Automated vs. manual coding of neuroimaging reports via natural language processing, using the international classification of diseases, tenth revision.

Objective: Natural language processing (NLP) can generate diagnoses codes from imaging reports. Meanwhile, the International Classification of Diseases (ICD-10) codes are the United States' standard for billing/coding, which enable tracking disease burden and outcomes. This cross-sectional study aimed to test feasibility of an NLP algorithm's performance and comparison to radiologists' and physicians' manual coding. Methods: Three neuroradiologists and one non-radiologist physician reviewers manually coded a randomly-selected pool of 200 craniospinal CT and MRI reports from a pool of >10,000. The NLP algorithm (Radnosis, VEEV, Inc., Minneapolis, MN) subdivided each report's Impression into "phrases", with multiple ICD-10 matches for each phrase. Only viewing the Impression, the physician reviewers selected the single best ICD-10 code for each phrase. Codes selected by the physicians and algorithm were compared for agreement. Results: The algorithm extracted the reports' Impressions into 645 phrases, each having ranked ICD-10 matches. Regarding the reviewers' selected codes, pairwise agreement was unreliable (Krippendorff α = 0.39-0.63). Using unanimous reviewer agreement as "ground truth", the algorithm's sensitivity/specificity/F2 for top 5 codes was 0.88/0.80/0.83, and for the single best code was 0.67/0.82/0.67. The engine tabulated "pertinent negatives" as negative codes for stated findings (e.g. "no intracranial hemorrhage"). The engine's matching was more specific for shorter than full-length ICD-10 codes (p = 0.00582x10-3). Conclusions: Manual coding by physician reviewers has significant variability and is time-consuming, while the NLP algorithm's top 5 diagnosis codes are relatively accurate. This preliminary work demonstrates the feasibility and potential for generating codes with reliability and consistency. Future works may include correlating diagnosis codes with clinical encounter codes to evaluate imaging's impact on, and relevance to care.

Academic Neuroradiology: 2023 Update on Turn-Around Time, Financial Recruitment and Retention Strategies.

The ASNR Neuroradiology Division Chief Working Group's 2023 survey, with responses from 62 division chiefs, provides insights into turn-around times, faculty recruitment, moonlighting opportunities, and academic funds.In emergency cases, 61% aim for a turn-around time of less than 45-60 minutes, with two-thirds meeting this expectation more than 75% of the time. For inpatient CT and MRI scans, 54% achieve a turn-around time of 4-8 hours, with three quarters meeting this expectation at least 50% of the time. Outpatient scans have an expected turn-around time of 24-48 hours, which is met in 50% of cases.Faculty recruitment strategies included 35% offering sign-on bonuses, with a median of $30,000. Additionally, 23% provided bonuses to fellows during fellowship to retain them in the practice upon completion of their fellowship. Internal moonlighting opportunities for faculty were offered by 70% of divisions, with a median pay of $250 per hour.The median annual academic fund for a full-time neuroradiology faculty member was $6,000, typically excluding license fees but including ACR and ABR membership, leaving $4,000 for professional expenses.This survey calls for further dialogue on adapting and innovating academic institutions to meet evolving needs in neuroradiology.

Patient Engagement in Neuroradiology: A Narrative Review and Case Studies.

The field of patient engagement in radiology is evolving and offers ample opportunities for neuroradiologists to become involved. The patient journey can serve as a model that inspires patient engagement initiatives. The patient journey in radiology may be viewed in 5 stages: 1) awareness that an imaging test is needed, 2) considering having a specific imaging test, 3) access to imaging, 4) imaging service delivery, and 5) ongoing care. Here, we describe patient engagement opportunities based on literature review and paired with case studies by practicing neuroradiologists.

The Central Dot Sign : A Specific Post-gadolinium Enhancement Feature of Intramedullary Spinal Cord Metastases.

