The diagnosis of idiopathic intracranial hypertension (IIH) is often challenging in patients who do not present with classic symptoms. Brain MRI can play a pivotal role, as several imaging findings, such as an empty sella appearance (ESA), have been shown to be associated with IIH. Yet, none of the MRI signs have been shown to have a high sensitivity and specificity. In this study, we tested the hypothesis that presence of a geniculate ganglion diverticulum (GGD) is a potential imaging marker for the detection of IIH.
This is an IRB-approved, single-institution, retrospective, observational study. Brain MRI examinations of patients referred to Radiology by Otology clinic over a period of 10 years were reviewed. 244 MRI exams fulfilling inclusion and exclusion criteria were independently screened for the presence of GGD and ESA by two Neuroradiology fellows. Electronic medical records (EMR) of patients in this study were reviewed for presence of clinical manifestations of IIH. Receiver operator characteristic (ROC) curves were generated to estimate the accuracy of each covariate in diagnosing IIH. The area under each ROC curve (AUC) was calculated to identify an accurate prognostic covariate. Statistical analysis was done using R programming language V 4.2.2.
GGD was identified in MRI exams of 51 patients. A 2:1 propensity score (PS) matching for age, gender, and Body Mass Index (BMI) was used to select non-GGD control group for comparison with the GGD group. There was strong agreement between the 2 reviewers (kappa = 0.81, agreement = 95 %). Twelve patients in this study were diagnosed with IIH. There was a high incidence of GGD (OR = 12.19, 95 % CI (2.56, 58.10)) and ESA (OR = 4.97, 95 % CI (1.47, 16.74)) in IIH patients. The AUC observed in GGD for predicting IIH was 0.771 (0.655–0.888), specificity = 0.709 (0.638–0.780), and sensitivity = 0.833 (0.583–1). The AUC observed for ESA in predicting IIH was 0.682 (0.532–0.831), specificity = 0.780 (0.709–0.844), and sensitivity = 0.583 (0.333–0.833).
GGD is potentially a novel imaging marker of IIH with sensitivity higher than and specificity comparable to that of ESA.
Presence of GGD should raise the possibility of IIH.
Favorable clinical outcomes have been reported with the adjunct use of beta-blockers in cancer treatment, hypothetically secondary to their anti-angiogenic/anti-proliferative effects. Hereby, we investigate whether there is synergy between beta-blockers and TACE in the treatment of HCC.
36 HCC patients on beta-blockers (mean dose of 48 mg daily) at the time of first-line treatment with TACE at our institution were retrospectively identified out of a cohort of 221 patients between 2008 and 2019. Using propensity scoring, a matched cohort of 36 patients not exposed to beta-blockers was generated based on age, gender, ethnicity, etiology of liver disease, BCLC, child Pugh score, PS/ECOG, cirrhosis, largest mass treated, type of TACE and treated liver segments. Tumor response was assessed at 1st and 2nd post-TACE imaging timepoints (1.4 and 4.1 months on average respectively). Variables were compared using chi-square test and Student's t-test. Kaplan-Meier transplant-free survival plots were generated using IBM® SPSS® software. Cox regression analysis was used to evaluate survival predictors. A p values < 0.05 was considered significant.
Comparing the control and beta-blocker cohorts, there were no differences in baseline characteristics, post-TACE imaging timepoints, tumor response or transplant free survival (p > 0.05). Tumor size was found to be a predictor of survival when the two cohorts were combined (p = 0.03).
Transplant-free survival and HCC response to first-line TACE treatment were similar in the control and beta-blocker groups. Large tumor sizes were associated with higher mortality in combined analysis of the cohorts.
AI adoption requires perceived value by end-users. AI-enabled opportunistic CT screening (OS) detects incidental clinically meaningful imaging risk markers on CT for potential preventative health benefit. This investigation assesses radiologists' perspectives on AI and OS.
An online survey was distributed to 7500 practicing radiologists among ACR membership of which 4619 opened the emails. Familiarity with and views of AI applications were queried and tabulated, as well as knowledge of OS and inducements and impediments to use.
Respondent (n = 211) demographics: mean age 55 years, 73 % male, 91 % diagnostic radiologists, 46 % in private practice. 68 % reported using AI in practice, while 52 % were only somewhat familiar with AI. 70 % viewed AI positively though only 46 % reported AI's overall accuracy met expectations. 57 % were unfamiliar with OS, with 52 % of those familiar having a positive opinion. Patient perceptions were the most commonly reported (25 %) inducement for OS use. Provider (44 %) and patient (40 %) costs were the most common impediments. Respondents reported that osteoporosis/osteopenia (81 %), fatty liver (78 %), and atherosclerotic cardiovascular disease risk (76 %) could be well assessed by OS. Most indicated OS output requires radiologist oversight/signoff and should be included in a separate “screening” section in the Radiology report. 28 % indicated willingness to spend 1–3 min reviewing AI-generated output while 18 % would not spend any time. Society guidelines/recommendations were most likely to impact OS implementation.
Radiologists' perspectives on AI and OS provide practical insights on AI implementation. Increasing end-user familiarity with AI-enabled applications and development of society guidelines/recommendations are likely essential prerequisites for Radiology AI adoption.
