A tree-based machine learning model to approach morphologic assessment of malignant salivary gland tumors

Mucoepidermoid carcinoma: Enhancing diagnostic accuracy and treatment strategy through machine learning models and web-based prognostic tool

BACKGROUND

Oral cancer, particularly mucoepidermoid carcinoma (MEC), presents diagnostic challenges due to its histological diversity and rarity. This study aimed to develop machine learning (ML) models to predict survival outcomes for MEC patients and pioneer a clinically accessible prognostic tool.

METHODS

Using the SEER database (2000-2020), we constructed predictive models with five ML algorithms: Random Forest Classifier (RFC), Gradient Boosting Classifier (GBC), Logistic Regression (LR), K-Nearest Neighbors (KNN), and Multilayer Perceptron (MLP). Predictive variables were identified via Cox regression, and Kaplan-Meier analysis assessed survival trends. Model performance was validated through the area under the curve (AUC) of receiver operating characteristic (ROC) curves.

RESULTS

This study included 1314 patients diagnosed with MEC of the oral cavity. The RFC demonstrated the highest predictive accuracy (AUC = 0.55), followed by the GBC and RFC (AUC = 0.53). The most affected primary site was the hard palate, followed by the retromolar and cheek mucosa. Survival rates varied with the treatment modality, with the highest rates observed in patients undergoing surgery alone. ML models have identified age, sex, and metastasis as significant prognostic factors influencing survival outcomes, underscoring the complexity and heterogeneity of MEC.

CONCLUSIONS

This study highlights ML's potential to enhance survival predictions and personalize treatment for MEC patients. We developed the first web-based prognostic tool, providing a novel, accessible solution for improving clinical decision-making in MEC.

Generative Artificial Intelligence, With Constrained Information, Outperforms Pre-Doctoral Student Average on Oral Pathology Differential Diagnosis Questions

BACKGROUND

Artificial intelligence (AI) technologies have seen rapid advancement and are increasingly used in healthcare fields, including clinical diagnostics and dental education. Despite their growing prominence, their effectiveness in assisting clinical decision-making in dental education remains under-explored. This study examined the performance of Generative AI in generating a clinical impression for oral pathology cases relative to dental students.

AIMS

The aim of this experiment was to assess the diagnostic accuracy and potential difference of Generative AI in clinical oral pathology compared to that of Doctor of Dental Surgery (DDS) students.

METHODS

A clinical oral pathology differential diagnosis exam was administered to both an AI model and DDS students. The AI model received limited information about each case, while the DDS students were provided with standard case details and a multiple-choice selection. The accuracy and statistical significance between both groups were compared and evaluated.

RESULTS

The AI model displayed higher diagnostic accuracy compared to the students, 95.65% to 78.92%, respectively, and the difference in groups was statistically significant.

CONCLUSION

The findings suggest that Generative AI has the potential to be a valuable tool in clinical oral pathology, even when provided with minimal case information. Its superior diagnostic performance compared to DDS students highlights prospective benefits of incorporating AI into dental education and specifically in helping students formulate clinical impressions.

Development and Evaluation of a Convolutional Neural Network for Microscopic Diagnosis Between Pleomorphic Adenoma and Carcinoma Ex-Pleomorphic Adenoma

AIMS

To develop a model capable of distinguishing carcinoma ex-pleomorphic adenoma from pleomorphic adenoma using a convolutional neural network architecture.

METHODS AND RESULTS

A cohort of 83 Brazilian patients, divided into carcinoma ex-pleomorphic adenoma (n = 42) and pleomorphic adenoma (n = 41), was used for training a convolutional neural network. The whole-slide images were annotated and fragmented into 743 869 (carcinoma ex-pleomorphic adenomas) and 211 714 (pleomorphic adenomas) patches, measuring 224 × 224 pixels. Training (80%), validation (10%), and test (10%) subsets were established. The Residual Neural Network (ResNet)-50 was chosen for its recognition and classification capabilities. The training and validation graphs, and parameters derived from the confusion matrix, were evaluated. The loss curve recorded 0.63, and the accuracy reached 0.93. Evaluated parameters included specificity (0.88), sensitivity (0.94), precision (0.96), F1 score (0.95), and area under the curve (0.97).

CONCLUSIONS

The study underscores the potential of ResNet-50 in the microscopic diagnosis of carcinoma ex-pleomorphic adenoma. The developed model demonstrated strong learning potential, but exhibited partial limitations in generalization, as indicated by the validation curve. In summary, the study established a promising baseline despite limitations in model generalization. This indicates the need to refine methodologies, investigate new models, incorporate larger datasets, and encourage inter-institutional collaboration for comprehensive studies in salivary gland tumors.

