Automated grading of enlarged perivascular spaces in clinical imaging data of an acute stroke cohort using an interpretable, 3D deep learning framework.

Enlarged perivascular spaces (EPVS), specifically in stroke patients, has been shown to strongly correlate with other measures of small vessel disease and cognitive impairment at 1 year follow-up. Typical grading of EPVS is often challenging and time consuming and is usually based on a subjective visual rating scale. The purpose of the current study was to develop an interpretable, 3D neural network for grading enlarged perivascular spaces (EPVS) severity at the level of the basal ganglia using clinical-grade imaging in a heterogenous acute stroke cohort, in the context of total cerebral small vessel disease (CSVD) burden. T2-weighted images from a retrospective cohort of 262 acute stroke patients, collected in 2015 from 5 regional medical centers, were used for analyses. Patients were given a label of 0 for none-to-mild EPVS (< 10) and 1 for moderate-to-severe EPVS (≥ 10). A three-dimensional residual network of 152 layers (3D-ResNet-152) was created to predict EPVS severity and 3D gradient class activation mapping (3DGradCAM) was used for visual interpretation of results. Our model achieved an accuracy 0.897 and area-under-the-curve of 0.879 on a hold-out test set of 15% of the total cohort (n = 39). 3DGradCAM showed areas of focus that were in physiologically valid locations, including other prevalent areas for EPVS. These maps also suggested that distribution of class activation values is indicative of the confidence in the model's decision. Potential clinical implications of our results include: (1) support for feasibility of automated of EPVS scoring using clinical-grade neuroimaging data, potentially alleviating rater subjectivity and improving confidence of visual rating scales, and (2) demonstration that explainable models are critical for clinical translation.

Utility of Magnetic Resonance Imaging in Differentiating Cerebrospinal Fluid Leak from Middle Ear Effusion.

OBJECTIVE: To demonstrate the clinical utility, sensitivity, and specificity of standard magnetic resonance imaging (MRI) sequences in differentiating temporal bone cerebrospinal fluid leaks from all other middle ear effusions. STUDY DESIGN: Retrospective imaging review. SETTING: Academic medical center. SUBJECTS: Patients with cerebrospinal fluid leaks or other middle ear effusions who also underwent MRI. METHODS: Patients were assigned to cerebrospinal fluid leak and other effusion cohorts based on clinical course, findings at surgery/myringotomy, and beta-2 transferrin fluid analysis. Reviewers blinded to the clinical outcome examined T1-weighted, T2-weighted, diffusion-weighted, fluid-attenuated inversion recovery (FLAIR), and 3-dimensional (3D) acquired T2-weighted MRI sequences. For each sequence, fluid imaged in the temporal bone was graded as either similar or dissimilar in signal intensity to cerebrospinal fluid in the adjacent subarachnoid space. Signal similarity was interpreted as being diagnostic of a leak. Test characteristics in predicting the presence of a leak were calculated for each series. RESULTS: Eighty patients met criteria (41 leaks, 39 other effusions). The 3D T2 series was 76% sensitive and 100% specific in diagnosing a leak, and FLAIR was 44% sensitive and 100% specific. The T1-weighted (73% sensitive, 69% specific), T2-weighted (98% sensitive, 5.1% specific), and diffusion-weighted (63% sensitive, 66% specific) series were less useful. CONCLUSIONS: MRI, with attention to 3D T2 and FLAIR series, is a noninvasive and highly specific test for diagnosing cerebrospinal fluid leak in the setting of an indeterminate middle ear effusion.

ACR Appropriateness Criteria® Cranial Neuropathy.

Evaluation of cranial neuropathy can be complex given the different pathway of each cranial nerve as well as the associated anatomic landmarks. Radiological evaluation requires imaging of the entire course of the nerve from its nucleus to the end organ. MRI is the modality of choice with CT playing a complementary role, particularly in the evaluation of the bone anatomy. Since neoplastic and inflammatory lesions are prevalent on the differential diagnosis, contrast enhanced studies are preferred when possible. The American College of Radiology Appropriateness Criteria are evidencebased 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.

ACR Appropriateness Criteria® Sinonasal Disease.

Imaging of sinonasal pathology may occur for assessment of rhinosinusitis or mass lesions. Rhinosinusitis is prevalent in up to 16% of the US population with annual economic burdens estimated at 22 billion dollars. Rhinosinusitis is characterized as acute or chronic based on symptom duration; if four or more episodes occur annually, the term recurrent acute rhinosinusitis (RARS) is used. In acute uncomplicated rhinosinusitis when inflammatory change remains in the paranasal sinuses and nasal cavity, imaging may not be required. Distinction between viral or bacterial rhinosinusitis is a clinical diagnosis, and imaging should be interpreted in conjunction with clinical and endoscopic findings. Sinus CT imaging is appropriate per clinical judgment in associated complications including headache, facial pain, swelling, orbital proptosis, or cranial nerve palsies. In maxillary sinusitis, teeth may require assessment because 20% may be odontogenic in origin. MRI may be complementary in aggressive infections with intraocular/intracranial complications, invasive fungal sinusitis, or sinonasal masses. 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.