PURPOSE: Peripheral enhancement characteristics on magnetic resonance imaging (MRI), namely the rim and flame signs, are specific for intramedullary spinal cord metastases (ISCM) compared to primary cord masses. The study compared the frequency of a novel finding-the central dot sign-in ISCMs versus primary intramedullary masses. METHODS: In this study 45 patients with 64 ISCMs and 64 control patients with 64 primary intramedullary cord masses were investigated and 2 radiologists blinded to lesion type independently evaluated MR images for the presence of a central dot sign: a punctate focus of enhancement in/near the center of an enhancing intramedullary mass. The frequency of this sign in the two patient groups was compared. RESULTS: A total of 63 enhancing ISCMs in 44 patients and 54 enhancing primary cord masses in 54 patients were included. The central dot sign was identified in 6% (4/63) of enhancing ISCMs in 9% (4/44) of patients and in none (0/54) of the enhancing primary cord masses (p = 0.038, per patient). The specificity for diagnosing ISCMs among spinal cord masses was 100%. The central dot sign was present in the axial plane only in two ISCMs and in the axial and sagittal planes in two ISCMs. The two ISCMs harboring the central dot sign also demonstrated both the previously described rim and flame signs, and two also demonstrated the rim sign alone. CONCLUSION: The central dot sign is not sensitive but highly specific for ISCMs compared to primary spinal cord masses. The rim and/or flame signs may or may not be concurrently present in ISCMs.

Lumbar puncture under fluoroscopy guidance: a technical review for radiologists.

There are many differences in fluoroscopy-guided lumbar puncture (FG-LP) technique among radiologists. Even within the same institution, there are a variety of preferences among proceduralists with individual perspectives based on the literature, training, and/or experience. Our aim is to provide familiarity with various techniques involved in FG-LP and provide insight on how to improve patient outcomes. The pertinent anatomy and physiology, indications, contraindications, patient management, complications of the procedure, and procedural techniques for performing an FG-LP are reviewed in detail. Potentially controversial topics regarding FG-LP are also addressed. There are many differences in fluoroscopy-guided lumbar puncture (FG-LP) technique among radiologists (1). Even within the same institution, there are a variety of individual preferences among physicians with different perspectives based on a combination of literature familiarity, training, and personal experience. Our aim is to provide familiarity with various techniques involved in FG-LP, improve efficiency, and improve patient outcomes. We will also address possible controversial issues regarding FG-LPs using an evidence-based approach.

The efficacy of fluoroscopy-guided epidural blood patch in the treatment of spontaneous and iatrogenic cerebrospinal fluid leakage.

OBJECTIVE: To evaluate patient outcomes following fluoroscopy-guided epidural blood patch (FGEBP), factors affecting the outcome, and to identify the rate of fluoroscopy-guided lumbar punctures (FGLP) requiring FGEBP. METHODS: All FGLPs and FGEBPs between January 2014 and May 2017 were retrospectively evaluated. Information regarding patient characteristics, details of previous dural puncture (DP), details of the FGEBP, and FGEBP outcome were recorded. The outcome was classified into three categories as "complete response", "partial response", and "no response". Patients with "complete response" were compared to the combined group of "no response" and "partial response", classified as "incomplete response". Two-sample/Fisher's exact (continued/categorical variables) tests were used (p < 0.05). RESULTS: Sity-seven FGEBPs were performed in 63 patients (female/male, 36/27; mean age/BMI 38/28.2). Fifty-nine were referred following DP; 31 were performed by radiologists. The rate of FGLPs requiring FGEBP was 1.78% within 3.5 years. The mean DP-FGEBP interval was 4.8 days. "Complete response" was achieved in 56 (84.8%), "no response" was found following 4 (6%) procedures. Average applied blood volume was 16 cc (5-30 cc). No difference was found between "complete response" and "incomplete response" groups regarding age, sex, BMI, DP performer, DP level, DP fluoroscopy time, DP needle caliber/type, FGEBP level, FGEBP needle caliber/type, FGEBP fluoroscopy time, FGEBP performer, and applied blood volume (p > 0.05). Despite approaching significance, no statistically significant difference was found regarding the presence of previous DP (p = 0.06). CONCLUSIONS: The efficacy of FGEBP is high in a group of patients referred to radiology for treatment of CSF leakage with complete response in 84.8% of patients. KEY POINTS: • Fluoroscopy-guided epidural blood patch completely resolved symptoms in 85% of post-dural puncture headaches. • The success approaches 95% when including the patients with partial resolution of symptoms. • Epidural blood patch rate is found 1.8% following 1703 fluoroscopy-guided lumbar punctures.

Concomitant Acute Toxic Leukoencephalopathy and Posterior Reversible Encephalopathy Syndrome.

