducted in 17 Latin American centres. There were included cases of OSCC, analysing age, gender, OSCC and their association with previous OPMD. Clinicopathological variables were retrieved. The condition of sequential-OSCC versus OSCC-de novo (OSCC-dn) was analysed concerning the aforementioned variables. Quantitative variables were analysed using Student's t-test, and qualitative variables with chi-square. RESULTS: In total, 2705 OSCC were included with a mean age of 62.8 years old. 55.8% were men. 53.75% of the patients were smokers and 38% were common drinkers. The lateral tongue border was the most affected site (24.65%). There were regional variations in OPMD, being leukoplakia the most frequent. Of the overall 2705 OSCC cases, 81.4% corresponded to OSCC-dn, while s-OSCC were 18.6%. Regarding lip vermillion SCC, 35.7% corresponded to de novo lip SCC and 64.3% were associated with previous OPMD. CONCLUSIONS: In Latin America, OSCC-dn seems to be more frequent with regional variations of some clinical and histopathological features. Further prospective studies are needed to analyse this phenomenon.

The use of deep learning state-of-the-art architectures for oral epithelial dysplasia grading: A comparative appraisal.

BACKGROUND: Dysplasia grading systems for oral epithelial dysplasia are a source of disagreement among pathologists. Therefore, machine learning approaches are being developed to mitigate this issue. METHODS: This cross-sectional study included a cohort of 82 patients with oral potentially malignant disorders and correspondent 98 hematoxylin and eosin-stained whole slide images with biopsied-proven dysplasia. All whole-slide images were manually annotated based on the binary system for oral epithelial dysplasia. The annotated regions of interest were segmented and fragmented into small patches and non-randomly sampled into training/validation and test subsets. The training/validation data were color augmented, resulting in a total of 81,786 patches for training. The held-out independent test set enrolled a total of 4,486 patches. Seven state-of-the-art convolutional neural networks were trained, validated, and tested with the same dataset. RESULTS: The models presented a high learning rate, yet very low generalization potential. At the model development, VGG16 performed the best, but with massive overfitting. In the test set, VGG16 presented the best accuracy, sensitivity, specificity, and area under the curve (62%, 62%, 66%, and 65%, respectively), associated with the higher loss among all Convolutional Neural Networks (CNNs) tested. EfficientB0 has comparable metrics and the lowest loss among all convolutional neural networks, being a great candidate for further studies. CONCLUSION: The models were not able to generalize enough to be applied in real-life datasets due to an overlapping of features between the two classes (i.e., high risk and low risk of malignization).

Clinicians' perception of oral potentially malignant disorders: a pitfall for image annotation in supervised learning.

OBJECTIVE: The present study aims to quantify clinicians' perceptions of oral potentially malignant disorders (OPMDs) when evaluating, classifying, and manually annotating clinical images, as well as to understand the source of inter-observer variability when assessing these lesions. The hypothesis was that different interpretations could affect the quality of the annotations used to train a Supervised Learning model. STUDY DESIGN: Forty-six clinical images from 37 patients were reviewed, classified, and manually annotated at the pixel level by 3 labelers. We compared the inter-examiner assessment based on clinical criteria through the κ statistics (Fleiss's kappa). The segmentations were also compared using the mean pixel-wise intersection over union (IoU). RESULTS: The inter-observer agreement for homogeneous/non-homogeneous criteria was substantial (κ = 63, 95% CI: 0.47-0.80). For the subclassification of non-homogeneous lesions, the inter-observer agreement was moderate (κ = 43, 95% CI: 0.34-0.53) (P < .001). The mean IoU of 0.53 (±0.22) was considered low. CONCLUSION: The subjective clinical assessment (based on human visual observation, variable criteria that have suffered adjustments over the years, different educational backgrounds, and personal experience) may explain the source of inter-observer discordance for the classification and annotation of OPMD. Therefore, there is a strong probability of transferring the subjectivity of human analysis to artificial intelligence models. The use of large data sets and segmentation based on the union of all labelers' annotations holds the potential to overcome this limitation.

Machine learning for the prediction of toxicities from head and neck cancer treatment: A systematic review with meta-analysis.

