Imaging approach to ingested foreign bodies in the neck.

Foreign body ingestion is a common clinical occurrence worldwide, with high morbidity in the pediatric population and in adult patients with intentional attempts. Coins and button battery ingestions are more common among children. Bone impaction and swallowed dentures are usually seen in older adults. While most ingested foreign bodies pass through the gastrointestinal tract spontaneously with no complications, some require endoscopic and/or surgical intervention. Complications such as pharyngoesophageal ulceration, perforation, stricture, and deep neck infection can develop without timely diagnosis and management. The purpose of this article is to familiarize radiologists with the imaging approach to assess for characteristics and impacted locations of ingested foreign bodies in the neck.

Using Texture Analysis of Neck Computed Tomography Images to Differentiate Primary Hyperparathyroidism From Normal Controls.

OBJECTIVE: To investigate the utility of texture analysis in detecting osseous changes associated with hyperparathyroidism on neck CT examinations compared with control patients and to explore the best regions in the head and neck to evaluate changes in the trabecular architecture secondary to hyperparathyroidism. METHODS: Patients with hyperparathyroidism who underwent a 4D CT of the neck with contrast were included in this study. Age-matched control patients with no history of hyperparathyroidism who underwent a contrast-enhanced neck CT were also included. Mandibular condyles, bilateral mandibular bodies, the body of the C4 vertebra, the manubrium of the sternum, and bilateral clavicular heads were selected for analysis, and oval-shaped regions of interest were manually placed. These segmented areas were imported into an in-house developed texture analysis program, and 41 texture analysis features were extracted. A mixed linear regression model was used to compare differences in the texture analysis features contoured at each of the osseous structures between patients with hyperparathyroidism and age-matched control patients. RESULTS: A total of 30 patients with hyperparathyroidism and 30 age-matched control patients were included in this study. Statistically significant differences in texture features between patients with hyperparathyroidism and control patients in all 8 investigated osseous regions. The sternum showed the greatest number of texture features with statistically significant differences between these groups. CONCLUSIONS: Some CT texture features demonstrated statistically significant differences between patients with hyperparathyroidism and control patients. The results suggest that texture features may discriminate changes in the osseous architecture of the head and neck in patients with hyperparathyroidism.

Comparing accuracy of machine learning approaches to identifying parathyroid adenomas: Lessons and new directions.

PURPOSE: The purpose of this investigation is to understand the accuracy of machine learning techniques to detect biopsy-proven adenomas from similar appearing lymph nodes and factors that influence accuracy by comparing support vector machine (SVM) and bidirectional Long short-term memory (Bi-LSTM) analyses. This will provide greater insight into how these tools could integrate multidimensional data and aid the detection of parathyroid adenomas consistently and accurately. METHODS: Ninety-nine patients were identified; 93 4D-CTs of patients with pathology-proven parathyroid adenomas were reviewed; 94 parathyroid adenomas and 112 lymph nodes were analyzed. A 2D slice through the lesions in each phase was used to perform sequence classification with ResNet50 as the pre-trained network to construct the Bi-LSTM model, and the mean enhancement curves were used to form an SVM model. The model characteristics and accuracy were calculated for the training and validation data sets. RESULTS: On the training data, the area under the curve (AUC) of the Bi-LSTM was 0.99, while the SVM was 0.95 and statistically significant on the DeLong test. The overall accuracy of the Bi-LSTM on the validation data set was 92 %, while the SVM was 88 %. The accuracy for parathyroid adenomas specifically was 93 % for the Bi-LSTM and 83 % for the SVM model. CONCLUSION: Enhancement characteristics are a distinguishing feature that accurately identifies parathyroid adenomas alone. The Bi-LSTM performs statistically better in identifying parathyroid adenomas than the SVM analysis when using both morphologic and enhancement information to distinguish between parathyroid adenomas and lymph nodes. SUMMARY STATEMENT: The Bi-LSTM more accurately identifies parathyroid adenomas than the SVM analysis, which uses both morphologic and enhancement information to distinguish between parathyroid adenomas and lymph nodes, performs statistically better.

Fully automated 3D machine learning model for HPV status characterization in oropharyngeal squamous cell carcinomas based on CT images.

