Improved optic nerve visualization and treatment planning through a dedicated optic nerve MRI protocol.

OBJECTIVE: This study describes an innovative optic nerve MRI protocol for better delineating optic nerve anatomy from neighboring pathology. METHODS: Twenty-two patients undergoing MRI examination of the optic nerve with the dedicated protocol were identified and included for analysis of imaging, surgical strategy, and outcomes. T2-weighted and fat-suppressed T1-weighted gadolinium-enhanced images were acquired perpendicular and parallel to the long axis of the optic nerve to achieve en face and in-line views along the course of the nerve. RESULTS: Dedicated optic nerve MRI sequences provided enhanced visualization of the nerve, CSF within the nerve sheath, and local pathology. Optic nerve sequences leveraged the "CSF ring" within the optic nerve sheath to create contrast between pathology and normal tissue, highlighting areas of compression. Tumor was readily tracked along the longitudinal axis of the nerve by images obtained parallel to the nerve. The findings augmented treatment planning. CONCLUSIONS: The authors present a dedicated optic nerve MRI protocol that is simple to use and affords improved cross-sectional and longitudinal visualization of the nerve, surrounding CSF, and pathology. This improved visualization enhances radiological evaluation and treatment planning for optic nerve lesions.

Surgical Navigation in the Anterior Skull Base Using 3-Dimensional Endoscopy and Surface Reconstruction.

Importance: Image guidance is an important adjunct for endoscopic sinus and skull base surgery. However, current systems require bulky external tracking equipment, and their use can interrupt efficient surgical workflow. Objective: To evaluate a trackerless surgical navigation system using 3-dimensional (3D) endoscopy and simultaneous localization and mapping (SLAM) algorithms in the anterior skull base. Design, Setting, and Participants: This interventional deceased donor cohort study and retrospective clinical case study was conducted at a tertiary academic medical center with human deceased donor specimens and a patient with anterior skull base pathology. Exposures: Participants underwent endoscopic endonasal transsphenoidal dissection and surface model reconstruction from stereoscopic video with registration to volumetric models segmented from computed tomography (CT) and magnetic resonance imaging. Main Outcomes and Measures: To assess the fidelity of surface model reconstruction and accuracy of surgical navigation and surface-CT model coregistration, 3 metrics were calculated: reconstruction error, registration error, and localization error. Results: In deceased donor models (n = 9), high-fidelity surface models of the posterior wall of the sphenoid sinus were reconstructed from stereoscopic video and coregistered to corresponding volumetric CT models. The mean (SD; range) reconstruction, registration, and localization errors were 0.60 (0.24; 0.36-0.93), 1.11 (0.49; 0.71-1.56) and 1.01 (0.17; 0.78-1.25) mm, respectively. In a clinical case study of a patient who underwent a 3D endoscopic endonasal transsphenoidal resection of a tubercular meningioma, a high-fidelity surface model of the posterior wall of the sphenoid was reconstructed from intraoperative stereoscopic video and coregistered to a volumetric preoperative fused CT magnetic resonance imaging model with a root-mean-square error of 1.38 mm. Conclusions and Relevance: The results of this study suggest that SLAM algorithm-based endoscopic endonasal surgery navigation is a novel, accurate, and trackerless approach to surgical navigation that uses 3D endoscopy and SLAM-based algorithms in lieu of conventional optical or electromagnetic tracking. While multiple challenges remain before clinical readiness, a SLAM algorithm-based endoscopic endonasal surgery navigation system has the potential to improve surgical efficiency, economy of motion, and safety.

Time-Saving 3D MR Imaging Protocols with Millimeter and Submillimeter Isotropic Spatial Resolution for Face and Neck Imaging as Implemented at a Single-Site Major Referral Center.