INTRODUCTION: The aim of the present systematic review (SR) is to summarize Machine Learning (ML) models currently used to predict head and neck cancer (HNC) treatment-related toxicities, and to understand the impact of image biomarkers (IBMs) in prediction models (PMs). The present SR was conducted following the guidelines of the PRISMA 2022 and registered in PROSPERO database (CRD42020219304). METHODS: The acronym PICOS was used to develop the focused review question (Can PMs accurately predict HNC treatment toxicities?) and the eligibility criteria. The inclusion criteria enrolled Prediction Model Studies (PMSs) with patient cohorts that were treated for HNC and developed toxicities. Electronic database search encompassed PubMed, EMBASE, Scopus, Cochrane Library, Web of Science, LILACS, and Gray Literature (Google Scholar and ProQuest). Risk of Bias (RoB) was assessed through PROBAST and the results were synthesized based on the data format (with and without IBMs) to allow comparison. RESULTS: A total of 28 studies and 4,713 patients were included. Xerostomia was the most frequently investigated toxicity (17; 60.71 %). Sixteen (57.14 %) studies reported using radiomics features in combination with clinical or dosimetrics/dosiomics for modelling. High RoB was identified in 23 studies. Meta-analysis (MA) showed an area under the receiver operating characteristics curve (AUROC) of 0.82 for models with IBMs and 0.81 for models without IBMs (p value < 0.001), demonstrating no difference among IBM- and non-IBM-based models. DISCUSSION: The development of a PM based on sample-specific features represents patient selection bias and may affect a model's performance. Heterogeneity of the studies as well as non-standardized metrics prevent proper comparison of studies, and the absence of an independent/external test does not allow the evaluation of the model's generalization ability. CONCLUSION: IBM-featured PMs are not superior to PMs based on non-IBM predictors. The evidence was appraised as of low certainty.

Machine learning concepts applied to oral pathology and oral medicine: A convolutional neural networks' approach.

INTRODUCTION: Artificial intelligence models and networks can learn and process dense information in a short time, leading to an efficient, objective, and accurate clinical and histopathological analysis, which can be useful to improve treatment modalities and prognostic outcomes. This paper targets oral pathologists, oral medicinists, and head and neck surgeons to provide them with a theoretical and conceptual foundation of artificial intelligence-based diagnostic approaches, with a special focus on convolutional neural networks, the state-of-the-art in artificial intelligence and deep learning. METHODS: The authors conducted a literature review, and the convolutional neural network's conceptual foundations and functionality were illustrated based on a unique interdisciplinary point of view. CONCLUSION: The development of artificial intelligence-based models and computer vision methods for pattern recognition in clinical and histopathological image analysis of head and neck cancer has the potential to aid diagnosis and prognostic prediction.

Difficulties in the Prognostic Study of Oral Leukoplakia: Standardisation Proposal of Follow-Up Parameters.

Oral leukoplakia is the most prevalent potentially malignant disorder of the oral cavity. To evaluate its potential for malignancy, appropriate documentation of the biological parameters is crucial, allowing the patients' progression to be assessed. We hypothesized a lack of standardization in the parameters employed for the prognostic study of oral leukoplakia; our aims were to determine the different parameters used for follow-up according to definition, importance, and frequency of use, and to provide a standardization proposal of follow-up research. We made a scoping review to identify papers with the keywords "leukoplakia," "oral," and "follow-up" published until June 2019 in English, Spanish and Portuguese literature through an online search in PUBMED, SCIELO, and SCOPUS databases. In total, 514 articles were initially identified, and fifty-nine publications were selected, of which 37 were retrospective. The reports included a total of 18,660 patients between 13 and 98 years old, with a mean age of 57.6 years. Tobacco and alcohol habits were positive for 77 and 37% of the patients, respectively. Our results showed that reported leukoplakias were predominantly located on buccal mucosa (40.4%), were homogeneous (60.8%), multiple (59.9%), smaller than 2 cm (74.4%) and histopathologically non-dysplastic (71%). The mean follow-up time was 55 months, with a 13% malignant transformation rate. The categorization and definition of multiple variables were notably diverse. Age, sex, habits (tobacco and alcohol), site, size, distribution, morphology, degree of dysplasia, and evolution were the chosen parameters for our proposal. The current study reflected the lack of consensus found in the literature regarding parameters for diagnosis or follow-up, impacting negatively on clinical and research results. standardization comprises an efficient way to facilitate the prognosis assessment of oral leukoplakia, being beneficial for clinical practice, and enabling better quality information to apply in research.