Explainable machine learning via intra-tumoral radiomics feature mapping for patient stratification in adjuvant chemotherapy for locoregionally advanced nasopharyngeal carcinoma.

PURPOSE: This study aimed to discover intra-tumor heterogeneity signature and validate its predictive value for adjuvant chemotherapy (ACT) following concurrent chemoradiotherapy (CCRT) in locoregionally advanced nasopharyngeal carcinoma (LA-NPC). MATERIALS AND METHODS: 397 LA-NPC patients were retrospectively enrolled. Pre-treatment contrast-enhanced T1-weighted (CET1-w) MR images, clinical variables, and follow-up were retrospectively collected. We identified single predictive radiomic feature from primary gross tumor volume (GTVnp) and defined predicted subvolume by calculating voxel-wised feature mapping and within GTVnp. We independently validate predictive value of identified feature and associated predicted subvolume. RESULTS: Only one radiomic feature, gldm_DependenceVariance in 3 mm-sigma LoG-filtered image, was discovered as a signature. In the high-risk group determined by the signature, patients received CCRT + ACT achieved 3-year disease free survival (DFS) rate of 90% versus 57% (HR, 0.20; 95%CI, 0.05-0.94; P = 0.007) for CCRT alone. The multivariate analysis showed patients receiving CCRT + ACT had a HR of 0.21 (95%CI: 0.06-0.68, P = 0.009) for DFS compared to those receiving CCRT alone. The predictive value can also be generalized to the subvolume with multivariate HR of 0.27 (P = 0.017) for DFS. CONCLUSION: The signature with its heterogeneity mapping could be a reliable and explainable ACT decision-making tool in clinical practice.

Potential and impact of artificial intelligence algorithms in dento-maxillofacial radiology.

OBJECTIVES: Novel artificial intelligence (AI) learning algorithms in dento-maxillofacial radiology (DMFR) are continuously being developed and improved using advanced convolutional neural networks. This review provides an overview of the potential and impact of AI algorithms in DMFR. MATERIALS AND METHODS: A narrative review was conducted on the literature on AI algorithms in DMFR. RESULTS: In the field of DMFR, AI algorithms were mainly proposed for (1) automated detection of dental caries, periapical pathologies, root fracture, periodontal/peri-implant bone loss, and maxillofacial cysts/tumors; (2) classification of mandibular third molars, skeletal malocclusion, and dental implant systems; (3) localization of cephalometric landmarks; and (4) improvement of image quality. Data insufficiency, overfitting, and the lack of interpretability are the main issues in the development and use of image-based AI algorithms. Several strategies have been suggested to address these issues, such as data augmentation, transfer learning, semi-supervised training, few-shot learning, and gradient-weighted class activation mapping. CONCLUSIONS: Further integration of relevant AI algorithms into one fully automatic end-to-end intelligent system for possible multi-disciplinary applications is very likely to be a field of increased interest in the future. CLINICAL RELEVANCE: This review provides dental practitioners and researchers with a comprehensive understanding of the current development, performance, issues, and prospects of image-based AI algorithms in DMFR.

Automatic detection and segmentation of morphological changes of the maxillary sinus mucosa on cone-beam computed tomography images using a three-dimensional convolutional neural network.

OBJECTIVES: To 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 METHODS: A 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. RESULTS: For 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. CONCLUSIONS: The 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 RELEVANCE: An implementation of this artificial intelligence application in daily practice as an automated diagnostic and reporting system seems possible.

Comparison of new magnetic resonance imaging grading system with conventional endoscopy for the early detection of nasopharyngeal carcinoma.

