Toward Precision Diagnosis: Machine Learning in Identifying Malignant Orbital Tumors With Multiparametric 3 T MRI.

BACKGROUND: Orbital tumors present a diagnostic challenge due to their varied locations and histopathological differences. Although recent advancements in imaging have improved diagnosis, classification remains a challenge. The integration of artificial intelligence in radiology and ophthalmology has demonstrated promising outcomes. PURPOSE: This study aimed to evaluate the performance of machine learning models in accurately distinguishing malignant orbital tumors from benign ones using multiparametric 3 T magnetic resonance imaging (MRI) data. MATERIALS AND METHODS: In this single-center prospective study, patients with orbital masses underwent presurgery 3 T MRI scans between December 2015 and May 2021. The MRI protocol comprised multiparametric imaging including dynamic contrast-enhanced (DCE), diffusion-weighted imaging (DWI), intravoxel incoherent motion (IVIM), as well as morphological imaging acquisitions. A repeated nested cross-validation strategy using random forest classifiers was used for model training and evaluation, considering 8 combinations of explanatory features. Shapley additive explanations (SHAP) values were used to assess feature contributions, and the model performance was evaluated using multiple metrics. RESULTS: One hundred thirteen patients were analyzed (57/113 [50.4%] were women; average age was 51.5 ± 17.5 years, range: 19-88 years). Among the 8 combinations of explanatory features assessed, the performance on predicting malignancy when using the most comprehensive model, which is the most exhaustive one incorporating all 46 explanatory features-including morphology, DWI, DCE, and IVIM, achieved an area under the curve of 0.9 [0.73-0.99]. When using the streamlined "10-feature signature" model, performance reached an area under the curve of 0.88 [0.71-0.99]. Random forest feature importance graphs measured by the mean of SHAP values pinpointed the 10 most impactful features, which comprised 3 quantitative IVIM features, 4 quantitative DCE features, 1 quantitative DWI feature, 1 qualitative DWI feature, and age. CONCLUSIONS: Our findings demonstrate that a machine learning approach, integrating multiparametric MRI data such as DCE, DWI, IVIM, and morphological imaging, offers high-performing models for differentiating malignant from benign orbital tumors. The streamlined 10-feature signature, with a performance close to the comprehensive model, may be more suitable for clinical application.

Diagnostic Performance of Dynamic Contrast-Enhanced 3T MR Imaging for Characterization of Orbital Lesions: Validation in a Large Prospective Study.

BACKGROUND AND PURPOSE: Orbital lesions are rare but serious. Their characterization remains challenging. Diagnosis is based on biopsy or surgery, which implies functional risks. It is necessary to develop noninvasive diagnostic tools. The goal of this study was to evaluate the diagnostic performance of dynamic contrast-enhanced MR imaging at 3T when distinguishing malignant from benign orbital tumors on a large prospective cohort. MATERIALS AND METHODS: This institutional review board-approved prospective single-center study enrolled participants presenting with an orbital lesion undergoing a 3T MR imaging before surgery from December 2015 to May 2021. Morphologic, diffusion-weighted, and dynamic contrast-enhanced MR images were assessed by 2 readers blinded to all data. Univariable and multivariable analyses were performed. To assess diagnostic performance, we used the following metrics: area under the curve, sensitivity, and specificity. Histologic analysis, obtained through biopsy or surgery, served as the criterion standard for determining the benign or malignant status of the tumor. RESULTS: One hundred thirty-one subjects (66/131 [50%] women and 65/131 [50%] men; mean age, 52 [SD, 17.1] years; range, 19-88 years) were enrolled. Ninety of 131 (69%) had a benign lesion, and 41/131 (31%) had a malignant lesion. Univariable analysis showed a higher median of transfer constant from blood plasma to the interstitial environment (K trans) and of transfer constant from the interstitial environment to the blood plasma (minute-1) (Kep) and a higher interquartile range of K trans in malignant-versus-benign lesions (1.1 minute-1 versus 0.65 minute-1, P = .03; 2.1 minute-1 versus 1.1 minute-1, P = .01; 0.81 minute-1 versus 0.65 minute-1, P = .009, respectively). The best-performing multivariable model in distinguishing malignant-versus-benign lesions included parameters from dynamic contrast-enhanced imaging, ADC, and morphology and reached an area under the curve of 0.81 (95% CI, 0.67-0.96), a sensitivity of 0.82 (95% CI, 0.55-1), and a specificity of 0.81 (95% CI, 0.65-0.96). CONCLUSIONS: Dynamic contrast-enhanced MR imaging at 3T appears valuable when characterizing orbital lesions and provides complementary information to morphologic imaging and DWI.