BACKGROUND: Human papillomavirus (HPV) status plays a major role in predicting oropharyngeal squamous cell carcinoma (OPSCC) survival. This study assesses the accuracy of a fully automated 3D convolutional neural network (CNN) in predicting HPV status using CT images. METHODS: Pretreatment CT images from OPSCC patients were used to train a 3D DenseNet-121 model to predict HPV-p16 status. Performance was evaluated by the ROC Curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. RESULTS: The network achieved a mean AUC of 0.80 ± 0.06. The best-preforming fold had a sensitivity of 0.86 and specificity of 0.92 at the Youden's index. The PPV, NPV, and F1 scores are 0.97, 0.71, and 0.82, respectively. CONCLUSIONS: A fully automated CNN can characterize the HPV status of OPSCC patients with high sensitivity and specificity. Further refinement of this algorithm has the potential to provide a non-invasive tool to guide clinical management.

Primary Multiparametric Quantitative Brain MRI: State-of-the-Art Relaxometric and Proton Density Mapping Techniques.

This review on brain multiparametric quantitative MRI (MP-qMRI) focuses on the primary subset of quantitative MRI (qMRI) parameters that represent the mobile ("free") and bound ("motion-restricted") proton pools. Such primary parameters are the proton densities, relaxation times, and magnetization transfer parameters. Diffusion qMRI is also included because of its wide implementation in complete clinical MP-qMRI application. MP-qMRI advances were reviewed over the past 2 decades, with substantial progress observed toward accelerating image acquisition and increasing mapping accuracy. Areas that need further investigation and refinement are identified as follows: (a) the biologic underpinnings of qMRI parameter values and their changes with age and/or disease and (b) the theoretical limitations implicitly built into most qMRI mapping algorithms that do not distinguish between the different spatial scales of voxels versus spin packets, the central physical object of the Bloch theory. With rapidly improving image processing techniques and continuous advances in computer hardware, MP-qMRI has the potential for implementation in a wide range of clinical applications. Currently, three emerging MP-qMRI applications are synthetic MRI, macrostructural qMRI, and microstructural tissue modeling.

Quantitative MRI Characterization of the Extremely Preterm Brain at Adolescence: Atypical versus Neurotypical Developmental Pathways.

Background Extremely preterm (EP) birth is associated with higher risks of perinatal white matter (WM) injury, potentially causing abnormal neurologic and neurocognitive outcomes. MRI biomarkers distinguishing individuals with and without neurologic disorder guide research on EP birth antecedents, clinical correlates, and prognoses. Purpose To compare multiparametric quantitative MRI (qMRI) parameters of EP-born adolescents with autism spectrum disorder, cerebral palsy, epilepsy, or cognitive impairment (ie, atypically developing) with those without (ie, neurotypically developing), characterizing sex-stratified brain development. Materials and Methods This prospective multicenter study included individuals aged 14-16 years born EP (Extremely Low Gestational Age Newborns-Environmental Influences on Child Health Outcomes Study, or ELGAN-ECHO). Participants underwent 3.0-T MRI evaluation from 2017 to 2019. qMRI outcomes were compared for atypically versus neurotypically developing adolescents and for girls versus boys. Sex-stratified multiple regression models were used to examine associations between spatial entropy density (SEd) and T1, T2, and cerebrospinal fluid (CSF)-normalized proton density (nPD), and between CSF volume and T2. Interaction terms modeled differences in slopes between atypically versus neurotypically developing adolescents. Results A total of 368 adolescents were classified as 116 atypically (66 boys) and 252 neurotypically developing (125 boys) participants. Atypically versus neurotypically developing girls had lower nPD (mean, 557 10 × percent unit [pu] ± 46 [SD] vs 573 10 × pu ± 43; P = .04), while atypically versus neurotypically developing boys had longer T1 (814 msec ± 57 vs 789 msec ± 82; P = .01). Atypically developing girls versus boys had lower nPD and shorter T2 (eg, in WM, 557 10 × pu ± 46 vs 580 10 × pu ± 39 for nPD [P = .006] and 86 msec ± 3 vs 88 msec ± 4 for T2 [P = .003]). Atypically versus neurotypically developing boys had a more moderate negative association between T1 and SEd (slope, -32.0 msec per kB/cm3 [95% CI: -49.8, -14.2] vs -62.3 msec per kB/cm3 [95% CI: -79.7, -45.0]; P = .03). Conclusion Atypically developing participants showed sexual dimorphisms in the cerebrospinal fluid-normalized proton density (nPD) and T2 of both white matter (WM) and gray matter. Atypically versus neurotypically developing girls had lower WM nPD, while atypically versus neurotypically developing boys had longer WM T1 and more moderate T1 associations with microstructural organization in WM. © RSNA, 2022 Online supplemental material is available for this article.