BACKGROUND AND PURPOSE: Posterior reversible encephalopathy syndrome (PRES) and acute toxic leukoencephalopathy (ATL) are both potentially reversible clinicoradiologic entities. Although their magnetic resonance imaging (MRI) findings differ, rarely both may occur simultaneously in acutely encephalopathic patients. Our aim was to determine the incidence and causes of concomitant "ATL-PRES." METHODS: Retrospective search of suspected acutely encephalopathic adults since 1998 throughout our picture archiving and communication system revealed 167 patients with PRES and 106 patients with ATL. Images of these patients were retrospectively evaluated by two neuroradiologists and a fellow to identify the cases which carry both features of PRES and ATL. Imaging findings were scored based on previously reported scoring system as mild, moderate, and severe. The clinical outcome of the patients was determined according to the modified Rankin scale. RESULTS: Our search revealed a series of 6 patients (%2.2) in 273 patients who presented acutely with either encephalopathy or seizures, caused by various etiologies, including immunosuppression following transplantation (n = 2), hypertensive crisis (n = 2), chemotherapy (n = 1), and sepsis (n = 1). MRI demonstrated findings consistent with both PRES and ATL simultaneously on FLAIR and diffusion weighted imaging. Severity of imaging findings of concomitant "ATL-PRES" was concordant with each other (rho ≈ 1.0, P < .00001), and each patient eventually returned to clinical baseline. This finding, along with their similar etiologies, raises the possibility of an underlying common pathophysiologic thread, perhaps being endothelial toxicity. CONCLUSIONS: Concomitant "ATL-PRES" was found in 2.2% of the patients in a large cohort of ATL and PRES. Etiologies varied. Clinical symptoms and MRI findings were potentially reversible.

Utility of coronal contrast-enhanced fat-suppressed FLAIR in the evaluation of optic neuropathy and atrophy.

BACKGROUND AND PURPOSE: Evaluating chronic sequelae of optic neuritis, such as optic neuropathy with or without optic nerve atrophy, can be challenging on whole brain MRI. This study evaluated the utility of dedicated coronal contrast-enhanced fat-suppressed FLAIR (CE-FS-FLAIR) MR imaging to detect optic neuropathy and optic nerve atrophy. MATERIALS AND METHODS: Over 4.5 years, a 3 mm coronal CE-FS-FLAIR sequence at 1.5T was added to the routine brain MRIs of 124 consecutive patients, 102 of whom had suspected or known demyelinating disease. Retrospective record reviews confirmed that 28 of these 102 had documented onset of optic neuritis >4 weeks prior to the brain MRI. These 28 were compared to the other 22 ("controls") of the 124 patients who lacked a history of demyelinating disease or visual symptoms. Using coronal CE-FS-FLAIR, two neuroradiologists separately graded each optic nerve (n = 50 patients, 100 total nerves) as either negative, equivocal, or positive for optic neuropathy or atrophy. The scoring was later repeated. RESULTS: The mean time from acute optic neuritis onset to MRI was 4.1 ± 4.6 years (range 34 days-17.4 years). Per individual nerve grading, the range of sensitivity, specificity, and accuracy of coronal CE-FS-FLAIR in detecting optic neuropathy was 71.4-77.1%, 93.8-95.4%, and 85.5-89.0%, respectively, with strong interobserver (k = 0.667 - 0.678, p < 0.0001), and intraobserver (k = 0.706 - 0.763, p < 0.0001) agreement. For optic atrophy, interobserver agreement was moderate (k = 0.437 - 0.484, p < 0.0001), while intraobserver agreement was moderate-strong (k = 0.491 - 0.596, p < 0.0001). CONCLUSION: Coronal CE-FS-FLAIR is quite specific in detecting optic neuropathy years after the onset of acute optic neuritis, but is less useful in detecting optic nerve atrophy.

All that bleeds is not black: susceptibility weighted imaging of intracranial hemorrhage and the effect of T1 signal.

PURPOSE: To determine if intracranial hemorrhages (ICH) are always hypointense on Susceptibility weighted imaging (SWI) and to determine the effect of T1-signal intensity on the appearance of ICH in SWI series. METHODS: SWI and T1-signal intensities of ICH were retrospectively studied in a series of patients. SWI signal intensities were statistically correlated with T1-signal intensities. RESULTS: In a series of 57 MRI scans from 40 patients, ICH was hypointense in 19, mixed-intensity in 21, and hyperintense in 17. Hyperintensity of ICH on SWI was significantly associated with increased T1 signal (P<.001). CONCLUSION: ICH can have a varied appearance on SWI.

The Effects of DWI-Infarct Lesion Volume on DWI-FLAIR Mismatch: Is There a Need for Size Stratification?