MR imaging has become the routine technique for staging nasopharyngeal carcinoma, evaluating perineural tumor spread, and detecting cartilage invasion in laryngeal carcinoma. However, these protocols traditionally require in the range of 25 to 35 minutes of acquisition time. 3D sequences offer the potential advantage of time savings through the acquisition of 1-mm or submillimeter resolution isotropic data followed by multiplanar reformats that require no further imaging time. We have iteratively optimized vendor product 3D T1-weighted MR imaging sequences for morphologic face and neck imaging, reducing the average acquisition time of our 3T protocols by 9 minutes 57 seconds (40.9%) and of our 1.5T protocols by 9 minutes 5 seconds (37.0%), while simultaneously maintaining or improving spatial resolution. This clinical report describes our experience optimizing and implementing commercially available 3D T1-weighted MR imaging pulse sequence protocols for clinical face and neck MR imaging examinations using illustrative cases. We provide protocol details to allow others to replicate our implementations, and we report challenges we faced along with our solutions.

Actionability of Recommendations for Additional Imaging in Head and Neck Radiology.

PURPOSE: The aims of this study were to measure the actionability of recommendations for additional imaging (RAIs) in head and neck CT and MRI, for which there is a near complete absence of best practices or guidelines; to identify the most common recommendations; and to assess radiologist factors associated with actionability. METHODS: All head and neck CT and MRI radiology reports across a multi-institution, multipractice health care system from June 1, 2021, to May 31, 2022, were retrospectively reviewed. The actionability of RAIs was scored using a validated taxonomy. The most common RAIs were identified. Actionability association with radiologist factors (gender, years out of training, fellowship training, practice type) and with trainees was measured using a mixed-effects model. RESULTS: Two hundred nine radiologists generated 60,543 reports, of which 7.2% (n = 4,382) contained RAIs. Only 3.9% of RAIs (170 of 4,382) were actionable. More than 60% of RAIs were for eight examinations: thyroid ultrasound (14.1%), neck CT (12.6%), brain MRI (6.9%), chest CT (6.5%), neck CT angiography (5.5%), temporal bone CT (5.3%), temporal bone MRI (5.2%), and pituitary MRI (4.6%). Radiologists >23 years out of training (odds ratio, 0.39; 95% confidence interval, 0.15-1.02; P = .05) and community radiologists (odds ratio, 0.53; 95% confidence interval, 0.22-1.31; P = .17) had substantially lower estimated odds of making actionable RAIs than radiologists <7 years out of training and academic radiologists, respectively. CONCLUSIONS: The studied radiologists rarely made actionable RAIs, which makes it difficult to identify and track clinically necessary RAIs to timely performance. Multifaceted quality improvement initiatives including peer comparisons, clinical decision support at the time of reporting, and the development of evidence-based best practices, may help improve tracking and timely performance of clinically necessary RAIs.

Time-Saving 3D MR Imaging Protocols with Millimeter and Submillimeter Isotropic Spatial Resolution for Face and Neck Imaging as Implemented at a Single-Site Major Referral Center.

MR imaging has become the routine technique for staging nasopharyngeal carcinoma, evaluating perineural tumor spread, and detecting cartilage invasion in laryngeal carcinoma. However, these protocols traditionally require in the range of 25 to 35 minutes of acquisition time. 3D sequences offer the potential advantage of time savings through the acquisition of 1-mm or submillimeter resolution isotropic data followed by multiplanar reformats that require no further imaging time. We have iteratively optimized vendor product 3D T1-weighted MR imaging sequences for morphologic face and neck imaging, reducing the average acquisition time of our 3T protocols by 9 minutes 57 seconds (40.9%) and of our 1.5T protocols by 9 minutes 5 seconds (37.0%), while simultaneously maintaining or improving spatial resolution. This clinical report describes our experience optimizing and implementing commercially available 3D T1-weighted MR imaging pulse sequence protocols for clinical face and neck MR imaging examinations using illustrative cases. We provide protocol details to allow others to replicate our implementations, and we report challenges we faced along with our solutions.

Recommendations for Additional Imaging on Head and Neck Imaging Examinations: Interradiologist Variation and Associated Factors.

