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.

Incorporating algorithmic uncertainty into a clinical machine deep learning algorithm for urgent head CTs.

Machine learning (ML) algorithms to detect critical findings on head CTs may expedite patient management. Most ML algorithms for diagnostic imaging analysis utilize dichotomous classifications to determine whether a specific abnormality is present. However, imaging findings may be indeterminate, and algorithmic inferences may have substantial uncertainty. We incorporated awareness of uncertainty into an ML algorithm that detects intracranial hemorrhage or other urgent intracranial abnormalities and evaluated prospectively identified, 1000 consecutive noncontrast head CTs assigned to Emergency Department Neuroradiology for interpretation. The algorithm classified the scans into high (IC+) and low (IC-) probabilities for intracranial hemorrhage or other urgent abnormalities. All other cases were designated as No Prediction (NP) by the algorithm. The positive predictive value for IC+ cases (N = 103) was 0.91 (CI: 0.84-0.96), and the negative predictive value for IC- cases (N = 729) was 0.94 (0.91-0.96). Admission, neurosurgical intervention, and 30-day mortality rates for IC+ was 75% (63-84), 35% (24-47), and 10% (4-20), compared to 43% (40-47), 4% (3-6), and 3% (2-5) for IC-. There were 168 NP cases, of which 32% had intracranial hemorrhage or other urgent abnormalities, 31% had artifacts and postoperative changes, and 29% had no abnormalities. An ML algorithm incorporating uncertainty classified most head CTs into clinically relevant groups with high predictive values and may help accelerate the management of patients with intracranial hemorrhage or other urgent intracranial abnormalities.

Diagnostic performance of computed tomography features in detecting oropharyngeal squamous cell carcinoma extranodal extension.

OBJECTIVES: Accurate pre-treatment imaging determination of extranodal extension (ENE) could facilitate the selection of appropriate initial therapy for HPV-positive oropharyngeal squamous cell carcinoma (HPV + OPSCC). Small studies have associated 7 CT features with ENE with varied results and agreement. This article seeks to determine the replicable diagnostic performance of these CT features for ENE. METHODS: Five expert academic head/neck neuroradiologists from 5 institutions evaluate a single academic cancer center cohort of 75 consecutive HPV + OPSCC patients. In a web-based virtual laboratory for imaging research and education, the experts performed training on 7 published CT features associated with ENE and then independently identified the "single most (if any) suspicious" lymph node and presence/absence of each of the features. Inter-rater agreement was assessed using percentage agreement, Gwet's AC1, and Fleiss' kappa. Sensitivity, specificity, and positive and negative predictive values were calculated for each CT feature based on histologic ENE. RESULTS: All 5 raters identified the same node in 52 cases (69%). In 15 cases (20%), at least one rater selected a node and at least one rater did not. In 8 cases (11%), all raters selected a node, but at least one rater selected a different node. Percentage agreement and Gwet's AC1 coefficients were > 0.80 for lesion identification, matted/conglomerated nodes, and central necrosis. Fleiss' kappa was always < 0.6. CT sensitivity for histologically confirmed ENE ranged 0.18-0.94, specificity 0.41-0.88, PPV 0.26-0.36, and NPV 0.78-0.96. CONCLUSIONS: Previously described CT features appear to have poor reproducibility among expert head/neck neuroradiologists and poor predictive value for histologic ENE. KEY POINTS: • Previously described CT imaging features appear to have poor reproducibility among expert head and neck subspecialized neuroradiologists as well as poor predictive value for histologic ENE. • Although it may still be appropriate to comment on the presence or absence of these CT features in imaging reports, the evidence indicates that caution is warranted when incorporating these features into clinical decision-making regarding the likelihood of ENE.

Magnetic Resonance Imaging of Head and Neck Emergencies, a Symptom-Based Review, Part 1: General Considerations, Vision Loss, and Eye Pain.

Use of magnetic resonance (MR) imaging in the emergency department continues to increase. Although computed tomography is the first-line imaging modality for most head and neck emergencies, MR is superior in some situations and imparts no ionizing radiation. This article provides a symptom-based approach to nontraumatic head and neck pathologic conditions most relevant to emergency head and neck MR imaging, emphasizing relevant anatomy, "do not miss" findings affecting clinical management, and features that may aid differentiation from potential mimics. Essential MR sequences and strategies for obtaining high-quality images when faced with patient motion and other technical challenges are also discussed.

Magnetic Resonance Imaging of Head and Neck Emergencies, a Symptom-Based Review, Part 2: Ear Pain, Face Pain, and Fever.