ACR Appropriateness Criteria® Tinnitus.

Tinnitus is the perception of sound in the absence of an external source. It is a common symptom that can be related to hearing loss and other benign causes. However, tinnitus may be disabling and can be the only symptom in a patient with a central nervous system process disorder. History and physical examination are crucial first steps to determine the need for imaging. CT and MRI are useful in the setting of pulsatile tinnitus to evaluate for an underlying vascular anomaly or abnormality. If there is concomitant asymmetric hearing loss, neurologic deficit, or head trauma, imaging should be guided by those respective ACR Appropriateness Criteria® documents, rather than the presence of tinnitus. Imaging is not usually appropriate in the evaluation of subjective, nonpulsatile tinnitus that does not localize to one ear. 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.

ACR Appropriateness Criteria® Plexopathy.

MRI without and with contrast is the most accurate imaging method to determine whether a process is intrinsic or extrinsic to a nerve of the brachial or lumbosacral plexus. However, there are no Current Procedural Terminology codes to correspond to imaging studies of the brachial or lumbar plexus discretely. This assessment uses "MRI of the brachial plexus" or "MRI of the lumbosacral plexus" as independent entities given that imaging acquisition for the respective plexus differs in sequences and planes compared with those of a routine neck, chest, spine, or pelvic MRI, yet acknowledges the potential variability of ordering practices across institutions. In patients unable to undergo MRI, CT offers the next highest level of anatomic evaluation. In oncologic patients, PET/CT imaging can identify the extent of tumor involvement and be beneficial to differentiate radiation plexitis from tumor recurrence but provides limited resolution of the plexus itself. 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.

ACR Appropriateness Criteria® Cerebrovascular Disease.

Diseases of the cerebral vasculature represent a heterogeneous group of ischemic and hemorrhagic etiologies, which often manifest clinically as an acute neurologic deficit also known as stroke or less commonly with symptoms such as headache or seizures. Stroke is the fourth leading cause of death and is a leading cause of serious long-term disability in the United States. Eighty-seven percent of strokes are ischemic, 10% are due to intracerebral hemorrhage, and 3% are secondary to subarachnoid hemorrhage. The past two decades have seen significant developments in the screening, diagnosis, and treatment of ischemic and hemorrhagic causes of stroke with advancements in CT and MRI technology and novel treatment devices and techniques. Multiple different imaging modalities can be used in the evaluation of cerebrovascular disease. The different imaging modalities all have their own niches and their own advantages and disadvantages in the evaluation of cerebrovascular disease. 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.

Radiographic Evidence of Occult Intracranial Hypertension in Patients with Ménière's Disease.

Objectives (1) Describe the prevalence of radiographic signs of intracranial hypertension (ICH) in Ménière's disease (MD) and (2) compare the prevalence of radiographic signs of ICH in MD patients managed medically to those managed surgically. Study Design Case-control study. Setting Academic neurotologic practice. Subjects and Methods Adult MD patients (aged ≥17 years) treated from 2011 to 2015 were reviewed. Inclusion required magnetic resonance imaging (MRI) of the head and follow-up >6 months. Patients with intracranial tumors, mass effect, trauma, previous intracranial surgery, and glaucoma were excluded. MD patients were separated by administered treatment into medical and surgical subgroups. Cochlear implant (CI) recipients served as radiographic controls. Eighty-four MD patients (46 surgical, 38 medical) and 37 CI controls were assessed. MRI measurements assessed for empty/partial sella (ES/PS), dilated/tortuous optic nerve sheath (ONS), and posterior globe flattening (PGF). Results Mean age was 53.8 ± 1.3 years and median body mass index (BMI) was 28.2 kg/m2. Of the patients, 64% were female and 92% were white. MRI findings in the MD cohort were as follows: ES/PS, 46.4%; ONS change, 42.8%; and PGF, 8.3%. The prevalence of ONS change was higher in MD patients than in controls (42.8% vs 13.5%, P = .003). The surgical MD group had higher prevalence of ONS change (52%) compared with the medical group (31.5%, P = .05) and controls (13.5%, P = .0004). The surgical group had a higher prevalence of ≥2 simultaneous MRI findings compared with medical MD patients (39% vs 10%, P = .01) and controls (14%, P = .01). Conclusion MD patients demonstrate a high prevalence of radiographic signs of ICH. MD patients who required surgery had a greater prevalence of radiographic signs of ICH compared with non-MD patients and medically managed MD patients.