BACKGROUND. A paucity of relevant guidelines may lead to pronounced variation among radiologists in issuing recommendations for additional imaging (RAI) for head and neck imaging. OBJECTIVE. The purpose of this article was to explore associations of RAI for head and neck imaging examinations with examination, patient, and radiologist factors and to assess the role of individual radiologist-specific behavior in issuing such RAI. METHODS. This retrospective study included 39,200 patients (median age, 58 years; 21,855 women, 17,315 men, 30 with missing sex information) who underwent 39,200 head and neck CT or MRI examinations, interpreted by 61 radiologists, from June 1, 2021, through May 31, 2022. A natural language processing (NLP) tool with manual review of NLP results was used to identify RAI in report impressions. Interradiologist variation in RAI rates was assessed. A generalized mixed-effects model was used to assess associations between RAI and examination, patient, and radiologist factors. RESULTS. A total of 2943 (7.5%) reports contained RAI. Individual radiologist RAI rates ranged from 0.8% to 22.0% (median, 7.1%; IQR, 5.2-10.2%), representing a 27.5-fold difference between minimum and a maximum values and 1.8-fold difference between 25th and 75th percentiles. In multivariable analysis, RAI likelihood was higher for CTA than for CT examinations (OR, 1.32), for examinations that included a trainee in report generation (OR, 1.23), and for patients with self-identified race of Black or African American versus White (OR, 1.25); was lower for male than female patients (OR, 0.90); and was associated with increasing patient age (OR, 1.09 per decade) and inversely associated with radiologist years since training (OR, 0.90 per 5 years). The model accounted for 10.9% of the likelihood of RAI. Of explainable likelihood of RAI, 25.7% was attributable to examination, patient, and radiologist factors; 74.3% was attributable to radiologist-specific behavior. CONCLUSION. Interradiologist variation in RAI rates for head and neck imaging was substantial. RAI appear to be more substantially associated with individual radiologist-specific behavior than with measurable systemic factors. CLINICAL IMPACT. Quality improvement initiatives, incorporating best practices for incidental findings management, may help reduce radiologist preference-sensitive decision-making in issuing RAI for head and neck imaging and associated care variation.

Inner Ear Breaches from Vestibular Schwannoma Surgery: Revisiting the Incidence of Otologic Injury from Retrosigmoid and Middle Cranial Fossa Approaches.

OBJECTIVE: To assess the rate of iatrogenic injury to the inner ear in vestibular schwannoma resections. STUDY DESIGN: Retrospective case review. SETTING: Multiple academic tertiary care hospitals. PATIENTS: Patients who underwent retrosigmoid or middle cranial fossa approaches for vestibular schwannoma resection between 1993 and 2015. INTERVENTION: Diagnostic with therapeutic implications. MAIN OUTCOME MEASURE: Drilling breach of the inner ear as confirmed by operative note or postoperative computed tomography (CT). RESULTS: 21.5% of patients undergoing either retrosigmoid or middle fossa approaches to the internal auditory canal were identified with a breach of the vestibulocochlear system. Because of the lack of postoperative CT imaging in this cohort, this is likely an underestimation of the true incidence of inner ear breaches. Of all postoperative CT scans reviewed, 51.8% had an inner ear breach. As there may be bias in patients undergoing postoperative CT, a middle figure based on sensitivity analyses estimates the incidence of inner ear breaches from lateral skull base surgery to be 34.7%. CONCLUSIONS: A high percentage of vestibular schwannoma surgeries via retrosigmoid and middle cranial fossa approaches result in drilling breaches of the inner ear. This study reinforces the value of preoperative image analysis for determining risk of inner ear breaches during vestibular schwannoma surgery and the importance of acquiring CT studies postoperatively to evaluate the integrity of the inner ear.

Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium.

BACKGROUND: Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group. METHODS: We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality. RESULTS: We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance. CONCLUSION: These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

Infantile Sinonasal Myxoma Is Clinically and Genetically Distinct From Other Myxomas of the Craniofacial Bones and From Desmoid Fibromatosis.