Long-term clinical and ultrasound follow-up after transient perivascular inflammation of the carotid artery (TIPIC) syndrome: a multicenter study.

BACKGROUND: The present study aimed to describe the clinical and ultrasound (US) long-term follow-up of patients with transient perivascular inflammation of the carotid artery (TIPIC) syndrome and the risk of recurrence. METHODS: We enrolled patients with a definitive diagnosis of TIPIC syndrome who were included in a retrospective multicenter study. These patients were recontacted at least six months after the first TIPIC episode for a clinical and imaging follow-up. Each patient underwent a clinical evaluation through a tailored questionnaire as well as US imaging. RESULTS: Twenty-eight patients were enrolled with a median follow-up of 58.7 months (interquartile range = 8-121). Nineteen out of the 28 patients (67.8%) had residual pain, eight (28.6%) had experienced a clinical recurrence and 12 (42.9%) had a thickening of the carotid wall on US. No patients had neurological complication or other associated diseases. CONCLUSIONS: Patients with TIPIC syndrome have often residual pain and recurrence in about one quarter of cases but the long-term follow-up is in favor a benign self-limited pathology.Trial registration: ClinicalTrials.gov (identifier NCT03804112).

Reproducibility and accuracy of vessel wall MRI in diagnosing giant cell arteritis: a study with readers of varying expertise.

OBJECTIVE: To evaluate the reproducibility of vessel wall magnetic resonance imaging (VW-MRI) in diagnosing giant cell arteritis (GCA) among groups of radiologists with varying levels of expertise. METHODS: This institutional review board-approved retrospective single-center study recruited patients with suspected GCA between December 2014 and September 2021. Patients underwent 3 -T VW-MRI before temporal artery biopsy. Ten radiologists with varying levels of expertise, blinded to all data, evaluated several intracranial and extracranial arteries to assess GCA diagnosis. Interobserver reproducibility and diagnostic performance were evaluated. RESULTS: Fifty patients (27 women and 23 men) with a mean age of 75.9 ± 9 years were included. Thirty-one of 50 (62%) had a final diagnosis of GCA.VW-MRI had an almost perfect reproducibility among expert readers (kappa = 0.93; 95% CI 0.77-1) and substantial reproducibility among all readers, junior and non-expert senior readers (kappa = 0.7; 95% CI 0.66-0.73; kappa = 0.67 95% CI 0.59-0.74; kappa = 0.65; 95% CI 0.43-0.88 respectively) when diagnosing GCA. Substantial interobserver agreement was observed for the frontal branch of superficial temporal artery. Moderate interobserver agreement was observed for the superficial temporal artery and its parietal branch, as well as ophthalmic arteries in all groups of readers. Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy varied depending on the group of readers. CONCLUSION: VW-MRI is a reproducible and accurate imaging modality for detecting GCA, even among less-experienced readers. This study advocates for the use of VW-MRI when diagnosing GCA even in less-experienced centers. CLINICAL RELEVANCE STATEMENT: VW-MRI is a reproducible and accurate imaging modality for detecting GCA, even among less-experienced readers, and it could be used as a first-line diagnostic tool for GCA in centers with limited expertise in GCA diagnosis. KEY POINTS: • Vessel wall magnetic resonance imaging (VW-MRI) is a reproducible and accurate imaging modality for detecting giant cell arteritis (GCA) in both extracranial and intracranial arteries. • The reproducibility of vessel wall magnetic resonance imaging for giant cell arteritis diagnosis was high among expert readers and moderate among less-experienced readers. • The use of vessel wall magnetic resonance imaging for giant cell arteritis diagnosis can be recommended even in centers with less-experienced readers.