BACKGROUND: Although stratifying individuals with respect to nasopharyngeal carcinoma (NPC) risk with Epstein-Barr virus-based markers is possible, the performance of diagnostic methods for detecting lesions among screen-positive individuals is poorly understood. METHODS: The authors prospectively evaluated 882 participants aged 30 to 70 years who were enrolled between October 2014 and November 2018 in an ongoing, population-based NPC screening program and had an elevated NPC risk. Participants were offered endoscopy and magnetic resonance imaging (MRI), and lesions were identified either by biopsy at a follow-up endoscopy or further contact and linkage to the local cancer registry through December 31, 2019. The diagnostic performance characteristics of endoscopy and MRI for NPC detection were investigated. RESULTS: Eighteen of 28 identified NPC cases were detected by both methods, 1 was detected by endoscopy alone, and 9 were detected by MRI alone. MRI had significantly higher sensitivity than endoscopy for NPC detection overall (96.4% vs 67.9%; Pdifference = .021) and for early-stage NPC (95.2% vs 57.1%; P = .021). The sensitivity of endoscopy was suggestively lower among participants who had previously been screened in comparison with those undergoing an initial screening (50.0% vs 81.2%; P = .11). The authors observed a higher overall referral rate by MRI versus endoscopy (17.3% vs 9.1%; P < .001). Cases missed by endoscopy had early-stage disease and were more commonly observed for tumors originating from the pharyngeal recess. CONCLUSIONS: MRI was more sensitive than endoscopy for NPC detection in the context of population screening but required the referral of a higher proportion of screen-positive individuals. The sensitivity of endoscopy was particularly low for individuals who had previously been screened.

Convolutional neural network for discriminating nasopharyngeal carcinoma and benign hyperplasia on MRI.

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.

Pre-treatment amide proton transfer imaging predicts treatment outcome in nasopharyngeal carcinoma.

OBJECTIVE: To investigate the value of pre-treatment amide proton transfer-weighted (APTw) imaging for predicting survival of patients with nasopharyngeal carcinoma (NPC). MATERIALS AND METHODS: Pre-treatment APTw imaging was performed in 77 NPC patients and the mean, 90th percentile, skewness, and kurtosis of APT asymmetry (APTmean, APT90, APTskewness, and APTkurtosis, respectively) were obtained from the primary tumor. Associations of APTw parameters with locoregional relapse-free survival (LRRFS), distant metastasis-free survival (DMFS), and disease-free survival (DFS) after 2 years were assessed by univariable Cox regression analysis and significant APTw parameters, together with age, sex, treatment, and stage as confounding variables, were added to the multivariable model. Kaplan-Meier analysis was used to determine the prognostic significance of patients with high or low APT values based on a threshold value from receiver operating characteristic curve analysis. RESULTS: Locoregional relapse, distant metastases, and disease relapse occurred in 14/77 (18%), 10/77 (13%), and 20/77 (26%) patients, respectively, at a median follow-up of 48.3 (10.6-67.4) months. Univariable analysis showed significant associations of LRRFS with APTskewness (HR = 1.98; p = 0.034), DMFS with APTmean (HR = 2.44; p = 0.033), and APT90 (HR = 1.93; p = 0.009), and DFS with APTmean (HR = 2.01; p = 0.016), APT90 (HR = 1.68; p = 0.009), and APTskewness (HR = 1.85; p = 0.029). In multivariable analysis, the significant predictors for DMFS were APT90 (HR = 3.51; p = 0.004) and nodal stage (HR = 5.95; p = 0.034) and for DFS were APT90 (HR = 1.97; p = 0.010) and age (HR = 0.92; p = 0.014). An APT90 ≥ 4.38% was associated with a significantly poorer DFS at 2 years than APT90 < 4.38% (66% vs. 91%; HR = 4.01; p = 0.005). CONCLUSION: APTw imaging may potentially predict survival in patients with NPC. KEY POINTS: • APTw imaging may provide new markers to predict survival in nasopharyngeal carcinoma. • APT90 is an independent predictor of distant metastases-free survival and disease-free survival. • The APThigh group is at higher risk of disease relapse than the APTlow group.

Intravoxel incoherent motion diffusion-weighted imaging for discrimination of benign and malignant retropharyngeal nodes.

PURPOSE: Anatomical imaging criteria for the diagnosis of malignant head and neck nodes may not always be reliable. This study aimed to evaluate the diagnostic value of conventional diffusion-weighted imaging (DWI) and intravoxel incoherent motion (IVIM) DWI in discriminating benign and malignant metastatic retropharyngeal nodes (RPNs). METHODS: IVIM DWI using 14 b-values was performed on RPNs of 30 patients with newly diagnosed metastatic nasopharyngeal carcinoma (NPC) and 30 patients with elevated plasma Epstein-Barr virus (EBV)-DNA without NPC who were part of an EBV-based NPC screening program. Histogram measurements of the two groups were compared for pure diffusion coefficient (D), pseudo-diffusion coefficient (D*), perfusion volume fraction (f) and apparent diffusion coefficient (ADC) using the Mann-Whitney U test. Area under the curves (AUCs) of significant measurements were calculated from receiver-operating characteristics analysis and compared using the DeLong test. RESULTS: Compared with metastatic RPNs, benign RPNs had lower ADCmean (0.73 vs 0.82 × 10-3 mm2/s) and Dmean (0.60 vs 0.71 × 10-3 mm2/s) and a higher D*mean (35.21 vs 28.66 × 10-3 mm2/s) (all p < 0.05). There was no difference in the f measurements between the two groups (p = 0.204 to 0.301). Dmean achieved the highest AUC of 0.800, but this was not statistically better than the AUCs of the other parameters (p = 0.148 to 0.991). CONCLUSION: Benign RPNs in patients with EBV-DNA showed greater restriction of diffusion compared with malignant metastatic RPNs from NPC. IVIM did not show a significant advantage over conventional DWI in discriminating benign and malignant nodes.

