ACR Appropriateness Criteria ® Tinnitus

Canadian Association of Radiologists Head and Neck Imaging Referral Guideline

The Canadian Association of Radiologists (CAR) Head and Neck Expert Panel consists of radiologists, a laryngologist and laryngeal surgeon, a patient advisor, and an epidemiologist/guideline methodologist. After developing a list of 11 clinical/diagnostic scenarios, a systematic rapid scoping review was undertaken to identify systematically produced referral guidelines that provide recommendations for one or more of these clinical/diagnostic scenarios. Recommendations from 17 guidelines and contextualization criteria in the Grading of Recommendations, Assessment, Development, and Evaluations (GRADE) for guidelines framework were used to develop 26 recommendation statements across the 11 scenarios. This guideline presents the methods of development and the referral recommendations for sinus disease, tinnitus, thyroid and parathyroid disease, neck mass of unknown origin, acute sialadenitis, chronic salivary conditions, and temporomandibular joint dysfunction.

ACR Appropriateness Criteria® Dizziness and Ataxia: 2023 Update

Diagnostic evaluation of a patient with dizziness or vertigo is complicated by a lack of standardized nomenclature, significant overlap in symptom descriptions, and the subjective nature of the patient's symptoms. Although dizziness is an imprecise term often used by patients to describe a feeling of being off-balance, in many cases dizziness can be subcategorized based on symptomatology as vertigo (false sense of motion or spinning), disequilibrium (imbalance with gait instability), presyncope (nearly fainting or blacking out), or lightheadedness (nonspecific). As such, current diagnostic paradigms focus on timing, triggers, and associated symptoms rather than subjective descriptions of dizziness type. Regardless, these factors complicate the selection of appropriate diagnostic imaging in patients presenting with dizziness or vertigo. This document serves to aid providers in this selection by using a framework of definable clinical variants. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

CT evaluation of unilateral pulsatile tinnitus with jugular bulb wall dehiscence

OBJECTIVES

To investigate the imaging features of unilateral pulsatile tinnitus (PT) with jugular bulb wall dehiscence (JBWD).

METHODS

Computerized tomography angiography images of unilateral PT patients were reviewed between 2019 and 2021. Thirty-one symptomatic JBWD patients without sigmoid sinus wall dehiscence (SSWD) were included. Thirty-eight patients with SSWD were used as the control group. The prevalence of JBWD was calculated. The area and height of the jugular bulb, the extent of dehiscence, the presence of jugular bulb diverticulum, posterior condylar emissary vein (PCEV), oblique occipital sinus (OOS), venous outflow laterality (VOL), the degree of transverse sinus stenosis (TSS), and the pituitary height to sella turcica ratio were compared between the two groups.

RESULTS

The prevalence of JBWD was 12.1%, and JBWD was established as a causative diagnosis in 5.0% of unilateral PT patients. There were no statistical differences in the gender, symptomatic side, or VOL between the two groups. The area of the jugular bulb was larger and the height was higher (p_area < 0.001, p_height = 0.005). The prevalence of jugular bulb diverticulum was higher in the JBWD group (p = 0.002). The degree of symptomatic TSS was less severe (p < 0.001), and the prevalence of bilateral TSS was lower in the JBWD group (p < 0.001). The pituitary height to sella turcica ratio was greater (p = 0.004), the prevalence of PCEV (p = 0.014) was lower, and OOS (p = 0.015) was greater in the JBWD group.

CONCLUSIONS

The correlating factors of PT with JBWD and PT with SSWD are significantly different. These findings can further facilitate early and efficient PT treatment.

KEY POINTS

• The incidence of jugular bulb dehiscence (JBWD) accounted for approximately 12.1% in pulsatile tinnitus (PT) patients, and JBWD was established as a causative diagnosis in 5.0% of PT patients. • PT required large blood flows and abnormal flow patterns, whether in JBWD or sigmoid sinus wall dehiscence groups. • JBWD causing PT has some unique characteristic findings on CT.

Automatic text classification of actionable radiology reports of tinnitus patients using bidirectional encoder representations from transformer (BERT) and in-domain pre-training (IDPT)

Background

Given the increasing number of people suffering from tinnitus, the accurate categorization of patients with actionable reports is attractive in assisting clinical decision making. However, this process requires experienced physicians and significant human labor. Natural language processing (NLP) has shown great potential in big data analytics of medical texts; yet, its application to domain-specific analysis of radiology reports is limited.

Objective

The aim of this study is to propose a novel approach in classifying actionable radiology reports of tinnitus patients using bidirectional encoder representations from transformer BERT-based models and evaluate the benefits of in domain pre-training (IDPT) along with a sequence adaptation strategy.