Characteristics and Prognosis of Binocular Diplopia in Patients With Giant Cell Arteritis.

BACKGROUND: Giant cell arteritis (GCA) is a large vessel vasculitis associated with a risk of permanent ophthalmologic complications. Data about diplopia prognosis in GCA are scarce. This study was designed to better characterize diplopia in newly diagnosed GCA patients. METHODS: All consecutive patients diagnosed with GCA from January 2015 to April 2021 in a French tertiary ophthalmologic center were retrospectively reviewed. GCA diagnosis relied on a positive temporal artery biopsy or high-definition MRI. RESULTS: Among 111 patients diagnosed with GCA, 30 patients (27%) had diplopia. Characteristics of patients with diplopia were similar to other GCA patients. Diplopia resolved spontaneously in 6 patients (20%). Diplopia was attributed to cranial nerve palsy in 21/24 patients (88%), especially third (46%) and sixth cranial nerve (42%). Ocular ischemic lesions occurred in 11 of the 30 patients with diplopia (37%); 2 patients developed vision loss after initiation of corticosteroids. In the remaining 13 patients, diplopia resolved after treatment onset in 12 patients (92%) with a median delay of 10 days. Patients treated intravenously tended to have a quicker improvement than those treated orally, but with a similar resolution rate of diplopia at 1 month. Two patients had relapse of diplopia at 4 and 6 weeks after an initial treatment course of 24 and 18 months, respectively. CONCLUSIONS: Diplopia is a rare feature at GCA diagnosis, but should raise clinician suspicion for GCA when associated with cephalic symptoms and prompt the initiation of corticosteroids to prevent ocular ischemic complications.

High diagnostic accuracy of T2FLAIR at 3 T in the detection of optic nerve head edema in acute optic neuritis.

OBJECTIVES: Optic nerve head edema (ONHE) detected by fundoscopy is observed in one-third of patients presenting optic neuritis (ON). While ONHE is an important semiological feature, the correlation between ONHE and optic nerve head MRI abnormalities (ONHMA), sometimes called "optic nerve head swelling," remains unknown. Our study aimed to assess the diagnostic accuracy of T2 fluid-attenuated inversion recovery (FLAIR) MRI sequence in detecting ONHE in patients with acute ON. METHODS: In the present single-center study, data were extracted from two prospective cohort studies that consecutively included adults with a first episode of acute ON treated between 2015 and 2020. Two experienced readers blinded to study data independently analyzed imaging. A senior neuroradiologist resolved any discrepancies. The primary judgment criterion of ONHMA was assessed as optic nerve head high signal intensity on gadolinium-enhanced T2FLAIR MRI sequence. Its diagnostic accuracy was evaluated with both the gold standard of ONHE on fundus photography (FP) and peripapillary retinal nerve fiber layer thickening on optic coherence tomography (OCT). RESULTS: A total of 102 patients were included, providing 110 affected and 94 unaffected optic nerves. Agreement was high between the different modalities: 92% between MRI and FP (k = 0.77, 95% CI: 0.67-0.88) and 93% between MRI and OCT (k = 0.77, 95% CI: 0.67-0.87). MRI sensitivity was 0.84 (95% CI: 0.70-0.93) and specificity was 0.94 (95% CI: 0.89-0.97) when compared with the FP. CONCLUSION: Optic nerve head high T2FLAIR signal intensity corresponds indeed to the optic nerve head edema diagnosed by the ophthalmologists. MRI is a sensitive tool for detecting ONHE in patients presenting acute ON. CLINICAL RELEVANCE STATEMENT: In patients with optic neuritis the high T2FLAIR (fluid-attenuated inversion recovery) signal intensity of the optic nerve head corresponds indeed to optic nerve head edema, which is a useful feature in optic neuritis etiological evaluation and treatment. KEY POINTS: Optic nerve head edema is a prominent clinical feature of acute optic neuritis and is usually diagnosed during dilated or non-dilated eye fundus examination. Agreement was high between magnetic resonance imaging, fundus photography, and optical coherence tomography. Optic nerve head high T2 fluid attenuation inversion recovery signal intensity is a promising detection tool for optic nerve head edema in patients presenting acute optic neuritis.