ACR Appropriateness Criteria Low Back Pain.

Most patients presenting with uncomplicated acute low back pain (LBP) and/or radiculopathy do not require imaging. Imaging is considered in those patients who have had up to 6 weeks of medical management and physical therapy that resulted in little or no improvement in their back pain. It is also considered for those patients presenting with red flags raising suspicion for serious underlying conditions, such as cauda equina syndrome, malignancy, fracture, and infection. Many imaging modalities are available to clinicians and radiologists for evaluating LBP. Application of these modalities depends largely on the working diagnosis, the urgency of the clinical problem, and comorbidities of the patient. When there is concern for fracture of the lumbar spine, multidetector CT is recommended. Those deemed to be interventional candidates, with LBP lasting for > 6 weeks having completed conservative management with persistent radiculopathic symptoms, may seek MRI. Patients with severe or progressive neurologic deficit on presentation and red flags should be evaluated with MRI. The ACR 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 (the RAND/UCLA Appropriateness Method and the Grading of Recommendations Assessment, Development, and Evaluation) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances in which evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

ACR Appropriateness Criteria Head Trauma.

Neuroimaging plays an important role in the management of head trauma. Several guidelines have been published for identifying which patients can avoid neuroimaging. Noncontrast head CT is the most appropriate initial examination in patients with minor or mild acute closed head injury who require neuroimaging as well as patients with moderate to severe acute closed head injury. In short-term follow-up neuroimaging of acute traumatic brain injury, CT and MRI may have complementary roles. In subacute to chronic traumatic brain injury, MRI is the most appropriate initial examination, though CT may have a complementary role in select circumstances. Advanced neuroimaging techniques are areas of active research but are not considered routine clinical practice at this time. In suspected intracranial vascular injury, CT angiography or venography or MR angiography or venography is the most appropriate imaging study. In suspected posttraumatic cerebrospinal fluid leak, high-resolution noncontrast skull base CT is the most appropriate initial imaging study to identify the source, with cisternography reserved for problem solving. The ACR Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed every three years by a multidisciplinary expert panel. The guideline development and review include an extensive analysis of current medical literature from peer-reviewed journals and the application of a well-established consensus methodology (modified Delphi) to rate the appropriateness of imaging and treatment procedures by the panel. In those instances in which evidence is lacking or not definitive, expert opinion may be used to recommend imaging or treatment.

MR imaging findings of endophthalmitis.

Endophthalmitis is a sight-threatening ophthalmologic emergency. The clinical diagnosis is often challenging, and delayed diagnosis may exacerbate the poor visual prognosis. B-scan ultrasonography or spectral domain optical coherence tomography are imaging aids at the clinician's office. Cross-sectional imaging such as CT and particularly MRI can also help in the assessment of disease extent or complications. MR imaging findings are rarely described in the literature. Here, we discuss the spectrum of imaging findings of endophthalmitis and correlate them with key anatomic and pathophysiologic details of the globe. Early disease is often subtle on MR imaging with thick uveal enhancement, while advanced disease demonstrates retinal/choroidal detachment, vitreal exudates and peribulbar inflammation. Other noninfectious inflammatory diseases of the globe can show similar findings; however, MR diffusion-weighted images help identify infectious exudates and evaluate response to therapy. Knowledge of the spectrum of imaging findings of this disease is important for radiologists and help in the management decision process.

Head and neck reconstructive surgery: what the radiologist needs to know.

UNLABELLED: Head and neck reconstructive surgery after cancer ablative surgery is now commonly performed with closure of the surgical defects by microvascular free tissue transfer. The most common flaps used for reconstruction are the radial forearm flap, the anterolateral thigh flap and fibula flap. Radiographic appearance of these flaps depends on the individual components of the flap, and may consist of skin, fat, muscle and/or bone. There are various adverse outcomes in these patients, the most significant being tumour recurrence that typically occurs at the flap margins. Other flap complications include flap necrosis from vascular thrombosis or infection. The goal of this article is to enhance radiologists' familiarity with different methods of flap reconstruction, flap margins and vascular anastomoses that will lead to a better appreciation of expected postoperative radiographic appearance. KEY POINTS: • Flaps are the most common reconstructive techniques used in neck cancer surgery. • Imaging appearance of flaps depends on their components and time since surgery. • Most tumour recurrence after reconstruction occurs at the margins of the flap.

ACR Appropriateness Criteria Myelopathy.

