Explore the vast range of titles available.

The increasing use of computed tomography (CT) and cone beam computed tomography (CBCT) in oral and maxillofacial imaging has driven the development of deep learning and radiomics applications to assist clinicians in early diagnosis, accurate prognosis prediction, and efficient treatment planning of maxillofacial diseases. This narrative review aimed to provide an up-to-date overview of the current applications of deep learning and radiomics on CT and CBCT for the diagnosis and management of maxillofacial diseases. Based on current evidence, a wide range of deep learning models on CT/CBCT images have been developed for automatic diagnosis, segmentation, and classification of jaw cysts and tumors, cervical lymph node metastasis, salivary gland diseases, temporomandibular (TMJ) disorders, maxillary sinus pathologies, mandibular fractures, and dentomaxillofacial deformities, while CT-/CBCT-derived radiomics applications mainly focused on occult lymph node metastasis in patients with oral cancer, malignant salivary gland tumors, and TMJ osteoarthritis. Most of these models showed high performance, and some of them even outperformed human experts. The models with performance on par with human experts have the potential to serve as clinically practicable tools to achieve the earliest possible diagnosis and treatment, leading to a more precise and personalized approach for the management of maxillofacial diseases. Challenges and issues, including the lack of the generalizability and explainability of deep learning models and the uncertainty in the reproducibility and stability of radiomic features, should be overcome to gain the trust of patients, providers, and healthcare organizers for daily clinical use of these models.

Objectives A convolutional neural network (CNN) was adapted to automatically detect early-stage nasopharyngeal carcinoma (NPC) and discriminate it from benign hyperplasia on a non-contrast-enhanced MRI sequence for potential use in NPC screening programs. Methods We retrospectively analyzed 412 patients who underwent T2-weighted MRI, 203 of whom had biopsy-proven primary NPC confined to the nasopharynx (stage T1) and 209 had benign hyperplasia without NPC. Thirteen patients were sampled randomly to monitor the training process. We applied the Residual Attention Network architecture, adapted for three-dimensional MR images, and incorporated a slice-attention mechanism, to produce a CNN score of 0–1 for NPC probability. Threefold cross-validation was performed in 399 patients. CNN scores between the NPC and benign hyperplasia groups were compared using Student's t test. Receiver operating characteristic with the area under the curve (AUC) was performed to identify the optimal CNN score threshold. Results In each fold, significant differences were observed in the CNN scores between the NPC and benign hyperplasia groups ( p < .01). The AUCs ranged from 0.95 to 0.97 with no significant differences between the folds ( p = .35 to .92). The combined AUC from all three folds ( n = 399) was 0.96, with an optimal CNN score threshold of > 0.71, producing a sensitivity, specificity, and accuracy of 92.4%, 90.6%, and 91.5%, respectively, for NPC detection. Conclusion Our CNN method applied to T2-weighted MRI could discriminate between malignant and benign tissues in the nasopharynx, suggesting that it as a promising approach for the automated detection of early-stage NPC. Key Points • The convolutional neural network (CNN)–based algorithm could automatically discriminate between malignant and benign diseases using T2-weighted fat-suppressed MR images. • The CNN-based algorithm had an accuracy of 91.5% with an area under the receiver operator characteristic curve of 0.96 for discriminating early-stage T1 nasopharyngeal carcinoma from benign hyperplasia. • The CNN-based algorithm had a sensitivity of 92.4% and specificity of 90.6% for detecting early-stage nasopharyngeal carcinoma.