Co-registration with subtraction and color-coding or fusion improves the detection of new and growing lesions on follow-up MRI examination of patients with multiple sclerosis.

PURPOSE: The purpose of this study was to compare the performance of three magnetic resonance imaging (MRI) reading methods in the follow-up of patients with multiple sclerosis (MS). MATERIALS AND METHODS: This retrospective study included patients with MS who underwent two brain follow-up MRI examinations with three-dimensional fluid-attenuated inversion recovery (FLAIR) sequences between September 2016 and December 2019. Two neuroradiology residents independently reviewed FLAIR images using three post-processing methods including conventional reading (CR), co-registration fusion (CF), and co-registration subtraction with color-coding (CS), while being blinded to all data but FLAIR images. The presence and number of new, growing, or shrinking lesions were compared between reading methods. The reading time, reading confidence, and inter- and intra-observer agreements were also assessed. An expert neuroradiologist established the standard of reference. Statistical analyses were corrected for multiple testing. RESULTS: A total of 198 patients with MS were included. There were 130 women and 68 men, with a mean age of 41 ± 12 (standard deviation) years (age range: 21-79 years). Using CS and CF, more patients were detected with new lesions compared to CR (93/198 [47%] and 79/198 [40%] vs. 54/198 [27%], respectively; P < 0.01). The median number of new hyperintense FLAIR lesions detected was significantly greater using CS and CF compared to CR (2 [Q1, Q3: 0, 6] and 1 [Q1, Q3: 0, 3] vs. 0 [Q1, Q3: 0, 1], respectively; P < 0.001). The mean reading time was significantly shorter using CS and CF compared to CR (P < 0.001), with higher confidence in readings and higher inter- and intra-observer agreements. CONCLUSION: Post-processing tools such as CS and CF substantially improve the accuracy of follow-up MRI examinations in patients with MS while reducing reading time and increasing readers' confidence and reproducibility.

Acute optic neuritis: What are the clues to the aetiological diagnosis in real life?

BACKGROUND: Previous cross-sectional studies have reported distinct clinical and radiological features among the different acute optic neuritis (ON) aetiologies. Nevertheless, these reports often included the same number of patients in each group, not taking into account the disparity in frequencies of ON aetiologies in a real-life setting and thus, it remains unclear what are the truly useful features for distinguishing the different ON causes. To determine whether clinical evaluation, ophthalmological assessment including the optical coherence tomography (OCT), CSF analysis, and MRI imaging may help to discriminate the different causes of acute ON in a real-life cohort. METHODS: In this prospective monocentric study, adult patients with recent acute ON (<1 month) underwent evaluation at baseline and 1 and 12 months, including, high- and low-contrast visual acuity, visual field assessment and OCT measurements, baseline CSF analysis and MRI. RESULTS: Among 108 patients, 71 (65.7%) had multiple sclerosis (MS), 19 (17.6%) had idiopathic ON, 13 (12.0%) and 5 (4.6%) had myelin oligodendrocyte glycoprotein and aquaporin-4 antibodies, at last follow up respectively.At baseline, the distribution of bilateral ON, CSF-restricted oligoclonal bands, optic perineuritis, optic nerve length lesions and positive dissemination in space and dissemination in time criteria on MRI were significantly different between the four groups (p <0.001). No significant difference in visual acuity nor inner retinal layer thickness was found between the different ON aetiologies. CONCLUSIONS: In this large prospective study, bilateral visual involvement, CSF and MRI results are the most useful clues in distinguishing the different aetiologies of acute ON, whereas ophthalmological assessments including OCT measurements revealed no significant difference between the aetiologies.

Relevance of kappa free light chains index in patients with aquaporin-4 or myelin-oligodendrocyte-glycoprotein antibodies.