Synthesis of Electromagnetic Wave-Absorbing Co-Ni Alloys and Co-Ni Core-Shell Structured Nanoparticles.

Co-Ni alloy nanoparticles, a potential candidate for microwave absorption material, were successfully synthesized by tuning the reduction timing of Co and Ni ions by introducing oleylamine as a complexing agent and 1-heptanol as a reducing solvent. The formation mechanism elucidated using time-resolved sampling and in situ X-ray absorption spectroscopy (XAS) and ultraviolet-visible (UV-vis) spectrophotometry measurements suggested that the delay in the reduction of Co ions via complexation with oleylamine facilitated the co-reduction of Co with Ni ions and led to the formation of Co-Ni alloys. The successful synthesis of Co-Ni alloys experimentally confirmed the differences in magnetic properties between alloy and core-shell structured Co50Ni50 particles. Further, the syntheses of Co-Ni alloys with different compositions were also possible using the above technique. In addition, the microwave absorption properties were measured using the free-space method utilizing a vector network analyzer of Co50Ni50─polyethylene composite with different sheet thicknesses. A reflection loss (RL) value of -25.7 dB at 13.6 GHz for the alloy structure was more significant than the core-shell counterpart. The above values are high compared to results reported in the past. The validity of the measurements was confirmed by utilizing the parameter retrieval method to extract permittivity and permeability from the scattering parameter (S) and recalculation of the RL as a function of frequency.

Normal Variants of the Oral and Maxillofacial Region: Mimics and Pitfalls.

A normal variant is defined as an incidental, often asymptomatic, imaging finding that mimics a true pathologic condition. Given the complex anatomy and wide variety of normal variants in the oral and maxillofacial region, a thorough understanding of commonly encountered normal variants in this region is essential to avoid misinterpretation and unnecessary further imaging or interventions. Moreover, familiarity with normal variants that are known to become symptomatic at times is necessary to facilitate further workup and guide the treatment plan. Intraoral radiography and panoramic radiography, which are unique to oral and maxillofacial radiology, provide two-dimensional (2D) images. Hence, the overlapping of structures or the displacement of the tomographic layer on images can confuse radiologists. It is crucial to understand the principle of 2D imaging to avoid being confused by ghost images or optical illusions. In addition, understanding the normal development of the maxillofacial region is essential when interpreting maxillofacial images in children or young adults because the anatomy may be quite different from that of mature adults. Knowledge of changes in the jaw bone marrow and each tissue's growth rate is essential. It is also necessary to know when the tooth germ begins to calcify and the tooth erupts for diagnostic imaging of the maxillofacial region. The authors describe imaging findings and clinical manifestations of common normal variants in the oral and maxillofacial region, divided into four parts: the maxilla, mandible, tooth, and temporomandibular joint, and discuss the imaging approach used to differentiate normal variants from true pathologic conditions. Online supplemental material is available for this article. ©RSNA, 2022.

A tissue-engineered, decellularized, connective tissue membrane for allogeneic arterial patch implantation.