The use of magnetic resonance (MR) imaging in the emergency department continues to increase. Although computed tomography is the first-line imaging modality for most head and neck emergencies, MR is superior in some situations and imparts no ionizing radiation. This article provides a symptom-based approach to nontraumatic head and neck pathologic conditions most relevant to emergency head and neck MR imaging, emphasizing relevant anatomy, "do not miss" findings affecting clinical management, and features that may aid differentiation from potential mimics. Essential MR sequences and strategies for obtaining high-quality images when faced with patient motion and other technical challenges are also discussed.

Parathyroid Computed Tomography: Pearls, Pitfalls, and Our Approach.

Parathyroid imaging is predominantly used for preoperative localization of parathyroid lesions in patients with the biochemical diagnosis of primary hyperparathyroidism. Although imaging algorithms vary, in the era of minimally invasive parathyroidectomy for single parathyroid adenomas, multiphase parathyroid computed tomography (CT) (4-dimensional CT) has emerged as a favored modality for presurgical mapping of parathyroid lesions. Implementation and correct interpretation of these studies can be challenging, although confidence and accuracy improve with experience and volume. This article reviews our approach to parathyroid imaging, focusing on pearls and pitfalls in parathyroid CT with ultrasound as a supportive and complementary modality.

Factors Influential in the Selection of Radiology Residents in the Post-Step 1 World: A Discrete Choice Experiment.

OBJECTIVES: Reporting of United States Medical Licensing Examination Step 1 results will transition from a numerical score to a pass or fail result. We sought an objective analysis to determine changes in the relative importance of resident application attributes when numerical Step 1 results are replaced. METHODS: A discrete choice experiment was designed to model radiology resident selection and determine the relative weights of various application factors when paired with a numerical or pass or fail Step 1 result. Faculty involved in resident selection at 14 US radiology programs chose between hypothetical pairs of applicant profiles between August and November 2020. A conditional logistic regression model assessed the relative weights of the attributes, and odds ratios (ORs) were calculated. RESULTS: There were 212 participants. When a numerical Step 1 score was provided, the most influential attributes were medical school (OR: 2.35, 95% confidence interval [CI]: 2.07-2.67), Black or Hispanic race or ethnicity (OR: 2.04, 95% CI: 1.79-2.38), and Step 1 score (OR: 1.8, 95% CI: 1.69-1.95). When Step 1 was reported as pass, the applicant's medical school grew in influence (OR: 2.78, 95% CI: 2.42-3.18), and there was a significant increase in influence of Step 2 scores (OR: 1.31, 95% CI: 1.23-1.40 versus OR 1.57, 95% CI: 1.46-1.69). There was little change in the relative influence of race or ethnicity, gender, class rank, or clerkship honors. DISCUSSION: When Step 1 reporting transitions to pass or fail, medical school prestige gains outsized influence and Step 2 scores partly fill the gap left by Step 1 examination as a single metric of decisive importance in application decisions.

Utilization of a Virtual Information Session to Increase Engagement With Prospective Applicants in the Setting of COVID-19.

PURPOSE: This study aimed to assess the efficacy of a virtual information session hosted by a diagnostic radiology residency program at addressing applicant concerns about the 2020-2021 interview cycle and highlighting key aspects of the residency program. METHODS: Participants were recruited to attend the virtual information session over a 2-week period via social media and communication with medical school radiology interest groups. Attendees were able to submit questions or topics of interest prior to the session. The virtual information session was hosted by trainees and faculty from a radiology residency. Data regarding the demographics of the attendees and the efficacy of the session were obtained through interactive live polling during the virtual session and a voluntary anonymous postsession survey. RESULTS: A total of 171 attendees participated in the virtual information session. Of the attendees, 42% learned about the session from Twitter and 72% were fourth-year medical students applying for residency. Among topics addressed during the session, attendees indicated that they were most interested in learning about "Application strategies during COVID-19" during an in-session poll. On the post-session survey, 96% of attendees reported being more knowledgeable about the residency program culture and the breadth of research and educational opportunities. CONCLUSION: Given the virtual nature of the 2020-2021 residency application cycle, utilization of web-based platforms for recruitment will be essential. Virtual information sessions can be effective at providing insight into aspects of a residency program that are typically gained during the in-person interview experience.

Parathyroid 4D CT: What the Surgeon Wants to Know.