Sinonasal myxomas are rare benign tumors of the maxillary bone and sinus. There is published evidence that sinonasal myxomas occurring in children up to 3 years of age ("infantile sinonasal myxomas") are clinically distinctive and harbor Wnt signaling pathway alterations. Here, we characterized 16 infantile sinonasal myxomas and compared them to 19 maxillary myxomas and 11 mandibular myxomas in older patients. Clinical follow-up was available for 21 patients (46%) overall (median: 2.6 y; range: 4 mo to 21 y), including 10 of 16 infantile sinonasal myxomas (62%). None of the 8 resected infantile sinonasal myxomas recurred, despite positive margins in 6 of them. One incompletely resected infantile sinonasal myxoma underwent partial regression without additional treatment. In contrast, 4 of the 11 other myxomas with follow-up recurred (36%), including one that recurred twice. Imaging studies demonstrated all infantile sinonasal myxomas to be expansile lesions arising from the anterior maxillary bone adjacent to the nasal aperture, with peripheral reactive bone formation. Histologically, infantile sinonasal myxomas showed short, intersecting fascicles of bland fibroblastic cells with prominent stromal vessels. Examples with collagenous stroma showed some morphologic overlap with desmoid fibromatosis, although none showed infiltrative growth into adjacent soft tissue. Immunohistochemistry demonstrated nuclear ß-catenin expression in 14 of 15 infantile sinonasal myxomas (93%), in contrast to 4 of 26 other myxomas of craniofacial bones (15%). Smooth muscle actin was expressed in only 1 of 11 infantile sinonasal myxomas (9%). Next-generation sequencing was successfully performed on 10 infantile sinonasal myxomas and 7 other myxomas. Infantile sinonasal myxomas harbored CTNNB1 point mutations in 4 cases (D32Y, G34E, G34R, and I35S), and none harbored alterations to the phosphorylation sites T41 and S45 that are altered in 99% of CTNNB1 -mutant desmoid fibromatoses. Three tumors showed alterations consistent with biallelic APC inactivation. Three infantile sinonasal myxomas that showed strong nuclear ß-catenin expression were negative for CTNNB1 and APC alterations. Sequencing was negative for CTNNB1 or APC alterations in all 7 myxomas of craniofacial bones in older patients. Four of these myxomas in older patients (57%) showed copy number alterations, and all lacked known driving alterations. These findings support the notion that infantile sinonasal myxomas are clinically and genetically distinctive, and we propose the use of the diagnostic term "infantile sinonasal myxoma" to distinguish this tumor type from other myxomas of the craniofacial bones. Infantile sinonasal myxoma should be distinguished from desmoid fibromatosis because of its unique clinical presentation, more indolent clinical behavior, different morphology, different immunohistochemical profile, and different genetics. Given its indolent behavior even when marginally excised, infantile sinonasal myxoma can be managed with conservative surgery.

Iatrogenic inner ear dehiscence associated with lateral skull base surgery: a systematic analysis of drilling injuries and their causal factors.

PURPOSE: Drilling injuries of the inner ear are an underreported complication of lateral skull base (LSB) surgery. Inner ear breaches can cause hearing loss, vestibular dysfunction, and third window phenomenon. This study aims to elucidate primary factors causing iatrogenic inner ear dehiscences (IED) in 9 patients who presented to a tertiary care center with postoperative symptoms of IED following LSB surgery for vestibular schwannoma, endolymphatic sac tumor, Meniere's disease, paraganglioma jugulare, and vagal schwannoma. METHODS: Utilizing 3D Slicer image processing software, geometric and volumetric analysis was applied to both preoperative and postoperative imaging to identify causal factors iatrogenic inner ear breaches. Segmentation analyses, craniotomy analyses, and drilling trajectory analyses were performed. Cases of retrosigmoid approaches for vestibular schwannoma resection were compared to matched controls. RESULTS: Excessive lateral drilling and breach of a single inner ear structure occurred in 3 cases undergoing transjugular (n=2) and transmastoid (n=1) approaches. Inadequate drilling trajectory breaching ≥1 inner ear structure occurred in 6 cases undergoing retrosigmoid (n=4), transmastoid (n=1), and middle cranial fossa approaches (n=1). In retrosigmoid approaches the 2-cm visualization window and craniotomy limits did not provide drilling angles to the entire tumor without causing IED in comparison to matched controls. CONCLUSIONS: Inappropriate drill depth, errant lateral drilling, inadequate drill trajectory, or a combination of these led to iatrogenic IED. Image-based segmentation, individualized 3D anatomical model generation, and geometric and volumetric analyses can optimize operative plans and possibly reduce inner ear breaches from lateral skull base surgery.