BACKGROUND: We have previously applied in vivo tissue-engineered vascular grafts constructed in patients' subcutaneous spaces. However, since the formation of these vascular grafts depends on host health, their application is challenging in patients with suppressed regenerative ability. Therefore, the allogeneic implantation of grafts from healthy donors needs to be evaluated. This study aimed to fabricate allogeneic cardiovascular grafts in animals. MATERIALS AND METHODS: Silicone rod molds were implanted into subcutaneous pouches in dogs; the implants, along with surrounding connective tissues, were harvested after four weeks. Tubular connective tissues were decellularized and stored before they were cut open, trimmed to elliptical sheets, and implanted into the common carotid arteries of another dog as vascular patches (n = 6); these were resected and histologically evaluated at 1, 2, and 4 weeks after implantation. RESULTS: No aneurysmal changes were observed by echocardiography. Histologically, we observed neointima formation on the luminal graft surface and graft wall cell infiltration. At 2 and 4 weeks after implantation, α-SMA-positive cells were observed in the neointima and graft wall. At 4 weeks after implantation, the endothelial lining was observed at the grafts' luminal surfaces. CONCLUSION: Our data suggest that decellularized connective tissue membranes can be prepared and stored for later use as allogeneic cardiovascular grafts.

State of the Art: Venous Causes of Pulsatile Tinnitus and Diagnostic Considerations Guiding Endovascular Therapy.

Venous variants and pathologic abnormalities are the most common causes of pulsatile tinnitus. These conditions include causes of turbulence within normally located veins and sinuses, and abnormally enlarged or abnormally located veins in close transmissive proximity to the conductive auditory pathway. Such disorders include pathologic abnormalities of the lateral sinus (transverse sinus stenosis and sigmoid sinus wall anomalies), abnormalities and variants of the emissary veins, and anomalies of the jugular bulb and jugular vein. Despite being the most common causes for pulsatile tinnitus, venous variants and pathologic abnormalities are often overlooked in the workup of pulsatile tinnitus. Such oversights can result in delayed patient care and prolonged patient discomfort. Advances in both cerebrovascular imaging and endovascular techniques allow for improved diagnostic accuracy and an increasing range of endovascular therapeutic options to address pulsatile tinnitus. This review illustrates the venous causes of pulsatile tinnitus and demonstrates the associated endovascular treatment. © RSNA, 2021.

Implementation of Institutional Triaging Algorithms Decreases Head and Neck MDCT Use in Blunt Trauma.

Background Multidetector CT (MDCT) enables rapid and accurate diagnosis of head and neck (HN) injuries in patients with blunt trauma (BT). However, MDCT is overused, and appropriate selection of patients for imaging could improve workflow. Purpose To investigate the effect of implementing clinical triaging algorithms on use of MDCT in the HN in patients who have sustained BT. Materials and Methods In this retrospective study, patients aged 15 years or older with BT admitted between October 28, 2007, and December 31, 2013, were included. Patients were divided into pre- and postalgorithm groups. The institutional trauma registry and picture archiving and communication system reports were reviewed to determine which patients underwent MDCT of the head, MDCT of the cervical spine (CS), and MDCT angiography of the HN at admission and whether these examinations yielded positive results. Injury Severity Score, Acute Physiology and Chronic Health Evaluation II score (only those patients in the intensive care unit), length of hospital stay (LOS), length of intensive care unit stay (ICULOS), and mortality were obtained from the trauma registry. Results A total of 8999 patients (mean age, 45 years ± 20 [standard deviation]; age range, 15-101 years; 6027 male) were included in this study. A lower percentage of the postalgorithm group versus the prealgorithm group underwent MDCT of the head (55.8% [2774 of 4969 patients]; 95% CI: 54.4, 57.2 vs 64.2% [2589 of 4030 patients]; 95% CI: 62.8, 65.7; P < .001) and CS (49.4% [2452 of 4969 patients]; 95% CI: 48.0, 50.7 vs 60.5% [2438 of 4030 patients]; 95% CI: 59.0, 62.0; P < .001) but not MDCT angiography of the HN (9.7% [480 of 4969 patients]; 95% CI: 8.9, 10.5 vs 9.8% [393 of 4030 patients]; 95% CI: 8.9, 10.7; P > .99). Pre- versus postalgorithm groups did not differ in LOS (mean, 4.8 days ± 7.1 vs 4.5 days ± 7.1, respectively; P = .42), ICULOS (mean, 4.6 days ± 6.6 vs 4.8 days ± 6.7, respectively; P > .99), or mortality (2.9% [118 of 4030 patients]; 95% CI: 2.5, 3.5; vs 2.8% [141 of 4969 patients]; 95% CI: 2.4, 3.3; respectively; P > .99). Conclusion Implementation of a clinical triaging algorithm resulted in decreased use of multidetector CT of the head and cervical spine in patients who experienced blunt trauma, without increased adverse outcomes. © RSNA, 2021 See also the editorial by Munera and Martin in this issue.