Methods

A total of 5864 temporal bone computed tomography(CT) reports are labeled by two experienced radiologists as follows: (1) normal findings without notable lesions; (2) notable lesions but uncorrelated to tinnitus; and (3) at least one lesion considered as potential cause of tinnitus. We then constructed a framework consisting of deep learning (DL) neural networks and self-supervised BERT models. A tinnitus domain-specific corpus is used to pre-train the BERT model to further improve its embedding weights. In addition, we conducted an experiment to evaluate multiple groups of max sequence length settings in BERT to reduce the excessive quantity of calculations. After a comprehensive comparison of all metrics, we determined the most promising approach through the performance comparison of F1-scores and AUC values.

Results

In the first experiment, the BERT finetune model achieved a more promising result (AUC-0.868, F1-0.760) compared with that of the Word2Vec-based models(AUC-0.767, F1-0.733) on validation data. In the second experiment, the BERT in-domain pre-training model (AUC-0.948, F1-0.841) performed significantly better than the BERT based model(AUC-0.868, F1-0.760). Additionally, in the variants of BERT fine-tuning models, Mengzi achieved the highest AUC of 0.878 (F1-0.764). Finally, we found that the BERT max-sequence-length of 128 tokens achieved an AUC of 0.866 (F1-0.736), which is almost equal to the BERT max-sequence-length of 512 tokens (AUC-0.868,F1-0.760).

Conclusion

In conclusion, we developed a reliable BERT-based framework for tinnitus diagnosis from Chinese radiology reports, along with a sequence adaptation strategy to reduce computational resources while maintaining accuracy. The findings could provide a reference for NLP development in Chinese radiology reports.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01946-y.

Diagnosing Pulsatile Tinnitus: A Review of 251 Patients

OBJECTIVE

To analyze the underlying etiologies, presenting characteristics, and diagnostic workup of patients with pulsatile tinnitus (PT).

STUDY DESIGN

Retrospective review.

SETTING

Tertiary referral center.

PATIENTS

All patients who received a diagnostic workup for PT from January 01, 2015 and May 31, 2020.

MAIN OUTCOME MEASURE

Diagnostic rate of imaging studies.

RESULTS

Among 251 patients with PT, the most common etiologies included neoplasms (16%), arteriopathies (14%), venopathies (8.5%), middle/inner ear pathology (9.0%), or idiopathic (50%). Patients with identifiable etiologies of PT more often had hypertension, obesity, vision changes, ipsilateral asymmetric hearing loss, or an abnormal otologic examination. Only 18.5% of patients without those characteristics had an identifiable etiology of PT. The most commonly ordered diagnostic studies were magnetic resonance imaging with contrast (n = 146), MR angiography (MRA) (n = 105), CT angiography (CTA) (n = 84), computed tomography (CT) without contrast (n = 76), and MR Venogram (MRV) (n = 62). Magnetic resonance imaging with contrast and CT without contrast preferentially identified patients with nonvascular etiologies of PT, while MRA and CTA identified patients with vascular etiologies of PT. MRV did not demonstrate high diagnostic rate for either type of PT. No difference in diagnostic rate was found between MR-based or CT-based imaging.

CONCLUSIONS

Patients who lack a history of hypertension, obesity, vision changes, ipsilateral asymmetric hearing loss, or an abnormal otologic examination are less likely to have an identifiable cause for PT. In cases where a specific etiology was identified, MR-based imaging (MRI with contrast and MRA) or CT-based imaging (CT without contrast and CTA) were equally efficacious in identifying that etiology. MR-based imaging is preferred for neoplasms, while CT-based imaging is preferred for semicircular canal dehiscence.

ACR Appropriateness Criteria® Neck Mass-Adenopathy

A palpable neck mass may be the result of neoplastic, congenital, or inflammatory disease. Older age suggests neoplasia, and a congenital etiology is more prevalent in the pediatric population. The imaging approach is based on the patient age, mass location, and clinical pulsatility. Underlying human papillomavirus-related malignancy should be considered in all age groups. Although the imaging appearance of some processes in the head and neck overlap, choosing the appropriate imaging examination may allow a specific diagnosis, or a limited differential diagnosis. Tissue sampling is indicated to confirm suspected malignancy. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Tinnitus Neuroimaging

This article reviews the use of human neuroimaging for chronic subjective tinnitus. Evidence-based guidance on the clinical use of imaging to identify relevant auditory lesions when evaluating tinnitus patients is given. After introducing the anatomy and imaging modalities most pertinent to the neuroscience of tinnitus, the article reviews tinnitus-associated alterations in key auditory and nonauditory networks in the central nervous system. Emphasis is placed on how these findings support proposed models of tinnitus and how this line of investigation is relevant to practicing clinicians.