Distinguishing early-stage nasopharyngeal carcinoma from benign hyperplasia using intravoxel incoherent motion diffusion-weighted MRI.

OBJECTIVES: MRI can detect early-stage nasopharyngeal carcinoma (NPC), but the detection is more challenging in early-stage NPCs because they must be distinguished from benign hyperplasia in the nasopharynx. This study aimed to determine whether intravoxel incoherent motion diffusion-weighted imaging (IVIM DWI) MRI could distinguish between these two entities. METHODS: Thirty-four subjects with early-stage NPC and 30 subjects with benign hyperplasia prospectively underwent IVIM DWI. The mean pure diffusion coefficient (D), pseudo-diffusion coefficient (D*), perfusion fraction (f) and apparent diffusion coefficient (ADC) values were calculated for all subjects and compared between the 2 groups using Student's t test. Receiver operating characteristics with the area under the curve (AUC) was used to identify the optimal threshold for all significant parameters, and the corresponding diagnostic performance was calculated. A p value of < 0.05 was considered statistically significant. RESULTS: Compared with benign hyperplasia, early-stage NPC exhibited a significantly lower D mean (0.64 ± 0.06 vs 0.87 ± 0.11 × 10-3 mm2/s), ADC0-1000 mean (0.77 ± 0.08 vs 1.00 ± 0.13 × 10-3 mm2/s), ADC300-1000 (0.63 ± 0.05 vs 0.86 ± 0.10 × 10-3 mm2/s) and a higher D* mean (32.66 ± 4.79 vs 21.96 ± 5.21 × 10-3 mm2/s) (all p < 0.001). No significant difference in the f mean was observed between the two groups (p = 0.216). The D and ADC300-1000 mean had the highest AUC of 0.985 and 0.988, respectively, and the D mean of < 0.75 × 10-3 mm2/s yielded the highest sensitivity, specificity and accuracy (100%, 93.3% and 96.9%, respectively) in distinguishing early-stage NPC from benign hyperplasia. CONCLUSION: DWI has potential to distinguish early-stage NPC from benign hyperplasia and D and ADC300-1000 mean were the most promising parameters. KEY POINTS: • Diffusion-weighted imaging has potential to distinguish early-stage nasopharyngeal carcinoma from benign hyperplasia in the nasopharynx. • The pure diffusion coefficient, pseudo-diffusion coefficient from intravoxel incoherent motion model and apparent diffusion coefficient from conventional diffusion-weighted imaging were significant parameters for distinguishing these two entities in the nasopharynx. • The pure diffusion coefficient, followed by apparent diffusion coefficient, may be the most promising parameters to be used in screening studies to help detect early-stage nasopharyngeal carcinoma.

Amide proton transfer MRI detects early changes in nasopharyngeal carcinoma: providing a potential imaging marker for treatment response.

PURPOSE: To determine if treatment of nasopharyngeal carcinoma (NPC) induces early changes in amide proton transfer-weighted (APTw) magnetic resonance imaging (MRI), and to perform a preliminary evaluation of APTw imaging in response assessment. METHODS: Sixteen patients with NPC planned for treatment with radiotherapy and/or chemotherapy underwent APTw imaging of the primary tumour pre-treatment and 2-week intra-treatment. Difference in pre- and intra-treatment APT mean (APTmean) was compared using the Wilcoxon signed rank test. Differences in APTmean and percentage change (%Δ) in APTmean were compared between responders and non-responders based on the outcome at 6 months, using the Mann-Whitney U test. RESULTS: APTmean decreased in 9/16 (56.3%) and increased in 7/16 (43.7%) with no significant difference between the pre- and intra-treatment APT values for the whole group (p > 0.05). NPC showed response in 11/16 (68.8%) and non-response in 5/11 (31.2%). There were significant differences between the %Δ of responders and non-responders for APTmean (p = 0.01). Responders showed %Δ decrease in APTmean of - 23.12% while non-responders showed a %Δ increase in APTmean of + 102.28%. CONCLUSION: APT value changes can be detected in early intra-treatment. Intra-treatment %Δ APTmean shows potential in predicting short-term outcome.