PurposeConvolutional neural networks (CNNs) show potential for delineating cancers on contrast-enhanced MRI (ce-MRI) but there are clinical scenarios in which administration of contrast is not desirable. We investigated performance of the CNN for delineating primary nasopharyngeal carcinoma (NPC) on non-contrast-enhanced images and compared the performance to that on ce-MRI.Materials and methodsWe retrospectively analyzed primary NPC in 195 patients using a well-established CNN, U-Net, for tumor delineation on the non-contrast-enhanced fat-suppressed (fs)-T2W, ce-T1W and ce-fs-T1W images. The CNN-derived delineations were compared to manual delineations to obtain Dice similarity coefficient (DSC) and average surface distance (ASD). The DSC and ASD on fs-T2W were compared to those on ce-MRI. Primary tumor volumes (PTVs) of CNN-derived delineations were compared to that of manual delineations.ResultsThe CNN for NPC delineation on fs-T2W images showed similar DSC (0.71 ± 0.09) and ASD (0.21 ± 0.48 cm) to those on ce-T1W images (0.71 ± 0.09 and 0.17 ± 0.19 cm, respectively) (p > 0.05), and lower DSC but similar ASD to ce-fs-T1W images (0.73 ± 0.09, p < 0.001; and 0.17 ± 0.20 cm, p > 0.05). The CNN overestimated PTVs on all sequences (p < 0.001).ConclusionThe CNN showed promise for NPC delineation on fs-T2W images in cases where it is desirable to avoid contrast agent injection. The CNN overestimated PTVs on all sequences.

Purpose T1rho imaging showed potential applications in cancer imaging but little research explored the underlying biological processes that contribute to the T1rho values in cancer. This study aimed to investigate the potential associations between quantitative imaging biomarkers from T1rho imaging and the well-established diffusion weighted imaging (DWI), with tumour-stromal, immunohistochemical (IHC), and tumour-infiltration-lymphocytes (TIL) biomarkers in nasopharyngeal carcinoma (NPC). Methods Pre-treatment T1rho and DWI imaging of primary NPCs were performed in 50 prospectively recruited patients. The mean T1rho and apparent diffusion coefficient (ADC) of NPC were obtained and correlated with tumour-stromal, IHC, TIL biomarkers using the Pearson Correlation test and the coefficients (R) were calculated. Results The mean T1rho values negatively correlated with collagenous stroma-lymphoid stroma ( R =-0.314, p  = 0.03) and positively correlated with percentage of tumour cells positive for Ki-67 ( R  = 0.402, p  < 0.01), but there were no associations between T1rho values and the other tumour-stromal, IHC or TIL biomarkers ( p  = 0.16–0.98) or between ADC values and any of these biomarkers ( p  = 0.07–0.82). Conclusion Our results showed the possible underlying biological mechanisms of T1rho imaging in head and neck cancer. T1rho imaging negatively correlated with the ratio of collagenous to lymphoid stroma, and positively correlated with tumour cell proliferation, which are both known to be predictors of outcome, suggesting that T1rho imaging may have a valuable role in head and neck cancer imaging. As this is a preliminary study with small sample size, further studies are encouraged to validate our findings.

Purpose To investigate change in diffusion weighted imaging (DWI) between pre-treatment (pre-) and after induction chemotherapy (post-IC) for long-term outcome prediction in advanced nasopharyngeal carcinoma (adNPC). Materials and methods Mean apparent diffusion coefficients (ADCs) of two DWIs (ADC pre and ADC post−IC ) and changes in ADC between two scans (ΔADC%) were calculated from 64 eligible patients with adNPC and correlated with disease free survival (DFS), locoregional recurrence free survival (LRRFS), distant metastases free survival (DMFS), and overall survival (OS) using Cox regression analysis. C-indexes of the independent parameters for outcome were compared with that of RECIST response groups. Survival rates between two patient groups were evaluated and compared. Results Univariable analysis showed that high ΔADC% predicted good DFS, LRRFS, and DMFS p  < 0.05), but did not predict OS ( p  = 0.40). Neither ADC pre nor ADC post−IC ( p  = 0.07 to 0.97) predicted outcome. Multivariate analysis showed that ΔADC% independently predicted DFS, LRRFS, and DMFS ( p  < 0.01 to 0.03). Compared with the RECIST groups, the ΔADC% groups (threshold of 34.2%) showed a higher c-index for 3-year (0.47 vs. 0.71, p  < 0.01) and 5-year DFS (0.51 vs. 0.72, p  < 0.01). Compared with patients with ΔADC%<34.2%, patients with ΔADC%≥34.2% had higher 3-year DFS, LRRFS and DMFS of 100%, 100% and 100%, respectively ( p  < 0.05). Conclusion Results suggest that ΔADC% was an independent predictor for long-term outcome and was superior to RECIST guideline for outcome prediction in adNPC. A ΔADC% threshold of ≥ 34.2% may be valuable for selecting patients who respond to treatment for de-escalation of treatment or post-treatment surveillance.