Improving Cognitive Function Through High-Intensity Interval Training in Breast Cancer Patients Undergoing Chemotherapy: Protocol for a Randomized Controlled Trial.

BACKGROUND: More than 75% of patients with breast cancer treated with chemotherapy experience cognitive impairments (eg, memory and attention problems), commonly known as chemo-brain. Exercise, especially aerobic high-intensity interval training (HIIT), is associated with better cognitive function in healthy populations. However, clinical trials testing the impact of exercise interventions on chemotherapy-induced cognitive decline in patients with cancer are lacking, and the mechanisms through which exercise could improve cognitive function are unclear. OBJECTIVE: The objective of the Improving Cognitive Function Through High-Intensity Interval Training in Breast Cancer Patients Undergoing Chemotherapy trial is to examine the effects of HIIT on cognitive function in patients with breast cancer undergoing chemotherapy. METHODS: This 2-arm, single-center, pilot randomized controlled trial will randomize 50 patients with breast cancer undergoing chemotherapy to HIIT or attention control. The HIIT group will perform a supervised 16-week, thrice-weekly intervention, with each session including a 5-minute warm-up at 10% maximal power output (POmax), 10 sets of alternating 1-minute high-intensity (90% POmax) and 1-minute recovery (10% POmax) intervals, and a 5-minute cooldown (10% POmax). The attention control group will receive a stretching program with no exercise components and be asked to maintain their exercise levels for 16 weeks. The primary outcomes of the study are executive function and memory measured using the National Institutes of Health toolbox and resting-state connectivity and diffusion tensor imaging microstructure evaluated using magnetic resonance imaging. The secondary and tertiary outcomes include cardiorespiratory fitness, body composition, physical fitness, and psychosocial health. The study has been approved by the institutional review board of the Dana-Farber Cancer Institute (20-222). RESULTS: The trial was funded in January 2019, with recruitment started in June 2021. As of May 2022, a total of 4 patients have consented and been randomized (n=2, 50% to exercise; n=1, 25% to control; and n=1, 25% nonrandomized). Trial completion is expected in January 2024. CONCLUSIONS: This first-of-its-kind study incorporates a novel exercise intervention (ie, HIIT) and comprehensive cognitive measures. If positive, our findings will establish the pilot efficacy of HIIT on chemotherapy-induced cognitive function in patients with breast cancer, providing the foundation for future larger phase-II and phase-III trials to confirm the findings and potentially establish HIIT as a standard of care for women undergoing chemotherapy for breast cancer. TRIAL REGISTRATION: ClinicalTrials.gov NCT04724499; https://clinicaltrials.gov/ct2/show/NCT04724499. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/39740.

Evaluation of Standard Response Assessment in Neuro-Oncology, Modified Response Assessment in Neuro-Oncology, and Immunotherapy Response Assessment in Neuro-Oncology in Newly Diagnosed and Recurrent Glioblastoma.