Head and Neck Tumors: Amide Proton Transfer MRI.

Purpose To evaluate the utility of amide proton transfer (APT) imaging in the characterization of head and neck tumors. Materials and Methods This retrospective study of APT imaging included 117 patients with 70 nasopharyngeal undifferentiated carcinomas (NUCs), 26 squamous cell carcinomas (SCCs), eight non-Hodgkin lymphomas (NHLs), and 13 benign salivary gland tumors (BSGTs). Normal tissues were examined in 25 patients. The APT means of malignant tumors, normal tissues, and benign tumors were calculated and compared with the Student t test and analysis of variance. The added value of the mean APT to the mean apparent diffusion coefficient (ADC) for differentiating malignant and benign tumors was evaluated by using receiver operating characteristic analysis and integrated discrimination index. Results The mean APT of malignant tumors (2.40% ± 0.97 [standard deviation]) was significantly higher than that of brain tissue (1.13% ± 0.43), muscle tissue (0.23% ± 0.73), and benign tumors (1.32% ± 1.20) (P < .001). There were no differences between malignant groups (NUC, 2.37% ± 0.90; SCC, 2.41% ± 1.16; NHL, 2.65% ± 0.89; P = .45 to P = .86). The mean ADC of malignant tumors ([0.85 ± 0.17] × 10-3 mm2/sec) was significantly lower than that of benign tumors ([1.46 ± 0.47] × 10-3 mm2/sec) (P = .001). Adding APT to ADC increased the area under the curve from 0.87 to 0.96, with an integrated discrimination index of 7.6% (P = .13). Conclusion These preliminary data demonstrate differences in amide proton transfer (APT) mean of malignant tumors, normal tissues, and benign tumors, although APT mean could not be used to differentiate between malignant tumor groups. APT imaging has the potential to be of added value to apparent diffusion coefficient in differentiating malignant from benign tumors.

Nasopharyngeal carcinoma: relationship between invasion of the prevertebral space and distant metastases.

PURPOSE: To identify primary sites of nasopharyngeal carcinoma (NPC) invasion on the staging head and neck magnetic resonance imaging (MRI) that correlate with distant metastases (DM). MATERIALS AND METHODS: Staging head and neck MRI examinations of 579 NPC patients were assessed for primary tumour invasion into 16 individual sites, primary stage (T) and nodal stage (N). Results were correlated with distant metastasis-free survival (DMFS) using the Cox regression, and the diagnostic performance of significant independent markers for DM was calculated. In addition, sites of primary tumour invasion were correlated also with involvement of the first echelon of ipsilateral nodes (FEN+) using logistic regression. RESULTS: Distant metastases were present in 128/579 NPC patients (22.1%) after intensity-modulated radiotherapy (IMRT)/chemo-IMRT and 5-year DMFS was 78.8%. Prevertebral space invasion (PVS+) and N stage, but not T stage, were independent prognostic markers of DMFS (p = 0.016, < 0.001, and 0.433, respectively). Compared to stage N3, PVS invasion had a higher sensitivity (28.1 vs. 68.8%), but lower specificity (90.5 vs. 47.4%) and accuracy (76.7 vs. 48.9%) for correlating patients with DM. PVS invasion, together with parapharyngeal fat space invasion (PPFS+), was also an independent predictive marker of FEN+. CONCLUSION: PVS was the only site of primary tumour invasion that independently correlated with DM, and together with PPFS + was an independent prognostic marker of FEN+, but the low specificity and accuracy of PVS invasion limits its use as a prognostic marker of DM.

Diffusion-weighted imaging of nasopharyngeal carcinoma to predict distant metastases.