Automated tooth segmentation and identification on dental radiographs are crucial steps in establishing digital dental workflows. While deep learning networks have been developed for these tasks, their performance has been inferior in partially edentulous individuals. This study proposes a novel semi-supervised Transformer-based framework (SemiTNet), specifically designed to improve tooth segmentation and identification performance on panoramic radiographs, particularly in partially edentulous cases, and establish an open-source dataset to serve as a unified benchmark. A total of 16,317 panoramic radiographs (1589 labeled and 14,728 unlabeled images) were collected from various datasets to create a large-scale dataset (TSI15k). The labeled images were divided into training and test sets at a 7:1 ratio, while the unlabeled images were used for semi-supervised learning. The SemiTNet was developed using a semi-supervised learning method with a label-guided teacher–student knowledge distillation strategy, incorporating a Transformer-based architecture. The performance of SemiTNet was evaluated on the test set using the intersection over union (IoU), Dice coefficient, precision, recall, and F1 score, and compared with five state-of-the-art networks. Paired t-tests were performed to compare the evaluation metrics between SemiTNet and the other networks. SemiTNet outperformed other networks, achieving the highest accuracy for tooth segmentation and identification, while requiring minimal model size. SemiTNet’s performance was near-perfect for fully dentate individuals (all metrics over 99.69%) and excellent for partially edentulous individuals (all metrics over 93%). In edentulous cases, SemiTNet obtained statistically significantly higher tooth identification performance than all other networks. The proposed SemiTNet outperformed previous high-complexity, state-of-the-art networks, particularly in partially edentulous cases. The established open-source TSI15k dataset could serve as a unified benchmark for future studies.

Background/Objectives: The detection of unknown primary tumours in the palatine tonsils (PTs) on imaging relies heavily on asymmetry in size between the right and left sides, but the expected normal range in asymmetry is not well documented. This study aimed to document the expected range of asymmetry in the size of the PTs in adults without cancer. Methods: This retrospective study evaluated 250 pairs of normal PTs on MRIs of adults without head and neck cancer. The size (volume, V) of the PTs on the left and right sides were measured, and the percentage difference in volume (ΔV%) between the two sides was calculated. An additional analysis of PT volumes in 29 patients with ipsilateral early-stage palatine tonsillar cancer (PTCs) was performed. Results: In patients without PTC, the normal PTs had a mean volume of 3.0 ± 1.7 cm3, and there was a difference in size between the left and right PTs, showing a median ΔV% of 11.6% (range: 0.1–79.0%); most patients had a ΔV% of ≤40% (95%) for PTs. In patients with ipsilateral PTC, the normal PT had a smaller size compared with PTC (p < 0.01), showing a median ΔV% of 132.9% (range: 8.5–863.2%). Compared with patients without PTC, those with PTC showed a greater ΔV% (p < 0.01). An optimal ΔV% threshold of >39.6% achieved the best accuracy of 95% for identifying PTC. Conclusions: PTs are asymmetrical in size in adults without PTC. An additional analysis involving patients with PTC confirmed a threshold of ΔV% of 40% for PTs, which may be clinically valuable to help detect pathology using MRI.