BACKGROUND: The lack of fluid-attenuated inversion-recovery (FLAIR) hyperintensity in areas of diffusion-weighted imaging (DWI) high signal, or DWI-FLAIR mismatch, is a potential imaging biomarker for timing of stroke onset. We aimed to determine the effects of DWI infarct lesion volume on DWI-FLAIR mismatch and its accuracy for identification of strokes within intravenous (IV) the thrombolytic therapy window. METHODS: Acute ischemic stroke patients with magnetic resonance imaging scan within 12 hours of witnessed stroke were included. Two neuroradiologists independently reviewed DWI and FLAIR sequences for DWI-FLAIR mismatch in areas of restricted diffusion compared to the contralateral normal side. RESULTS: DWI-FLAIR mismatch was identified in 21/82 (26%) patients. Infarct lesions with DWI-FLAIR mismatch were scanned earlier (3.8 ± .3 vs. 7.5 ± .3 hours from onset, P < .001) and were smaller in size (8.9±2.3 vs. 43.1±11.9 mL, P = .007) compared to lesions without mismatch. Multivariate regression analysis showed a significant interaction between lesion volume and time-from-onset in relationship with the presence of DWI-FLAIR mismatch (P = .045). The presence of DWI-FLAIR mismatch had 56% sensitivity, 83% specificity, 48% positive predictive value (PPV), and 87% negative predictive value (NPV) for identification of infarction within 4.5 hours of symptom onset; while for infarct lesions >15 mL, the DWI-FLAIR mismatch had 100% specificity and PPV for acute infarcts within 4.5 hours of onset. CONCLUSION: The effects of stroke onset-to-scan time gap on DWI-FLAIR mismatch are not the same for different DWI lesion volumes. At DWI lesion volumes >15 mL, the DWI-FLAIR mismatch is highly specific for acute infarcts within IV thrombolytic therapy time, and can identify wake-up stroke patients eligible for treatment.

Susceptibility-diffusion mismatch in middle cerebral artery territory acute ischemic stroke: clinical and imaging implications.

Background Recent studies have suggested a correlation between susceptibility-diffusion mismatch and perfusion-diffusion mismatch in acute ischemic stroke patients. Purpose To determine the clinical and imaging associations of susceptibility-diffusion mismatch in patients with acute ischemic stroke in the middle cerebral artery (MCA) territory. Material and Methods Consecutive patients with MCA territory acute ischemic stroke, who had magnetic resonance imaging (MRI) performed with susceptibility-weighted imaging (SWI) and diffusion-weighted imaging (DWI) within 24 h of symptom onset or time last-seen-well, were included. Two neuroradiologists reviewed SWI scans for SWI-DWI mismatch defined by regionally increased vessel number or diameter on SWI extending beyond the DWI hyperintensity territory in the affected hemisphere. The stroke severity at admission was evaluated using the National Institutes of Health Stroke Scale (NIHSS) score. Poor clinical outcome was defined by a 3-month modified Rankin Scale (mRS) score >2. Results The SWI-DWI mismatch was identified in 44 (29.3%) of 150 patients included in this study. Patients with SWI-DWI mismatch had smaller admission infarct volumes (31.2 ± 44.7 versus 55.9 ± 117.7 mL, P = 0.045) and were younger (60.4 ± 18.9 versus 67.1 ± 15.5, P = 0.026). After correction for age, admission NIHSS score, and infarct volume, the SWI-DWI mismatch was associated with a 22.6% lower rate of poor clinical outcome using propensity score matching ( P = 0.032). In our cohort, thrombolytic therapy showed no significant effect on outcome. Conclusion The presence of SWI-DWI mismatch in acute MCA territory ischemic infarct is associated with smaller infarct volume. Moreover, SWI-DWI mismatch was associated with better outcome after correction for infarct size, severity of admission symptoms, and age.

Prominent cortical and medullary veins on susceptibility-weighted images of acute ischaemic stroke.

OBJECTIVE: To determine the clinical and imaging implications of prominent cortical and medullary veins on susceptibility-weighted images (SWI) of patients with acute stroke. METHODS: Consecutive patients with acute ischaemic stroke who had SWI scan within 24 h of symptom onset or time last-seen-well were included. The SWI series were reviewed for the presence of prominent cortical and medullary veins and were graded independently by two neuroradiologists. The correlations between prominent vein grades with different imaging and clinical variables were determined. RESULTS: Among 213 patients, prominent SWI cortical and medullary veins were identified in 35 (16.4%) patients and 20 (9.4%) patients, respectively. There was fair interobserver agreement (k = 0.314-0.338, p ≤ 0.001) for grading, and moderate agreement (k = 0.406-0.413, p ≤ 0.001) for the presence of prominent veins. Both prominent cortical and medullary veins were associated with the presence of arterial occlusion (rho = 0.232, p = 0.001; rho = 0.180, p = 0.008; respectively) and larger infarct volume (rho = 0.445, p < 0.001; rho = 0.167, p = 0.015; respectively). However, neither cortical nor medullary cortical veins were associated with the severity of symptoms at admission or clinical outcome. Prominent cortical veins were independent predictors of arterial occlusion (p = 0.018), whereas prominent medullary veins were more strongly associated with larger infarct volumes (p < 0.001). CONCLUSION: There were small but significant correlations between cortical and medullary veins on SWI with arterial occlusion and large infarct volume in acute ischaemic stroke. Advances in knowledge: In consecutive patients with acute ischaemic stroke within anterior and posterior circulation territories, prominent cortical and medullary veins on SWI series are associated with imaging biomarkers of poor clinical outcome (i.e. large infarct volume and major arterial occlusion).

