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 for detection and classification of oral potentially malignant disorders: A conceptual review.

Oral potentially malignant disorders represent precursor lesions that may undergo malignant transformation to oral cancer. There are many known risk factors associated with the development of oral potentially malignant disorders, and contribute to the risk of malignant transformation. Although many advances have been reported to understand the biological behavior of oral potentially malignant disorders, their clinical features that indicate the characteristics of malignant transformation are not well established. Early diagnosis of malignancy is the most important factor to improve patients' prognosis. The integration of machine learning into routine diagnosis has recently emerged as an adjunct to aid clinical examination. Increased performances of artificial intelligence AI-assisted medical devices are claimed to exceed the human capability in the clinical detection of early cancer. Therefore, the aim of this narrative review is to introduce artificial intelligence terminology, concepts, and models currently used in oncology to familiarize oral medicine scientists with the language skills, best research practices, and knowledge for developing machine learning models applied to the clinical detection of oral potentially malignant disorders.

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.

BH3-mimetic small molecule inhibits the growth and recurrence of adenoid cystic carcinoma.

OBJECTIVES: To evaluate the anti-tumor effect of BM-1197, a new potent and highly specific small molecule inhibitor of Bcl-2/Bcl-xL, in preclinical models of human adenoid cystic carcinoma (ACC). METHODS: Low passage primary human adenoid cystic carcinoma cells (UM-HACC-2A,-2B,-5,-6) and patient-derived xenograft (PDX) models (UM-PDX-HACC) were developed from surgical specimens obtained from 4 patients. The effect of BM-1197 on cell viability and cell cycle were evaluated in vitro using this panel of low passage ACC cells. The effect of BM-1197 on tumor growth, recurrence and tumor cell apoptosis in vivo was evaluated with the PDX model of ACC (UM-PDX-HACC-5). RESULTS: Exposure of low passage primary human ACC cells to BM-1197 mediated an IC50 of 0.92-2.82 µM. This correlated with an increase in the fraction of apoptotic cells (p<0.0001) and an increase in caspase-3 activity (p<0.0001), but no noticeable differences in cell cycle (p>0.05). In vivo, BM-1197 inhibited tumor growth (p=0.0256) and induced tumor cell apoptosis (p=0.0165) without causing significant systemic toxicities, as determined by mouse weight over time. Surprisingly, weekly BM-1197 decreased the incidence of tumor recurrence (p=0.0297), as determined by Kaplan-Meier analysis. CONCLUSION: These data demonstrated that single agent BM-1197 induces apoptosis and inhibits tumor growth in preclinical models of adenoid cystic carcinoma. Notably, single agent BM-1197 inhibited tumor recurrence, which is considered a major clinical challenge in the clinical management of adenoid cystic carcinoma. Collectively, these results suggest that patients with adenoid cystic carcinoma might benefit from therapy with a BH3-mimetic small molecule.