Our study aimed to identify diffusion-weighted imaging (DWI) parameters obtained from primary nasopharyngeal carcinoma (NPC) at initial presentation, that can predict patients at risk of distant metastases. One hundred and sixty-four patients underwent pretreatment magnetic resonance imaging and DWI. The apparent diffusion coefficient (ADC)mean, ADCskewness, and ADCkurtosis were obtained by histogram analysis. Univariate and multivariate analyses of these ADC parameters together with primary volume (PV), nodal volume (NV), T stage, N stage and presence of locoregional relapse (LRR) were compared between patients with distant metastases (DM+) and patients without distant metastases (DM-) at 5 years using logistic regression. Twenty-eight out of 164 patients (17.1 %) were DM+ (2.5-60 months) and 136/164 patients were DM- (61.2-119.4 months). Compared to DM- patients, the primary tumour of DM+ patients showed significantly lower ADCskewness (ADC values with the greatest frequency were higher) (p = 0.041), and higher PV (p = 0.022), NV (p < 0.01), T stage (p = 0.023), N stage (p < 0.01) and LRR (p < 0.01). On multivariate analysis the ADCskewness was no longer significant (p = 0.120) and only NV and LRR were independent predictors for DM+ (p = 0.023 and 0.021, respectively). DWI showed that compared to DM- patients, DM+ patients had a significantly lower primary tumour ADCskewness, but at initial presentation NV was the only independent predictor of DM.

Radiographic Imaging for the Diagnosis and Treatment of Patients with Skeletal Class III Malocclusion.

Skeletal Class III malocclusion is one type of dentofacial deformity that significantly affects patients' facial aesthetics and oral health. The orthodontic treatment of skeletal Class III malocclusion presents challenges due to uncertainties surrounding mandibular growth patterns and treatment outcomes. In recent years, disease-specific radiographic features have garnered interest from researchers in various fields including orthodontics, for their exceptional performance in enhancing diagnostic precision and treatment effect predictability. The aim of this narrative review is to provide an overview of the valuable radiographic features in the diagnosis and management of skeletal Class III malocclusion. Based on the existing literature, a series of analyses on lateral cephalograms have been concluded to identify the significant variables related to facial type classification, growth prediction, and decision-making for tooth extractions and orthognathic surgery in patients with skeletal Class III malocclusion. Furthermore, we summarize the parameters regarding the inter-maxillary relationship, as well as different anatomical structures including the maxilla, mandible, craniofacial base, and soft tissues from conventional and machine learning statistical models. Several distinct radiographic features for Class III malocclusion have also been preliminarily observed using cone beam computed tomography (CBCT) and magnetic resonance imaging (MRI).

Trajectories of social isolation and loneliness and the risk of incident type 2 diabetes mellitus across genetic risk score.

AIM: This study aimed to investigate the association of social isolation, loneliness, and their trajectory with the risk of developing type 2 diabetes mellitus (T2DM) across genetic risk. METHODS: We included 439,337 participants (mean age 56.3 ± 8.1 years) enrolled in the UK Biobank study who were followed up until May 31, 2021. Social isolation and loneliness were self-reported and were further categorized into never, transient, incident, and persistent patterns. RESULTS: During a median follow-up of 12.7 years, 15,258 incident T2DM cases were documented. Social isolation (versus no social isolation: hazard ratio (HR) 95 % confidence interval (CI) 1.04 [1.00;1.09]) and loneliness (versus no loneliness: 1.26 [1.19;1.34]) were associated with an increased T2DM risk, independent of the genetic risk for T2DM. The interactions existed between social isolation and loneliness (Pinteraction < 0.05); the increased T2DM risk associated with social isolation was only significant among participants without loneliness. In the longitudinal analysis, only persistent social isolation (versus never social isolation: 1.22 [1.02;1.45]) was associated with an increased T2DM risk, whereas incident loneliness (versus never loneliness: 1.95 [1.40;2.71]) and persistent loneliness (2.00 [1.31;3.04]) were associated with higher T2DM risks. CONCLUSION: Social isolation and loneliness, especially their persistent pattern, were independently associated with an increased incident T2DM risk, irrespective of an individual's genetic risk. Loneliness modified the association between social isolation and incident T2DM.

Deep learning for the automatic detection and segmentation of parotid gland tumors on MRI.