Parathyroid four-dimensional (4D) CT is an increasingly used and powerful tool for preoperative localization of abnormal parathyroid tissue in the setting of primary hyperparathyroidism. Accurate and precise localization of a single adenoma facilitates minimally invasive parathyroidectomy, and localization of multiglandular disease aids bilateral neck exploration. However, many radiologists find the interpretation of these examinations to be an intimidating challenge. The authors review parathyroid 4D CT findings of typical and atypical parathyroid lesions and provide illustrative examples. Relevant anatomy, embryology, and operative considerations with which the radiologist should be familiar to provide clinically useful image interpretations are also discussed. The most important 4D CT information to the surgeon includes the number, size, and specific location of candidate parathyroid lesions with respect to relevant surgical landmarks; the radiologist's opinion and confidence level regarding what each candidate lesion represents; and the presence or absence of ectopic or supernumerary parathyroid tissue, concurrent thyroid pathologic conditions, and arterial anomalies associated with a nonrecurrent laryngeal nerve. The authors provide the radiologist with an accessible and practical approach to performing and interpreting parathyroid 4D CT images, detail what the surgeon really wants to know from the radiologist and why, and provide an accompanying structured report outlining the key information to be addressed. By accurately reporting and concisely addressing the key information the surgeon desires from a parathyroid 4D CT examination, the radiologist substantially impacts patient care by enabling the surgeon to develop and execute the best possible operative plan for each patient. ©RSNA, 2020.

Chew on This: Emergency Imaging of the Oral Cavity and Salivary Glands-What the Clinician Really Needs to Know.

Nontraumatic emergencies of the oral cavity, sublingual and submandibular spaces, and salivary glands are common and those requiring imaging will most often be infectious in nature.1,2 However, noninfectious pathologies such as sialolithiasis, autoimmune sialoadenitis, and soft tissue swelling due to angioedema or hemorrhage are also important conditions that radiologists must be familiar with in order to inform the clinician of critical imaging findings that can have a profound impact on patient outcomes. To understand these pathologies, familiarity with the anatomy of these spaces is essential.

Preoperative Imaging Techniques in Primary Hyperparathyroidism: A Review.

Importance: Successful minimally invasive parathyroidectomy requires confident and accurate preoperative localization. Several noninvasive imaging techniques are well established for preoperative localization, and others are emerging. Observations: Ultrasonography and sestamibi imaging are established preoperative localization techniques with good sensitivity and positive predictive value. Multiphase 4-dimensional computed tomography is a newer technique with arguably superior performance, particularly in the setting of negative or discordant ultrasonography and sestamibi imaging, residual or recurrent primary hyperparathyroidism following a previous surgical operation, and multiglandular disease. Emerging techniques that may further facilitate confident and accurate preoperative localization include ultrasonography, elastography, positron emission tomography, and 4-D magnetic resonance imaging. Conclusions and Relevance: The optimal imaging localization algorithm for hyperparathyroidism remains undetermined, but a combination of techniques tailored to the specific scenario will likely yield the best outcomes. An algorithm is proposed that considers test performance, surgeon confidence, patient-specific factors, cost, local radiologic expertise, and patient radiation exposure.

Mannequin-based Telesimulation: Increasing Access to Simulation-based Education.

A telesimulation platform utilizes communications technology to provide mannequin-based simulation education between learners and instructors located remotely from one another. Specifically, the instructor controls the mannequin and moderates the debriefing remotely. During these sessions, the instructor observes the learners in real time and provides immediate feedback during the debriefing. This platform obviates the need to have instructors, learners, and mannequins in the same place at the same time, potentially allowing simulation-based educational sessions to occur with greater frequency for institutions not located proximate to formal simulation centers. Additionally, the telesimulation platform enables an experienced simulation instructor to observe and directly help new simulation instructors at remote simulation locations. Readily available Web-conferencing, screen-sharing software, microphones, and webcams makes telesimulation possible. Mannequin-based telesimulation is relatively new and not well represented in the literature, but could facilitate systems changes, providing educational experiences to health care professionals in locations not currently benefiting from mannequin-based simulation opportunities. Several research questions need to be addressed in future studies to better develop this educational approach, including technical feasibility, logistic issues, a comparison of telesimulation to other simulation approaches, and assessing limitations of the telesimulation platform.

Chapter 2 Squamous Cell Carcinoma of the Head and Neck-Imaging Evaluation of Regional Lymph Nodes and Implications for Management.

The presence of cervical lymph node metastases is a major prognostic factor in squamous cell carcinoma of the head and neck. The presence of a solitary ipsilateral metastatic lymph node reduces expected survival by almost 50%, and the presence of regional metastatic nodes at the time of presentation is the strongest predictor of recurrence or the development of distant metastases or both. Therefore, accurate identification of metastatic cervical lymph nodes is essential for staging and treatment planning. Pretreatment imaging is important for identifying clinically occult pathologic nodes as well as delineating nodal size and morphologic characteristics used in staging. The role of imaging and its implications for management are reviewed, with emphasis on the traditional modalities and imaging criteria, including evaluation for extranodal extension.