Preliminary experience with intravenous gadoxetate disodium as a craniospinal MR contrast agent.

INTRODUCTION: Gadoxetate disodium is a gadolinium-based contrast agent (GBCA) typically used for body imaging, as about 50% of its excretion is via the liver. Its use for craniospinal MRI has not been reported. MATERIALS AND METHODS: Over a 3 years period, 31 adults underwent postcontrast MRI using gadoxetate disodium, each of whom had a relative contraindication to a GBCA, but a GBCA was deemed necessary by the clinical service to direct therapy. Postcontrast T1WI included either gradient-echo (GET1WI, n=12) or spin-echo (SET1WI, n=13) imaging. The contraindication in 29 patients was stage 3-5 chronic kidney disease (CKD) or acute kidney injury (AKI); the other two had normal kidney function, but a history of a reaction to another GBCA (vomiting in one and hypersensitivity in the other). Over a 3 years period, in those patients in whom a GBCA was both deemed necessary and had an estimated GFR (eGFR) of <40 ml/min/1.73 m(2) (i.e., stage 3-5 CKD), both informed consent and nephrology consultation was obtained. A 10 ml dose was given for cranial (n=23), spinal (n=9), and neck/face MRI (n=3), as well as craniocervical MRA (n=6). Three neuroradiologists separately evaluated for normal enhancement in 11 structures. The contrast enhancing percentage (CE%) was measured in 3 structures, and in enhancing lesions, if present. RESULTS: The pre-MRI eGFR was not significantly different from that at 30-90 days (p=0.522) in the 23 patients with an available eGFR at >90 days post-MRI; no patients developed acute kidney injury post-MRI, nor nephrogenic systemic fibrosis. Of the 11 intracranial structures scored, the superior sagittal sinus, pituitary stalk, and atrial choroid plexus enhanced in all 23 patients who underwent brain MRI, with CE%'s of 171.0%, 73.0%, and 69.8%, respectively. The number of patients with enhancing lesions were 3/23 brain MRI's, 8/9 spinal MRI's, 3/3 neck MRI's, and 2/6 craniocervical MRA/MRV's. In 9 spinal MRI's, the basivertebral plexus CE% was 213.7%; in the 7 with spondylodiscitis, the CE% measured 125.8% in enhancing epidural tissue, with a contrast-to-noise ratio (CNR) of 98.0%. CONCLUSION: This preliminary report describes the use of gadoxetate disodium as an alternative GBCA for craniospinal MRI and MRA in the renally impaired, but its efficacy in this regard must be further evaluated prospectively.

Posterior reversible encephalopathy syndrome.

Posterior reversible encephalopathy syndrome (PRES) is a complex disorder, our understanding of which continues to evolve. PRES has many clinical associations, many causative factors, a variety of imaging manifestations, and its pathophysiology remains a topic of debate. There are also many other disorders that may mimic PRES. We present a concise review of PRES to enable the radiologist to more readily and easily recognize this treatable disorder with important clinical implications.

Multiple myeloma of the thyroid cartilage.

A 60-year-old male presented with hoarseness. His past medical history was remarkable for a plasmacytoma of the left maxillary sinus having been resected without systemic evidence of plasma cell myeloma (PCM), also known as multiple myeloma (MM), at the time. This maxillary sinus disease recurred and was treated with radiation. Workup for PCM was conducted. Treatment included melphalan and autologous stem cell transplant. Because of the therapeutic and prognostic implications, a Plasma cell neoplasm (PCN) in a neck mass must be carefully evaluated by clinical and pathological criteria in order to distinguish plasmacytoma from PCM. PCN involvement of the thyroid cartilage is very rare, with only 5 previously reported cases.