Using AI in Optimizing Oral and Dental Diagnoses-A Narrative Review

Artificial intelligence (AI) is revolutionizing the field of oral and dental healthcare by offering innovative tools and techniques for optimizing diagnosis, treatment planning, and patient management. This narrative review explores the current applications of AI in dentistry, focusing on its role in enhancing diagnostic accuracy and efficiency. AI technologies, such as machine learning, deep learning, and computer vision, are increasingly being integrated into dental practice to analyze clinical images, identify pathological conditions, and predict disease progression. By utilizing AI algorithms, dental professionals can detect issues like caries, periodontal disease and oral cancer at an earlier stage, thus improving patient outcomes.

Case report: The diagnostic pitfall of Warthin-like mucoepidermoid carcinoma

Warthin-like mucoepidermoid carcinoma (WL-MEC) is a newly reported variant of mucoepidermoid carcinoma. Its histological feature is easy to confused with metaplastic Warthin Tumor, and its relationship with Warthin tumor in histogenesis is controversial. In this study, we presented two cases of WL-MEC, discussing their clinicopathological and molecular features. Notably, one case was initially misdiagnosed during the first onset of the tumor. Case 1 was a 60-year-old female with a mass in the right parotid gland. Case 2 featured a 29-year-old male who developed a lump at the original surgical site 6 months after a "Warthin tumor" resection from the submandibular gland. Histologically, both tumor exhibited a prominent lymphoid stroma and cystic pattern, accompanied by various amounts of epithelial nests composed of squamoid cells, intermediate cells and mucinous cells. The characteristic eosinophilic bilayer epithelium of Warthin tumor was not typically presented in either case. Both cases tested positive for MAML2 gene rearrangement. To contextualize our findings, we conducted a comprehensive review of forty-eight WL-MEC cases documented in the English literature, aiming to synthesizing a reliable differential diagnostic approach. WL-MEC is a rare yet clinically relevant variant, posing a diagnostic pitfall for pathologists. Our study underscores the importance of a meticulous evaluation of both clinical and histological features, coupled with the detection of MAML2 rearrangement, as a credible method for distinguishing WL-MEC from other benign and malignant lesions, particularly metaplastic Warthin tumor.

Artificial intelligence in head and neck cancer diagnosis

INTRODUCTION

Artificial intelligence (AI) is currently being used to augment histopathological diagnostics in pathology. This systematic review aims to evaluate the evolution of these AI-based diagnostic techniques for diagnosing head and neck neoplasms.

MATERIALS AND METHODS

Articles regarding the use of AI for head and neck pathology published from 1982 until March 2022 were evaluated based on a search strategy determined by a multidisciplinary team of pathologists and otolaryngologists. Data from eligible articles were summarized according to author, year of publication, country, study population, tumor details, study results, and limitations.

RESULTS

Thirteen articles were included according to inclusion criteria. The selected studies were published between 2012 and March 1, 2022. Most of these studies concern the diagnosis of oral cancer; in particular, 6 are related to the oral cavity, 2 to the larynx, 1 to the salivary glands, and 4 to head and neck squamous cell carcinoma not otherwise specified (NOS). As for the type of diagnostics considered, 12 concerned histopathology and 1 cytology.

DISCUSSION

Starting from the pathological examination, artificial intelligence tools are an excellent solution for implementing diagnosis capability. Nevertheless, today the unavailability of large training datasets is a main issue that needs to be overcome to realize the true potential.

Artificial Intelligence in the Diagnosis of Oral Diseases: Applications and Pitfalls

Background: Machine learning (ML) is a key component of artificial intelligence (AI). The terms machine learning, artificial intelligence, and deep learning are erroneously used interchangeably as they appear as monolithic nebulous entities. This technology offers immense possibilities and opportunities to advance diagnostics in the field of medicine and dentistry. This necessitates a deep understanding of AI and its essential components, such as machine learning (ML), artificial neural networks (ANN), and deep learning (DP). Aim: This review aims to enlighten clinicians regarding AI and its applications in the diagnosis of oral diseases, along with the prospects and challenges involved. Review results: AI has been used in the diagnosis of various oral diseases, such as dental caries, maxillary sinus diseases, periodontal diseases, salivary gland diseases, TMJ disorders, and oral cancer through clinical data and diagnostic images. Larger data sets would enable AI to predict the occurrence of precancerous conditions. They can aid in population-wide surveillance and decide on referrals to specialists. AI can efficiently detect microfeatures beyond the human eye and augment its predictive power in critical diagnosis. Conclusion: Although studies have recognized the benefit of AI, the use of artificial intelligence and machine learning has not been integrated into routine dentistry. AI is still in the research phase. The coming decade will see immense changes in diagnosis and healthcare built on the back of this research. Clinical significance: This paper reviews the various applications of AI in dentistry and illuminates the shortcomings faced while dealing with AI research and suggests ways to tackle them. Overcoming these pitfalls will aid in integrating AI seamlessly into dentistry.