Prediction of the local treatment outcome in patients with oropharyngeal squamous cell carcinoma using deep learning analysis of pretreatment FDG-PET images.

BACKGROUND: This study aimed to assess the utility of deep learning analysis using pretreatment FDG-PET images to predict local treatment outcome in oropharyngeal squamous cell carcinoma (OPSCC) patients. METHODS: One hundred fifty-four OPSCC patients who received pretreatment FDG-PET were included and divided into training (n = 102) and test (n = 52) sets. The diagnosis of local failure and local progression-free survival (PFS) rates were obtained from patient medical records. In deep learning analyses, axial and coronal images were assessed by three different architectures (AlexNet, GoogLeNET, and ResNet). In the training set, FDG-PET images were analyzed after the data augmentation process for the diagnostic model creation. A multivariate clinical model was also created using a binomial logistic regression model from a patient's clinical characteristics. The test data set was subsequently analyzed for confirmation of diagnostic accuracy. Assessment of local PFS rates was also performed. RESULTS: Training sessions were successfully performed with an accuracy of 74-89%. ROC curve analyses revealed an AUC of 0.61-0.85 by the deep learning model in the test set, whereas it was 0.62 by T-stage, 0.59 by clinical stage, and 0.74 by a multivariate clinical model. The highest AUC (0.85) was obtained with deep learning analysis of ResNet architecture. Cox proportional hazards regression analysis revealed deep learning-based classification by a multivariate clinical model (P < .05), and ResNet (P < .001) was a significant predictor of the treatment outcome. In the Kaplan-Meier analysis, the deep learning-based classification divided the patient's local PFS rate better than the T-stage, clinical stage, and a multivariate clinical model. CONCLUSIONS: Deep learning-based diagnostic model with FDG-PET images indicated its possibility to predict local treatment outcomes in OPSCCs.

CT-based assessment of laryngeal fracture patterns and associated soft tissue abnormality.

OBJECTIVE: Acute traumatic injuries to the larynx, including fractures of the hyoid bone, cricoid, and thyroid cartilage, are uncommon injuries. The purpose of this study was to assess fracture and soft tissue patterns associated with laryngeal trauma. METHODS: This was a retrospective review of patients with laryngeal fractures who presented to two level I trauma centers and underwent CT imaging. Imaging findings, including fractures of the cartilaginous structures of the larynx and hyoid bone, and soft tissue abnormalities including focal hematoma, edema with non-focal hemorrhage, and additional penetrating injuries were recorded. Frequencies of fracture patterns were recorded. RESULTS: Thyroid cartilage fractures were most frequently observed occurring in 45/55 patients, followed by cricoid fractures in 13/55 patients. Hyoid fractures were encountered in 8/55 patients. Multi-site fractures were observed in 12/55 patients with thyroid-cricoid fractures occurring in 8/12 patients, followed by thyroid-hyoid fractures in 2/12 patients. Most multi-site fractures occurred in association with focal supraglottic hematomas (10/12), supraglottic edema and non-focal hemorrhage (11/12), and focal subglottic hematoma (5/12). All 13 cricoid fractures occurred with either focal supraglottic hematoma (7), focal subglottic hematoma (4), or edema with non-focal hemorrhage (13). CONCLUSIONS: Thyroid cartilage fractures were the most frequently encountered fracture, followed by cricoid cartilage fractures. Cricoid fractures always occurred with soft tissue abnormalities. Recognition of fracture patterns in the setting of laryngeal trauma and associated patterns of soft tissue injury is important for practicing radiologists for early diagnosis of these conditions and reduction of associated morbidity. KEY POINTS: • Acute fractures to the larynx may be isolated fractures or occur as multi-focal fractures. • Thyroid cartilage fractures are the most frequent fractures followed by cricoid cartilage fractures. • Cricoid cartilage fractures always occurred in association with soft tissue abnormalities.

Utility of deep learning for the diagnosis of otosclerosis on temporal bone CT.