OBJECTIVES: Parotid gland tumors (PGTs) often occur as incidental findings on magnetic resonance images (MRI) that may be overlooked. This study aimed to construct and validate a deep learning model to automatically identify parotid glands (PGs) with a PGT from normal PGs, and in those with a PGT to segment the tumor. MATERIALS AND METHODS: The nnUNet combined with a PG-specific post-processing procedure was used to develop the deep learning model trained on T1-weighed images (T1WI) in 311 patients (180 PGs with tumors and 442 normal PGs) and fat-suppressed (FS)-T2WI in 257 patients (125 PGs with tumors and 389 normal PGs), for detecting and segmenting PGTs with five-fold cross-validation. Additional validation set separated by time, comprising T1WI in 34 and FS-T2WI in 41 patients, was used to validate the model performance. RESULTS AND CONCLUSION: To identify PGs with tumors from normal PGs, using combined T1WI and FS-T2WI, the deep learning model achieved an accuracy, sensitivity and specificity of 98.2% (497/506), 100% (119/119) and 97.7% (378/387), respectively, in the cross-validation set and 98.5% (67/68), 100% (20/20) and 97.9% (47/48), respectively, in the validation set. For patients with PGTs, automatic segmentation of PGTs on T1WI and FS-T2WI achieved mean dice coefficients of 86.1% and 84.2%, respectively, in the cross-validation set, and of 85.9% and 81.0%, respectively, in the validation set. The proposed deep learning model may assist the detection and segmentation of PGTs and, by acting as a second pair of eyes, ensure that incidentally detected PGTs on MRI are not missed.

Radiologic extranodal extension for nodal staging in nasopharyngeal carcinoma.

PURPOSE: Extranodal extension (ENE) has the potential to add value to the current nodal staging system (N8th) for predicting outcome in nasopharyngeal carcinoma (NPC). This study aimed to incorporate ENE, as well as cervical nodal necrosis (CNN) to the current stage N3 and evaluated their impact on outcome prediction. The findings were validated on an external cohort. METHODS & MATERIALS: Pre-treatment MRI of 750 patients from the internal cohort were retrospectively reviewed. Predictive values of six modified nodal staging systems that incorporated four patterns of ENE and two patterns of CNN to the current stage N3 for disease-free survival (DFS) were compared with that of N8th using multivariate cox-regression and concordance statistics in the internal cohort. Performance of stage N3 for predicting disease recurrence was calculated. An external cohort of 179 patients was used to validate the findings. RESULTS: Incorporation of advanced ENE, which infiltrates into adjacent muscle/skin/salivary glands outperformed the other five modifications for predicting outcomes (p < 0.01) and achieved a significantly higher c-index for 5-year DFS (0.69 vs 0.72) (p < 0.01) when compared with that of N8th staging system. By adding advanced ENE to the current N3 increased the sensitivity for predicting disease recurrence from 22.4 % to 47.1 %. The finding was validated in the external cohort (5-year DFS 0.65 vs. 0.72, p < 0.01; sensitivity of stage N3 increased from 14.0 % to 41.9 % for disease recurrence). CONCLUSION: Results from two centre cohorts confirmed that the radiological advanced ENE should be considered as a criterion for stage N3 disease in NPC.

Early detection of nasopharyngeal carcinoma: performance of a short contrast-free screening magnetic resonance imaging.

BACKGROUND: Although contrast-enhanced magnetic resonance imaging (MRI) detects early-stage nasopharyngeal carcinoma (NPC) not detected by endoscopic-guided biopsy (EGB), a short contrast-free screening MRI would be desirable for NPC screening programs. This study evaluated a screening MRI in a plasma Epstein-Barr virus (EBV)-DNA NPC screening program. METHODS: EBV-DNA-screen-positive patients underwent endoscopy, and endoscopy-positive patients underwent EGB. EGB was negative if the biopsy was negative or was not performed. Patients also underwent a screening MRI. Diagnostic performance was based on histologic confirmation of NPC in the initial study or during a follow-up period of at least 2 years. RESULTS: The study prospectively recruited 354 patients for MRI and endoscopy; 40/354 (11.3%) endoscopy-positive patients underwent EGB. Eighteen had NPC (5.1%), and 336 without NPC (94.9%) were followed up for a median of 44.8 months. MRI detected additional NPCs in 3/18 (16.7%) endoscopy-negative and 2/18 (11.1%) EGB-negative patients (stage I/II, n = 4; stage III, n = 1). None of the 24 EGB-negative patients who were MRI-negative had NPC. MRI missed NPC in 2/18 (11.1%), one of which was also endoscopy-negative. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of MRI, endoscopy, and EGB were 88.9%, 91.1%, 34.8%, 99.4%, and 91.0%; 77.8%, 92.3%, 35.0%, 98.7%, and 91.5%; and 66.7%, 92.3%, 31.6%, 98.1%, and 91.0%, respectively. CONCLUSION: A quick contrast-free screening MRI complements endoscopy in NPC screening programs. In EBV-screen-positive patients, MRI enables early detection of NPC that is endoscopically occult or negative on EGB and increases confidence that NPC has not been missed.