Patients presenting with myelopathic symptoms may have a number of causative intradural and extradural etiologies, including disc degenerative diseases, spinal masses, infectious or inflammatory processes, vascular compromise, and vertebral fracture. Patients may present acutely or insidiously and may progress toward long-term paralysis if not treated promptly and effectively. Noncontrast CT is the most appropriate first examination in acute trauma cases to diagnose vertebral fracture as the cause of acute myelopathy. In most nontraumatic cases, MRI is the modality of choice to evaluate the location, severity, and causative etiology of spinal cord myelopathy, and predicts which patients may benefit from surgery. Myelopathy from spinal stenosis and spinal osteoarthritis is best confirmed without MRI intravenous contrast. Many other myelopathic conditions are more easily visualized after contrast administration. Imaging performed should be limited to the appropriate spinal levels, based on history, physical examination, and clinical judgment. The ACR Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed every three years by a multidisciplinary expert panel. The guideline development and review include an extensive analysis of current medical literature from peer-reviewed journals, and the application of a well-established consensus methodology (modified Delphi) to rate the appropriateness of imaging and treatment procedures by the panel. In those instances in which evidence is lacking or not definitive, expert opinion may be used to recommend imaging or treatment.

Isolated cochlear neuritis from varicella reactivation mimicking a vestibular schwannoma.

We present a case of a patient with progressive unilateral sensorineural hearing loss and tinnitus with internal auditory canal enhancement on magnetic resonance imaging (MRI) secondary to isolated cochlear neuritis from varicella reactivation. MRI following antiviral treatment showed resolution of enhancement. Varicella reactivation is commonly seen in the form of Ramsay Hunt syndrome, which is known to produce abnormal MRI enhancement from facial and vestibulocochlear neuritis; however, its characteristic clinical signs aid the diagnosis. This case is unique in that the only manifestation of varicella infection was unilateral hearing loss. This case outlines the importance of maintaining a broad differential diagnosis in the evaluation of unilateral hearing loss as well as recognizing the limited specificity of MRI.

ACR Appropriateness Criteria Imaging in the Diagnosis of Thoracic Outlet Syndrome.

Thoracic outlet syndrome is a clinical entity characterized by compression of the neurovascular bundle, and may be associated with additional findings such as venous thrombosis, arterial stenosis, or neurologic symptoms. The goal of imaging is to localize the site of compression, the compressing structure, and the compressed organ or vessel, while excluding common mimics. A literature review is provided of current indications for diagnostic imaging, with discussion of potential limitations and benefits of the respective modalities. The ACR Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed every 3 years by a multidisciplinary expert panel. The guideline development and review include an extensive analysis of current medical literature from peer-reviewed journals and the application of a well-established consensus methodology (modified Delphi) to rate the appropriateness of imaging and treatment procedures by the panel. In those instances in which evidence is lacking or not definitive, expert opinion may be used to recommend imaging or treatment. In this document, we provided guidelines for use of various imaging modalities for assessment of thoracic outlet syndrome.

Magnetic resonance imaging in sinonasal disease.

Computed tomography (CT) is often the primary imaging modality for the evaluation of sinonasal disease. For some indications, magnetic resonance imaging (MRI) may provide additional information. There are established indications for using MRI in complicated sinonasal inflammatory disease, invasive fungal sinus disease, and sinonasal mass lesions. When MRI is used in the evaluation of sinonasal disease, it is usually used as a complementary modality in addition to CT. Magnetic resonance imaging in sinonasal disease can be used to further characterize the primary sinonasal disease process and to evaluate the extent of complications such as orbital or intracranial involvement. When MRI is used in sinonasal disease, it should be evaluated in the context of the clinical situation and CT imaging features. This will help radiologists provide a meaningful differential diagnosis to assist in clinical management.

ACR appropriateness criteria sinonasal disease.

Sinonasal imaging is performed in 2 major clinical scenarios: inflammatory rhinosinusitis or suspected mass lesion. Rhinosinusitis affects more than 16% of the US population annually. It poses an immense economic burden, accounting for more than 26 million outpatient visits annually and costing more than $4.3 billion annually in direct medical expenses. Most cases of uncomplicated acute and subacute rhinosinusitis are diagnosed clinically and should not require any imaging procedure. CT of the sinuses without contrast is the imaging method of choice in patients with recurrent acute sinusitis or chronic sinusitis. Sinusitis cannot be diagnosed on the basis of imaging findings alone. CT scan findings should be interpreted in conjunction with clinical and endoscopic findings. MRI is currently used for evaluation of sinus disease as a complementary study in cases of aggressive sinus infection with ocular/intracranial complications, potential invasive fungal sinusitis in immunocompromised patients or in the evaluation of a sinonasal mass. The ACR Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed every 2 years by a multidisciplinary expert panel. The guideline development and review include an extensive analysis of current medical literature from peer-reviewed journals and the application of a well-established consensus methodology (modified Delphi) to rate the appropriateness of imaging and treatment procedures by the panel. In those instances where evidence is lacking or not definitive, expert opinion may be used to recommend imaging or treatment.