BACKGROUND: The kappa free light chains index (κ-index) is increasing in importance as a fast, easy, cost-effective, and quantitative biomarker in multiple sclerosis (MS), which can replace cerebrospinal fluid (CSF)-restricted oligoclonal bands (OCB) detection. In previous studies, controls often included mixed patients with several inflammatory central nervous system disorders. The aim of the present study was to assess the κ-index in patients with serum aquaporin-4 (AQP4)-IgG or myelin-oligodendrocyte-glycoprotein (MOG)-IgG. METHODS: We analyzed CSF/serum samples of patients with AQP4-IgG or MOG-Ig and evaluated distinct κ-index cut-offs. We described clinical and magnetic resonance imaging (MRI) features of patients with the highest κ-index values. RESULTS: In 11 patients with AQP4-IgG, median κ-index was 16.8 (range 0.2; 63) and 6/11 (54.5%) had κ-index >12. Among 42 patients with MOG-IgG, 2 had low positive MOG-IgG titers, were ultimately diagnosed with MS, and had a markedly increased κ-index (54.1 and 102.5 respectively). For the remaining 40 MOG-IgG-positive patients the median κ-index was 0.3 (range 0.1; 15.5). Some 6/40 (15%) and 1/40 (2.5%) patients had a κ-index >6 and >12, respectively. None fulfilled MRI dissemination in space and dissemination in time (DIS/DIT) criteria and the final diagnosis was MOG-IgG-associated disease (MOGAD) for these 40 patients. Four of the 40 (10%) MOG-IgG-positive patients had OCB. CONCLUSION: While a marked increase in κ-index could discriminate MS from MOGAD, a low κ-index threshold could lead to confusion between MS and MOGAD or AQP4 antibody-positive neuromyelitis optica spectrum disorder.

Natalizumab extended-interval dosing in a real-life setting.

BACKGROUND: Natalizumab is a high-efficacy therapy for recurrent multiple sclerosis (RMS) with a four-week administration interval. Controlled trials have shown that extending this interval to six weeks led to better safety without increasing the risk of relapse. We aimed to analyze the safety of extending the natalizumab interdose interval from 4 to 6 weeks in a real-life setting. METHODS: This monocentric retrospective self-controlled study included adult patients with RMS treated with natalizumab with a four-week interval between infusions for a minimum of six months, before switching to a six-week interval. The main outcomes were the incidence of MS relapse, new MRI lesions, and MRI activity signs during the two periods, with patients being their own controls. RESULTS: Fifty-seven patients were included in the analysis. The mean (95%CI) annualized relapse rate (AAR) before natalizumab introduction was 1.03 (0.52; 1.55). During the four-week interval dosing period, no patient presented with an MS relapse, and seven (13.5%) patients had new MRI lesions. During the six-week interval dosing period, no relapse was observed and two (3.6%) patients had new MRI lesions. CONCLUSION: We did not observe more relapses or signs of MRI activity when extending the interval between natalizumab infusions from four to six weeks.

Management and Outcomes of Posterior Persistent Fetal Vasculature.

PURPOSE: To describe clinical features, management, and outcomes of posterior persistent fetal vasculature (PFV) and suggest a management algorithm. DESIGN: Retrospective, consecutive case series. PARTICIPANTS: All children diagnosed with posterior PFV and treated or followed at the Rothschild Foundation Hospital in France between June 2011 and September 2021. METHODS: Retrospective analysis of the clinical characteristics of posterior PFV. We reported age, gender, presenting symptoms, intraocular pressure, and visual acuity (VA) at diagnosis. Patients were divided into 4 groups depending on the severity and involvement or not of anterior segment. We reported the vitreoretinal surgical techniques used. MAIN OUTCOME MEASURES: Anatomic results, ocular hypertension, best-corrected distance visual acuity (BCDVA), presence of postoperative adverse events, and additional surgical interventions were recorded at each follow-up visit. RESULTS: Ninety-six patients were included. The median age at diagnosis was 8 months (IQR = 12), mean 18.9 ± 30.9 months) with a mean follow-up of 27 ± 31.2 months. Although PFV is often an isolated disease, it was associated with a systemic disease in 8% of cases. There was anterior involvement in 62 (64%) of eyes. Forty-one eyes (42.7%) were microphthalmic and more frequently associated with severe PFV (53% vs. 25%; P = 0.01). Surgery was performed in 85 patients (89%). Of them, 69 (81%) had a total success, 5 (6%) had a partial success due to persistent limited peripheral retinal detachment (RD), and 11 (13%) had a failure due to persistent total RD after surgery. Postoperative adverse events occured in 38 eyes including ocular hypertension requiring eye drop medication (7.1%), secondary cell proliferation around the intraocular lens (8.2%), intravitreal hemorrhages (7.1%), and persistent tractional RD (10.6%). Second surgery was performed in 18 patients (21%). At last follow-up, VA could be measured in logarithm of the minimum angle of resolution in 43 children (45%), light perception in 21 eyes (22%), and no light perception or impossible to assess in 32 eyes (33%). CONCLUSIONS: In our case series, most patients presenting with posterior PFV received complex vitreoretinal surgery. Goals of the surgery vary and include retinal flattening, reduction of vitreoretinal traction, freeing of visual axis, and aesthetic concerns. We propose a surgical and medical management algorithm for PFV. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references.