OBJECTIVE: Diagnosis of otosclerosis on temporal bone CT images is often difficult because the imaging findings are frequently subtle. Our aim was to assess the utility of deep learning analysis in diagnosing otosclerosis on temporal bone CT images. METHODS: A total of 198 temporal bone CT images were divided into the training set (n = 140) and the test set (n = 58). The final diagnosis (otosclerosis-positive or otosclerosis-negative) was determined by an experienced senior radiologist who carefully reviewed all 198 temporal bone CT images while correlating with clinical and intraoperative findings. In deep learning analysis, a rectangular target region that includes the area of the fissula ante fenestram was extracted and fed into the deep learning training sessions to create a diagnostic model. Transfer learning was used with the deep learning model architectures of AlexNet, VGGNet, GoogLeNet, and ResNet. The test data set was subsequently analyzed using these models and by another radiologist with 3 years of experience in neuroradiology following completion of a neuroradiology fellowship. The performance of the radiologist and the deep learning models was determined using the senior radiologist's diagnosis as the gold standard. RESULTS: The diagnostic accuracies were 0.89, 0.72, 0.81, 0.86, and 0.86 for the subspecialty trained radiologist, AlexNet, VGGNet, GoogLeNet, and ResNet, respectively. The performances of VGGNet, GoogLeNet, and ResNet were not significantly different compared to the radiologist. In addition, GoogLeNet and ResNet demonstrated non-inferiority compared to the radiologist. CONCLUSIONS: Deep learning technique may be a useful supportive tool in diagnosing otosclerosis on temporal bone CT. KEY POINTS: • Deep learning can be a helpful tool for the diagnosis of otosclerosis on temporal bone CT. • Deep learning analyses with GoogLeNet and ResNet demonstrate non-inferiority when compared to the subspecialty trained radiologist. • Deep learning may be particularly useful in medical institutions without experienced radiologists.

CT of Skull Base Fractures: Classification Systems, Complications, and Management.

As advances in prehospital and early hospital care improve survival of the head-injured patient, radiologists are increasingly charged with understanding the myriad skull base fracture management implications conferred by CT. Successfully parlaying knowledge of skull base anatomy and fracture patterns into precise actionable clinical recommendations is a challenging task. The authors aim to provide a pragmatic overview of CT for skull base fractures within the broader context of diagnostic and treatment planning algorithms. Laterobasal, frontobasal, and posterior basal fracture patterns are emphasized. CT often plays a complementary, supportive, or confirmatory role in management of skull base fractures in conjunction with results of physical examination, laboratory testing, and neurosensory evaluation. CT provides prognostic information about short- and long-term risk of cerebrospinal fluid (CSF) leak, encephalocele, meningitis, facial nerve paralysis, hearing and vision loss, cholesteatoma, vascular injuries, and various cranial nerve palsies and syndromes. The radiologist should leverage understanding of specific strengths and limitations of CT to anticipate next steps in the skull base fracture management plan. Additional imaging is warranted to clarify ambiguity (particularly for potential sources of CSF leak); in other cases, clinical and CT criteria alone are sufficient to determine the need for intervention and the choice of surgical approach. The radiologist should be able to envision stepping into a multidisciplinary planning discussion and engaging neurotologists, neuro-ophthalmologists, neurosurgeons, neurointerventionalists, and facial reconstructive surgeons to help synthesize an optimal management plan after reviewing the skull base CT findings at hand. Online supplemental material is available for this article. ©RSNA, 2021.

Cystic cervical lymph nodes of papillary thyroid carcinoma, tuberculosis and human papillomavirus positive oropharyngeal squamous cell carcinoma: utility of deep learning in their differentiation on CT.