PURPOSE: The Response Assessment in Neuro-Oncology (RANO) criteria are widely used in high-grade glioma clinical trials. We compared the RANO criteria with updated modifications (modified RANO [mRANO] and immunotherapy RANO [iRANO] criteria) in patients with newly diagnosed glioblastoma (nGBM) and recurrent GBM (rGBM) to evaluate the performance of each set of criteria and inform the development of the planned RANO 2.0 update. MATERIALS AND METHODS: Evaluation of tumor measurements and fluid-attenuated inversion recovery (FLAIR) sequences were performed by blinded readers to determine disease progression using RANO, mRANO, iRANO, and other response assessment criteria. Spearman's correlations between progression-free survival (PFS) and overall survival (OS) were calculated. RESULTS: Five hundred twenty-six nGBM and 580 rGBM cases were included. Spearman's correlations were similar between RANO and mRANO (0.69 [95% CI, 0.62 to 0.75] v 0.67 [95% CI, 0.60 to 0.73]) in nGBM and rGBM (0.48 [95% CI, 0.40 to 0.55] v 0.50 [95% CI, 0.42 to 0.57]). In nGBM, requirement of a confirmation scan within 12 weeks of completion of radiotherapy to determine progression was associated with improved correlations. Use of the postradiation magnetic resonance imaging (MRI) as baseline scan was associated with improved correlation compared with use of the pre-radiation MRI (0.67 [95% CI, 0.60 to 0.73] v 0.53 [95% CI, 0.42 to 0.62]). Evaluation of FLAIR sequences did not improve the correlation. Among patients who received immunotherapy, Spearman's correlations were similar among RANO, mRANO, and iRANO. CONCLUSION: RANO and mRANO demonstrated similar correlations between PFS and OS. Confirmation scans were only beneficial in nGBM within 12 weeks of completion of radiotherapy, and there was a trend in favor of the use of postradiation MRI as the baseline scan in nGBM. Evaluation of FLAIR can be omitted. The iRANO criteria did not add significant benefit in patients who received immune checkpoint inhibitors.

Development and External Validation of an Artificial Intelligence Model for Identifying Radiology Reports Containing Recommendations for Additional Imaging.

BACKGROUND. Reported rates of recommendations for additional imaging (RAIs) in radiology reports are low. Bidirectional encoder representations from transformers (BERT), a deep learning model pretrained to understand language context and ambiguity, has potential for identifying RAIs and thereby assisting large-scale quality improvement efforts. OBJECTIVE. The purpose of this study was to develop and externally validate an artificial intelligence (AI)-based model for identifying radiology reports containing RAIs. METHODS. This retrospective study was performed at a multisite health center. A total of 6300 radiology reports generated at one site from January 1, 2015, to June 30, 2021, were randomly selected and split by 4:1 ratio to create training (n = 5040) and test (n = 1260) sets. A total of 1260 reports generated at the center's other sites (including academic and community hospitals) from April 1 to April 30, 2022, were randomly selected as an external validation group. Referring practitioners and radiologists of varying sub-specialties manually reviewed report impressions for presence of RAIs. A BERT-based technique for identifying RAIs was developed by use of the training set. Performance of the BERT-based model and a previously developed traditional machine learning (TML) model was assessed in the test set. Finally, performance was assessed in the external validation set. The code for the BERT-based RAI model is publicly available. RESULTS. Among a total of 7419 unique patients (4133 women, 3286 men; mean age, 58.8 years), 10.0% of 7560 reports contained RAI. In the test set, the BERT-based model had 94.4% precision, 98.5% recall, and an F1 score of 96.4%. In the test set, the TML model had 69.0% precision, 65.4% recall, and an F1 score of 67.2%. In the test set, accuracy was greater for the BERT-based than for the TML model (99.2% vs 93.1%, p < .001). In the external validation set, the BERT-based model had 99.2% precision, 91.6% recall, an F1 score of 95.2%, and 99.0% accuracy. CONCLUSION. The BERT-based AI model accurately identified reports with RAIs, outperforming the TML model. High performance in the external validation set suggests the potential for other health systems to adapt the model without requiring institution-specific training. CLINICAL IMPACT. The model could potentially be used for real-time EHR monitoring for RAIs and other improvement initiatives to help ensure timely performance of clinically necessary recommended follow-up.

Screening for extranodal extension in HPV-associated oropharyngeal carcinoma: evaluation of a CT-based deep learning algorithm in patient data from a multicentre, randomised de-escalation trial.