"National survey for preliminary evaluation of neuroradiological protocols in patients with infective endocarditis".

OBJECTIVES: The aim of this study was to identify imaging protocols in patients with infective endocarditis through a nationwide survey. METHODS: An electronic evolutionary survey was sent to interventional Neuroradiologists among neuroradiological centers, under the aegis of the Société Française de Neuroradiologie. Among 33 contacted centers, 25 completed the survey (21 universitary hospitals and 4 peripheric hospitals). RESULTS: Most of the centers (88%) used systematic imaging screening in IE patients. MRI was the first imaging method used in 66% of cases, while CT was used in 44%. When no IIA was detectable in CT-scan screening, 6 (54,54%) stopped investigations, while 9 (81,81%) continued with MRI exploration in case of hemorrhage, ischemia or enhancement. Sulcal hemorrhage on MRI was an indication of complementary DSA in 25 centers (100%). Regarding IIA characterization, 12 centers (48%) used systematic DSA, whereas for 10 centers (40%), DSA was conditioned by hemorrhage or patient status. CONCLUSION: We highlighted large variations in Neuroimaging exploration and follow-up of IE patients in real-world practices. Expert guidelines able to standardize practices are warranted to improve the management of this serious and often misdiagnosed pathology.

Revolutionizing radiology with GPT-based models: Current applications, future possibilities and limitations of ChatGPT.

Artificial intelligence has demonstrated utility and is increasingly being used in the field of radiology. The use of generative pre-trained transformer (GPT)-based models has the potential to revolutionize the field of radiology, offering new possibilities for improving accuracy, efficiency, and patient outcome. Current applications of GPT-based models in radiology include report generation, educational support, clinical decision support, patient communication, and data analysis. As these models continue to advance and improve, it is likely that more innovative uses for GPT-based models in the field of radiology at large will be developed, further enhancing the role of technology in the diagnostic process. ChatGPT is a variant of GPT that is specifically fine-tuned for conversational language understanding and generation. This article reports some answers provided by ChatGPT to various questions that radiologists may have regarding ChatGPT and identifies the potential benefits ChatGPT may offer in their daily practice but also current limitations. Similar to other applications of artificial intelligence in the field of imaging, further formal validation of ChatGPT is required.

Contrast-Enhanced 3D Spin Echo T1-Weighted Sequence Outperforms 3D Gradient Echo T1-Weighted Sequence for the Detection of Multiple Sclerosis Lesions on 3.0 T Brain MRI.