Discriminating between benign and malignant salivary gland tumors using diffusion-weighted imaging and intravoxel incoherent motion at 3 Tesla.

PURPOSE: The purpose of this study was to retrospectively evaluate the diagnostic performances of diffusion-weighted imaging (DWI) and intravoxel incoherent motion (IVIM) for discriminating between benign and malignant salivary gland tumors (SGTs). MATERIALS AND METHODS: Sixty-seven patients with 71 SGTs who underwent MRI examination at 3 Tesla were included. There were 34 men and 37 women with a mean age of 57 ± 17 (SD) years (age range: 20-90 years). SGTs included 21 malignant tumors (MTs) and 50 benign SGTs (33 pleomorphic adenomas [PAs] and 17 Warthin's tumors [WTs]). For each SGT, DWI and IVIM parameters, mean, skewness, and kurtosis of apparent diffusion coefficient (ADC), pure diffusion coefficient (D), pseudo-diffusion coefficient (D*) and perfusion volume fraction (f) were calculated and further compared between SGTs using univariable analysis. Areas under the curves (AUC) of receiver operating characteristic of significant parameters were compared using the Delong test. RESULTS: Significant differences in ADCmean, Dmean and D*mean were found between SGTs (P < 0.001). The highest AUC values were obtained for ADCmean (0.949) for identifying PAs and D*mean (0.985) for identifying WTs and skewness and kurtosis did not outperform mean. To discriminate benign from malignant SGTs with thresholds set to maximize Youden index, IVIM and DWI produced accuracies of 85.9% (61/71; 95% CI: 75.6-93.0) and 77.5% (55/71; 95% CI: 66.0-86.5) but misdiagnosed MTs as benign in 28.6% (6/21) and 61.9% (13/21) of SGTs, respectively. After maximizing specificity to 100% for benign SGTs, the accuracies of IVIM and DWI decreased to 76.1% (54/71; 95% CI: 64.5-85.4) and 64.8% (46/71; 95% CI: 52.5-75.8) but no MTs were misdiagnosed as benign. IVIM and DWI correctly diagnosed 66.0% (33/50) and 50.0% (25/50) of benign SGTs and 46.5% (33/71) and 35.2% (25/71) of all SGTs, respectively. CONCLUSION: IVIM is more accurate than DWI for discriminating between benign and malignant SGTs because of its advantage in detecting WTs. Thresholds set by maximizing specificity for benign SGTs may be advantageous in a clinical setting.

Radiomics Analysis in Characterization of Salivary Gland Tumors on MRI: A Systematic Review.

Radiomics analysis can potentially characterize salivary gland tumors (SGTs) on magnetic resonance imaging (MRI). The procedures for radiomics analysis were various, and no consistent performances were reported. This review evaluated the methodologies and performances of studies using radiomics analysis to characterize SGTs on MRI. We systematically reviewed studies published until July 2023, which employed radiomics analysis to characterize SGTs on MRI. In total, 14 of 98 studies were eligible. Each study examined 23-334 benign and 8-56 malignant SGTs. Least absolute shrinkage and selection operator (LASSO) was the most common feature selection method (in eight studies). Eleven studies confirmed the stability of selected features using cross-validation or bootstrap. Nine classifiers were used to build models that achieved area under the curves (AUCs) of 0.74 to 1.00 for characterizing benign and malignant SGTs and 0.80 to 0.96 for characterizing pleomorphic adenomas and Warthin's tumors. Performances were validated using cross-validation, internal, and external datasets in four, six, and two studies, respectively. No single feature consistently appeared in the final models across the studies. No standardized procedure was used for radiomics analysis in characterizing SGTs on MRIs, and various models were proposed. The need for a standard procedure for radiomics analysis is emphasized.