ObjectivesTo propose and evaluate a convolutional neural network (CNN) algorithm for automatic detection and segmentation of mucosal thickening (MT) and mucosal retention cysts (MRCs) in the maxillary sinus on low-dose and full-dose cone-beam computed tomography (CBCT).Materials and methodsA total of 890 maxillary sinuses on 445 CBCT scans were analyzed. The air space, MT, and MRCs in each sinus were manually segmented. Low-dose CBCTs were divided into training, training-monitoring, and testing datasets at a 7:1:2 ratio. Full-dose CBCTs were used as a testing dataset. A three-step CNN algorithm built based on V-Net and support vector regression was trained on low-dose CBCTs and tested on the low-dose and full-dose datasets. Performance for detection of MT and MRCs using area under the curves (AUCs) and for segmentation using Dice similarity coefficient (DSC) was evaluated.ResultsFor the detection of MT and MRCs, the algorithm achieved AUCs of 0.91 and 0.84 on low-dose scans and of 0.89 and 0.93 on full-dose scans, respectively. The median DSCs for segmenting the air space, MT, and MRCs were 0.972, 0.729, and 0.678 on low-dose scans and 0.968, 0.663, and 0.787 on full-dose scans, respectively. There were no significant differences in the algorithm performance between low-dose and full-dose CBCTs.ConclusionsThe proposed CNN algorithm has the potential to accurately detect and segment MT and MRCs in maxillary sinus on CBCT scans with low-dose and full-dose protocols.Clinical relevanceAn implementation of this artificial intelligence application in daily practice as an automated diagnostic and reporting system seems possible.

The lack of a consistent MRI radiomic signature, partly due to the multitude of initial feature analyses, limits the widespread clinical application of radiomics for the discrimination of salivary gland tumors (SGTs). This study aimed to identify the optimal radiomics feature category and MRI sequence for characterizing SGTs, which could serve as a step towards obtaining a consensus on a radiomics signature. Preliminary radiomics models were built to discriminate malignant SGTs (n = 34) from benign SGTs (n = 57) on T1-weighted (T1WI), fat-suppressed (FS)-T2WI and contrast-enhanced (CE)-T1WI images using six feature categories. The discrimination performances of these preliminary models were evaluated using 5-fold-cross-validation with 100 repetitions and the area under the receiver operating characteristic curve (AUC). The differences between models’ performances were identified using one-way ANOVA. Results show that the best feature categories were logarithm for T1WI and CE-T1WI and exponential for FS-T2WI, with AUCs of 0.828, 0.754 and 0.819, respectively. These AUCs were higher than the AUCs obtained using all feature categories combined, which were 0.750, 0.707 and 0.774, respectively (p < 0.001). The highest AUC (0.846) was obtained using a combination of T1WI + logarithm and FS-T2WI + exponential features, which reduced the initial features by 94.0% (from 1015 × 3 to 91 × 2). CE-T1WI did not improve performance. Using one feature category rather than all feature categories combined reduced the number of initial features without compromising radiomic performance.

Background: Preoperative, noninvasive prediction of meningioma grade is important for therapeutic planning and decision making. In this study, we propose a dual-level augmentation strategy incorporating image-level augmentation (IA) and feature-level augmentation (FA) to tackle class imbalance and improve the predictive performance of radiomics for meningioma grading on Magnetic Resonance Imaging (MRI). Methods: This study recruited 160 consecutive patients with pathologically proven meningioma (129 low-grade (WHO grade I) tumors; 31 high-grade (WHO grade II and III) tumors) with preoperative multisequence MRI imaging. A dual-level augmentation strategy combining IA and FA was applied and evaluated in 100 repetitions in 3-, 5-, and 10-fold cross-validation. Results: The best area under the receiver operating characteristics curve of our method in 100 repetitions was ≥0.78 in all cross-validations. The corresponding cross-validation sensitivities (cross-validation specificity) were 0.72 (0.69), 0.76 (0.71), and 0.63 (0.82) in 3-, 5-, and 10-fold cross-validation, respectively. The proposed method achieved significantly better performance and distribution of results, outperforming single-level augmentation (IA or FA) or no augmentation in each cross-validation. Conclusions: The dual-level augmentation strategy using IA and FA significantly improves the performance of the radiomics model for meningioma grading on MRI, allowing better radiomics-based preoperative stratification and individualized treatment.