Large Language Models (LLM) like ChatGPT-4 hold significant promise in medical application, especially in the field of radiology. While previous studies have shown the promise of ChatGTP-4 in textual-based scenarios, its performance on image-based response remains suboptimal. This study investigates the impact of prompt engineering on ChatGPT-4's accuracy on the 2022 American College of Radiology In Training Test Questions for Diagnostic Radiology Residents that include textual and visual-based questions. Four personas were created, each with unique prompts, and evaluated using ChatGPT-4. Results indicate that encouraging prompts and those disclaiming responsibility led to higher overall accuracy (number of questions answered correctly) compared to other personas. Personas that threaten the LLM with legal action or mounting clinical responsibility were not only found to score less, but also refrain of answering questions at a higher rate. These findings highlight the importance of prompt context in optimizing LLM responses and the need for further research to integrate AI responsibly into medical practice.
To characterize brain MR imaging findings in a cohort of 58 patients with ECD and to evaluate relationship between these findings and the BRAFV600E pathogenic variant.
ECD patients of any gender and ethnicity, aged 2–80 years, with biopsy-confirmed ECD were eligible to enroll in this study. Two radiologists experienced in evaluating ECD CNS disease activity reviewed MRI studies. Any disagreements were resolved by a third reader. Frequencies of observed lesions were reported. The association between the distribution of CNS lesions and the BRAFV600Epathogenic variant was evaluated using Fisher's exact test and odd ratio.
The brain MRI of all 58 patients with ECD revealed some form of CNS lesions, most likely due to ECD. Cortical lesions were noted in 27/58 (46.6 %) patients, cerebellar lesions in 15/58 (25.9 %) patients, brain stem lesions in 17/58 cases (29.3 %), and pituitary lesions in 10/58 (17.2 %) patients. Premature cortical atrophy was observed in 8/58 (13.8 %) patients. BRAFV600E pathogenic variant was significantly associated with cerebellar lesions (p = 0.016) and bilateral brain stem lesions (p = 0.043). A trend toward significance was noted for cerebral atrophy (p = 0.053).
The study provides valuable insights into the brain MRI findings in ECD and their association with the BRAFV600E pathogenic variant, particularly its association in cases with bilateral lesions. We are expanding our understanding of how ECD affects cerebral structures. Knowledge of MRI CNS lesion patterns and their association with mutations such as the BRAF variant is helpful for both prognosis and clinical management.
Succinate dehydrogenase (SDH)-deficient renal cell carcinoma (RCC) is a newly defined, rare subtype of renal cancer, associated with pathogenic variations in the Succinate Dehydrogenase Subunit B (SDHB) gene. Our aim is to investigate the imaging findings of SDHB-associated renal tumors, utilizing cross-sectional and FDG-PET imaging in patients with pathogenic variations in SDHB gene, to facilitate accurate tumor characterization.
Twenty SDH-deficient tumors from 16 patients with pathogenic variations in SDHB gene were retrospectively evaluated using cross-sectional and FDG-PET imaging. Clinical findings such as demographics, family history, extra-renal findings and metastases were recorded. Tumor imaging characteristics on CT/MRI included were laterality, size, homogeneity, morphology, margins, internal content, T1/T2 signal intensity, enhancement features, and restricted diffusion.
Sixteen patients (median age 31 years, IQR 19–41, 8 males) were identified with 68.8 % of patients having a known family history of SDHB variation. 81.3 % of lesions were solitary and majority were solid (86.7 % on CT, 87.5 % on MRI) with well-defined margins in >62.5 % of lesions, without evidence of internal fat, calcifications, or vascular invasion. 100 % of lesions demonstrated restricted diffusion and avid enhancement, with degree >75 % for most lesions on CT and MRI. On FDG-PET, all renal masses showed increased radiotracer uptake. 43.8 % of patients demonstrated extra-renal manifestations and 43.8 % had distant metastasis.
SDHB-associated RCC is predominantly noted in young patients with no gender predilection. On imaging, SDH-deficient RCC are frequently unilateral, solitary, and solid with well-defined margins demonstrating avid enhancement with variability in enhancement pattern and showing restricted diffusion.
This study aimed to systematically assess the quality and performance of computed tomography (CT) radiomics studies in predicting brain metastasis (BM) among patients with lung cancer.
The PubMed, Embase and Web of Science were searched for studies predicting BM in patients with lung cancer using CT-based radiomics features. Information regarding patients, imaging, and radiomics analysis was extracted from eligible studies. We assessed the quality of included studies using the Radiomics Quality Scoring (RQS) tool and the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). A meta-analysis of studies regarding the prediction of BM in patients with lung cancer was performed.
Thirteen studies were identified, with sample sizes ranging from 75 to 602. The mean RQS of the studies was 12 (range 9–16), and the corresponding percentage of the score was 33.55 % (range 25.00–44.44 %). Four studies (30.8 %) were considered as low risk of bias, while the remaining nine studies (69.2 %) were considered to have unclear risks. The meta-analysis included twelve studies. The pooled sensitivity, specificity and Area Under the Curve (AUC) value with 95 % confidence intervals were 0.75 [0.69, 0.80], 0.76 [0.68, 0.82], and 0.81 [0.77–0.84], respectively.
CT radiomics-based models show promising results as a non-invasive method to predict BM in lung cancer patients. However, multicenter and prospective studies are warranted to enhance the stability and acceptance of radiomics.