BACKGROUND: Using reliable contrast-enhanced T1 sequences is crucial to detect enhancing brain lesions for multiple sclerosis (MS) at the time of diagnosis and over follow-up. Contrast-enhanced 3D gradient-recalled echo (GRE) T1-weighted imaging (WI) and 3D turbo spin echo (TSE) T1-WI are both available for clinical practice and have never been compared within the context of this diagnosis. PURPOSE: The aim of this study was to compare contrast-enhanced 3D GRE T1-WI and 3D TSE T1-WI for the detection of enhancing lesions in the brains of MS patients. METHODS: This single-center prospective study enrolled patients with MS who underwent a 3.0 T brain MRI from August 2017 to April 2021 for follow-up. Contrast-enhanced 3D GRE T1-WI and 3D TSE T1-WI were acquired in randomized order. Two independent radiologists blinded to all data reported all contrast-enhanced lesions in each sequence. Their readings were compared with a reference standard established by a third expert neuroradiologist. Interobserver agreement, contrast ratio, and contrast-to-noise ratio were calculated for both sequences. RESULTS: A total of 158 MS patients were included (mean age, 40 ± 11 years; 95 women). Significantly more patients had at least 1 contrast-enhanced lesion on 3D TSE T1-WI than on 3D GRE T1-WI for both readers (61/158 [38.6%] vs 48/158 [30.4%] and 60/158 [38.6%] vs 47/158 [29.7%], P < 0.001). Significantly more contrast-enhanced lesions per patient were detected on 3D TSE T1-WI (mean 2.47 vs 1.56 and 2.56 vs 1.39, respectively, P < 0.001). Interobserver agreement was excellent for both sequences, κ = 0.96 (confidence interval [CI], 0.91-1.00) for 3D TSE T1-WI and 0.92 (CI, 0.86-0.99) for 3D GRE T1-WI. Contrast ratio and contrast-to-noise ratio were significantly higher on 3D TSE T1-WI (0.84 vs 0.53, P < 0.001, and 87.9 vs 57.8, P = 0.03, respectively). CONCLUSIONS: At 3.0 T, contrast-enhanced 3D TSE-T1-WI supports the detection of significantly more enhancing lesions than 3D GRE T1-WI and should therefore be used for MS patients requiring contrast-enhanced examination.

MRI spot sign in acute intracerebral hemorrhage: an independent biomarker of hematoma expansion and poor functional outcome.

BACKGROUND: In acute intracerebral hemorrhage (ICH), the prognostic value of the MRI spot sign on hematoma expansion (HE) and poor functional outcome is poorly known. METHODS: We retrospectively included patients admitted over a 4-year period for an acute ICH in a single institution using MRI as the first-line imaging tool. The presence and number of MRI spot signs on contrast-enhanced T1-weighted imaging was evaluated by one neuroradiologist, blinded from outcomes. The primary outcome was HE, defined as > 6 mL or > 33% ICH volume growth from initial MRI to 24-48 h follow-up imaging; the secondary outcome was poor 3-month modified Rankin score (4-6). RESULTS: Overall, 147 patients were included, and 62% had a spot sign. Among the 130 patients with follow-up imaging, 24% experienced HE. HE occurred in 6%, 21% and 43% patients with 0, 1 and ≥ 2 spots, respectively (P < 0.001). The MRI spot sign was independently associated with HE (adjusted OR 6.15 [95% CI 1.60-23.65]; P = 0.008), with a dose-dependent effect. The negative and positive predictive values of the spot sign for HE were 0.94 and 0.35, respectively. Poor functional outcome occurred in 27%, 32% and 71% patients with 0, 1 and ≥ 2 spots, respectively (P < 0.001). In multivariable analysis, the presence of ≥ 2 spots was independently associated with poor functional outcome (adjusted OR 3.67 [95% CI 1.21-11.10]; P = 0.024). CONCLUSION: The MRI spot sign is an independent biomarker of HE, and the presence of ≥ 2 spots is independently associated with poor 3-month outcome. The lack of spot sign is highly predictive of a favorable evolution.

A signature of structural MRI features at 3 Tesla allows an accurate characterization of orbital cavernous venous malformation.