BACKGROUND: Pretreatment identification of pathological extranodal extension (ENE) would guide therapy de-escalation strategies for in human papillomavirus (HPV)-associated oropharyngeal carcinoma but is diagnostically challenging. ECOG-ACRIN Cancer Research Group E3311 was a multicentre trial wherein patients with HPV-associated oropharyngeal carcinoma were treated surgically and assigned to a pathological risk-based adjuvant strategy of observation, radiation, or concurrent chemoradiation. Despite protocol exclusion of patients with overt radiographic ENE, more than 30% had pathological ENE and required postoperative chemoradiation. We aimed to evaluate a CT-based deep learning algorithm for prediction of ENE in E3311, a diagnostically challenging cohort wherein algorithm use would be impactful in guiding decision-making. METHODS: For this retrospective evaluation of deep learning algorithm performance, we obtained pretreatment CTs and corresponding surgical pathology reports from the multicentre, randomised de-escalation trial E3311. All enrolled patients on E3311 required pretreatment and diagnostic head and neck imaging; patients with radiographically overt ENE were excluded per study protocol. The lymph node with largest short-axis diameter and up to two additional nodes were segmented on each scan and annotated for ENE per pathology reports. Deep learning algorithm performance for ENE prediction was compared with four board-certified head and neck radiologists. The primary endpoint was the area under the curve (AUC) of the receiver operating characteristic. FINDINGS: From 178 collected scans, 313 nodes were annotated: 71 (23%) with ENE in general, 39 (13%) with ENE larger than 1 mm ENE. The deep learning algorithm AUC for ENE classification was 0·86 (95% CI 0·82-0·90), outperforming all readers (p<0·0001 for each). Among radiologists, there was high variability in specificity (43-86%) and sensitivity (45-96%) with poor inter-reader agreement (κ 0·32). Matching the algorithm specificity to that of the reader with highest AUC (R2, false positive rate 22%) yielded improved sensitivity to 75% (+ 13%). Setting the algorithm false positive rate to 30% yielded 90% sensitivity. The algorithm showed improved performance compared with radiologists for ENE larger than 1 mm (p<0·0001) and in nodes with short-axis diameter 1 cm or larger. INTERPRETATION: The deep learning algorithm outperformed experts in predicting pathological ENE on a challenging cohort of patients with HPV-associated oropharyngeal carcinoma from a randomised clinical trial. Deep learning algorithms should be evaluated prospectively as a treatment selection tool. FUNDING: ECOG-ACRIN Cancer Research Group and the National Cancer Institute of the US National Institutes of Health.

Spinal Cord Delineation Based on Computed Tomography Myelogram Versus T2 Magnetic Resonance Imaging in Spinal Stereotactic Body Radiation Therapy.

Purpose: Spinal cord delineation is critical to the delivery of stereotactic body radiation therapy (SBRT). Although underestimating the spinal cord can lead to irreversible myelopathy, overestimating the spinal cord may compromise the planning target volume coverage. We compare spinal cord contours based on computed tomography (CT) simulation with a myelogram to spinal cord contours based on fused axial T2 magnetic resonance imaging (MRI). Methods and Materials: Eight patients with 9 spinal metastases treated with spinal SBRT were contoured by 8 radiation oncologists, neurosurgeons, and physicists, with spinal cord definition based on (1) fused axial T2 MRI and (2) CT-myelogram simulation images, yielding 72 sets of spinal cord contours. The spinal cord volume was contoured at the target vertebral body volume based on both images. The mixed-effect model assessed comparisons of T2 MRI- to myelogram-defined spinal cord in centroid deviations (deviations in the center point of the cord) through the vertebral body target volume, spinal cord volumes, and maximum doses (0.035 cc point) to the spinal cord applying the patient's SBRT treatment plan, in addition to in-between and within-subject variabilities. Results: The estimate for the fixed effect from the mixed model showed that the mean difference between 72 CT volumes and 72 MRI volumes was 0.06 cc and was not statistically significant (95% confidence interval, -0.034, 0.153; P = .1832). The mixed model showed that the mean dose at 0.035 cc for CT-defined spinal cord contours was 1.24 Gy lower than that of MRI-defined spinal cord contours and was statistically significant (95% confidence interval, -2.292, -0.180; P = .0271). Also, the mixed model indicated no statistical significance for deviations in any of the axes between MRI-defined spinal cord contours and CT-defined spinal cord contours. Conclusions: CT myelogram may not be required when MRI imaging is feasible, although uncertainty at the cord-to-treatment volume interface may result in overcontouring and hence higher estimated cord dose-maximums with axial T2 MRI-based cord definition.