OBJECTIVES: Cervical lymph nodes with internal cystic changes are seen with several pathologies, including papillary thyroid carcinoma (PTC), tuberculosis (TB), and HPV-positive oropharyngeal squamous cell carcinoma (HPV+OPSCC). Differentiating these lymph nodes is difficult in the absence of a known primary tumor or reliable medical history. In this study, we assessed the utility of deep learning in differentiating the pathologic lymph nodes of PTC, TB, and HPV+OPSCC on CT. METHODS: A total of 173 lymph nodes (55 PTC, 58 TB, and 60 HPV+OPSCC) were selected based on pathology records and suspicious morphological features. These lymph nodes were divided into the training set (n = 131) and the test set (n = 42). In deep learning analysis, JPEG lymph node images were extracted from the CT slice that included the largest area of each node and fed into a deep learning training session to create a diagnostic model. Transfer learning was used with the deep learning model architecture of ResNet-101. Using the test set, the diagnostic performance of the deep learning model was compared against the histopathological diagnosis and to the diagnostic performances of two board-certified neuroradiologists. RESULTS: Diagnostic accuracy of the deep learning model was 0.76 (=32/42), whereas those of Radiologist 1 and Radiologist 2 were 0.48 (=20/42) and 0.41 (=17/42), respectively. Deep learning derived diagnostic accuracy was significantly higher than both of the two neuroradiologists (P < 0.01, respectively). CONCLUSION: Deep learning algorithm holds promise to become a useful diagnostic support tool in interpreting cervical lymphadenopathy.

Deep learning analysis using FDG-PET to predict treatment outcome in patients with oral cavity squamous cell carcinoma.

OBJECTIVE: To assess the utility of deep learning analysis using 18F-fluorodeoxyglucose (FDG) uptake by positron emission tomography (PET/CT) to predict disease-free survival (DFS) in patients with oral cavity squamous cell carcinoma (OCSCC). METHODS: One hundred thirteen patients with OCSCC who received pretreatment FDG-PET/CT were included. They were divided into training (83 patients) and test (30 patients) sets. The diagnosis of treatment control/failure and the DFS rate were obtained from patients' medical records. In deep learning analyses, three planes of axial, coronal, and sagittal FDG-PET images were assessed by ResNet-101 architecture. In the training set, image analysis was performed for the diagnostic model creation. The test data set was subsequently analyzed for confirmation of diagnostic accuracy. T-stage, clinical stage, and conventional FDG-PET parameters (the maximum and mean standardized uptake value (SUVmax and SUVmean), heterogeneity index, metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were also assessed with determining the optimal cutoff from training dataset and then validated their diagnostic ability from test dataset. RESULTS: In dividing into patients with treatment control and failure, the highest diagnostic accuracy of 0.8 was obtained using deep learning classification, with a sensitivity of 0.8, specificity of 0.8, positive predictive value of 0.89, and negative predictive value of 0.67. In the Kaplan-Meier analysis, the DFS rate was significantly different only with the analysis of deep learning-based classification (p < .01). CONCLUSIONS: Deep learning-based diagnosis with FDG-PET images may predict treatment outcome in patients with OCSCC. KEY POINTS: • Deep learning-based diagnosis of FDG-PET images showed the highest diagnostic accuracy to predict the treatment outcome in patients with oral cavity squamous cell carcinoma. • Deep learning-based diagnosis was shown to differentiate patients between good and poor disease-free survival more clearly than conventional T-stage, clinical stage, and conventional FDG-PET-based parameters.

Determining the optimal osteotomy distance with the fibula free flap in mandibular reconstruction.

OBJECTIVE: Fibula free tissue transfer is a common and reliable method for mandibular reconstruction. Functional outcomes from this procedure are dependent on the successful union of the osseous segments postoperatively. This study was conducted to define the maximum gap-size criteria for osseous union to occur at osteotomy sites in fibula free flap reconstruction of the mandible. STUDY DESIGN: Retrospective chart review. SETTING: Tertiary care academic center. SUBJECTS AND METHODS: A retrospective chart review of computed tomography and medical records was conducted on patients who underwent fibula free flap surgery and had imaging of the mandible at <3 months and >6 months after surgery. Distances between osteotomies were measured and evaluated for interval healing. Secondary data included subject age, sex, smoking status, diabetes, number of osteotomies, complications, and adjuvant therapy. RESULTS: Thirty-eight osteotomy sites were analyzed from thirteen subjects and a total of 190 measurements were made. The mean gap size at the first scan that demonstrated union by the second scan interval was 1.31 mm and mean gap size demonstrating non-union was 2.55 mm (p < 0.01). Complication rate, number of osetotomies, adjuvant therapy, or medical co-morbidities did not significantly affect rates of union. CONCLUSIONS: In this study, osseous union was achieved with a mean osteotomy gap size of 1.31 mm. The data suggests that distances between ossesous segments >2 .55mm have a higher risk of non-union. We believe the information from this study will help augment current and future techniques in the field of mandible reconstruction.

Cerebral Venous Sinus Thromboses in Patients with SARS-CoV-2 Infection: Three Cases and a Review of the Literature.

INTRODUCTION: Early studies suggest that acute cerebrovascular events may be common in patients with coronavirus disease 2019 (COVID-19) and may be associated with a high mortality rate. Most cerebrovascular events described have been ischemic strokes, but both intracerebral hemorrhage and rarely cerebral venous sinus thrombosis (CVST) have also been reported. The diagnosis of CVST can be elusive, with wide-ranging and nonspecific presenting symptoms that can include headache or altered sensorium alone. OBJECTIVE: To describe the presentation, barriers to diagnosis, treatment, and outcome of CVST in patients with COVID-19. METHODS: We abstracted data on all patients diagnosed with CVST and COVID-19 from March 1 to August 9, 2020 at Boston Medical Center. Subsequently, we reviewed the literature and extracted all published cases of CVST in patients with COVID-19 from January 1, 2020 through August 9, 2020 and included all studies with case descriptions. RESULTS: We describe the clinical features and management of CVST in 3 women with COVID-19 who developed CVST days to months after initial COVID-19 symptoms. Two patients presented with encephalopathy and without focal neurologic deficits, while one presented with visual symptoms. All patients were treated with intravenous hydration and anticoagulation. None suffered hemorrhagic complications, and all were discharged home. We identified 12 other patients with CVST in the setting of COVID-19 via literature search. There was a female predominance (54.5%), most patients presented with altered sensorium (54.5%), and there was a high mortality rate (36.4%). CONCLUSIONS: During this pandemic, clinicians should maintain a high index of suspicion for CVST in patients with a recent history of COVID-19 presenting with non-specific neurological symptoms such as headache to provide expedient management and prevent complications. The limited data suggests that CVST in COVID-19 is more prevalent in females and may be associated with high mortality.

Increased Apparent Diffusion Coefficient Values of Masticatory Muscles on Diffusion-Weighted Magnetic Resonance Imaging in Patients With Temporomandibular Joint Disorder and Unilateral Pain.

PURPOSE: Myalgia of the masticatory muscles is difficult to evaluate quantitatively. The purpose of the present study was to quantitatively assess myalgia of the masticatory muscles in patients with temporomandibular disorders (TMDs) using the apparent diffusion coefficient (ADC) on diffusion-weighted magnetic resonance imaging (MRI). PATIENTS AND METHODS: Patients who had undergone MRI with clinically diagnosed TMDs according to the criteria of the American Academy of Orofacial Pain and unilateral temporomandibular joint pain from March 2015 to January 2017 were prospectively enrolled. The MRI techniques used included axial diffusion-weighted imaging (DWI) and short T1 inversion recovery imaging through the neck to the skull base. The regions of interest were drawn to completely include the right and left lateral pterygoid muscles, medial pterygoid muscles, and masseter muscles on a slice demonstrating the largest area of each muscle on the ADC map. We compared each masticatory muscle of the pain side with those of the contralateral side without pain. RESULTS: A total of 106 patients with TMD had met the inclusion criteria (18 males, 88 females; mean age, 48.7 years; range, 16 to 80). The mean ADC values of the masticatory muscles of the pain side were significantly greater than those of the no-pain sides (P < .01), as were those for the lateral pterygoid muscles (1.35 ± 0.79 × 10-3 mm2/second vs 1.13 ± 0.77 × 10-3 mm2/second), medial pterygoid muscles (1.28 ± 0.46 × 10-3 mm2/second vs 1.05 ± 0.69 × 10-3 mm2/second), masseter muscles (1.33 ± 0.78 × 10-3 mm2/second vs 1.09 ± 0.64 × 10-3 mm2/second). CONCLUSIONS: The ADC values of the masticatory muscles on the pain side were significantly greater than those of the contralateral side without pain. Our results suggest that DWI could be used to assess myalgia of the masticatory muscles quantitatively.