OBJECTIVES: To differentiate OCVM from other orbital lesions using structural MRI. METHODS: This IRB-approved a historical-prospective cohort single-center analysis of a prospective cohort that included consecutive adult patients presenting with an orbital lesion undergoing a 3T MRI before surgery from December 2015 to May 2021. Two readers blinded to all data read all MRIs assessing structural MRI characteristics. A univariate analysis followed by a stepwise multivariate analysis identified structural MRI features showing the highest sensitivity and specificity when diagnosing OCVM. RESULTS: One hundred ninety-one patients with 30/191 (16%) OCVM and 161/191 (84%) other orbital lesions were included. OCVM were significantly more likely to present with a higher signal intensity than that of the cortex on T2WI: 26/29 (89.7%) versus 28/160 (17.5%), p < 0.001, or with a chemical shift artifact (CSA): 26/29 (89.7%) versus 16/155 (10.3%), p < 0.001, or to present with a single starting point of enhancement, as compared to other orbital lesions: 18/29 (62.1%) versus 4/159 (2.5%), p = 0.001. The step-wise analysis identified 2 signatures increasing performances. Signature 1 combined a higher signal intensity than that of the cortex on T2WI and a CSA. Signature 2 included these two features and the presence of a single starting point of enhancement. Sensitivity, specificity, and accuracy were 0.83, 0.94, and 0.92 for signature 1 and 0.97, 0.93, and 0.93 for signature 2, respectively. CONCLUSION: Structural MRI yields high sensitivity and specificity when diagnosing OCVM. KEY POINTS: • Structural MRI shows high sensitivity and specificity when diagnosing orbital cavernous venous malformation. • We identified two signatures combining structural MRI features which might be used easily in routine clinical practice. • The combination of higher signal intensity of the lesion as compared to the cortex on T2WI and of a chemical shift artifact yields a sensitivity and specificity of 0.83 and 0.94 for the diagnosis of orbital cavernous venous malformation, respectively.

Artificial intelligence in diagnostic and interventional radiology: Where are we now?

The emergence of massively parallel yet affordable computing devices has been a game changer for research in the field of artificial intelligence (AI). In addition, dramatic investment from the web giants has fostered the development of a high-quality software stack. Going forward, the combination of faster computers with dedicated software libraries and the widespread availability of data has opened the door to more flexibility in the design of AI models. Radiomics is a process used to discover new imaging biomarkers that has multiple applications in radiology and can be used in conjunction with AI. AI can be used throughout the various processes of diagnostic imaging, including data acquisition, reconstruction, analysis and reporting. Today, the concept of "AI-augmented" radiologists is preferred to the theory of the replacement of radiologists by AI in many indications. Current evidence bolsters the assumption that AI-assisted radiologists work better and faster. Interventional radiology becomes a data-rich specialty where the entire procedure is fully recorded in a standardized DICOM format and accessible via standard picture archiving and communication systems. No other interventional specialty can bolster such readiness. In this setting, interventional radiology could lead the development of AI-powered applications in the broader interventional community. This article provides an update on the current status of radiomics and AI research, analyzes upcoming challenges and also discusses the main applications in AI in interventional radiology to help radiologists better understand and criticize articles reporting AI in medical imaging.

Imaging of Cerebral Venous Thrombosis.

Cerebral venous thrombosis is a rare cause of stroke. Imaging is essential for diagnosis. Although digital subtraction angiography is still considered by many to be the gold standard, it no longer plays a significant role in the diagnosis of cerebral venous thrombosis. MRI, which allows for imaging the parenchyma, vessels and clots, and CT are the reference techniques. CT is useful in case of contraindication to MRI. After presenting the radio-anatomy for MRI, we present the different MRI and CT acquisitions, their pitfalls and their limitations in the diagnosis of cerebral venous thrombosis.

Preservation of frontal white matter tracts in ventricular surgery: favoring an anterior interhemispheric transcallosal approach vs a transcortical transfrontal transventricular approach.

Secondary to the creation of a surgical corridor and retraction, white matter tracts degenerate, causing long-term scarring with potential neurological consequences. Third and lateral ventricle tumors require surgery that may lead to cognitive impairment. Our objective is to compare the long-term consequences of a transcortical transfrontal approach and an interhemispheric transcallosal approach on corpus callosum and frontal white matter tracts degeneration. Surgical patients with ventricular tumor accessible through both approaches were included and clinico-radiological data were retrospectively analyzed. The primary endpoint was the callosotomy length at 3-month post-operative T1 MRI, corrected by the extension of the tumor and the use of neuronavigation. Secondary outcomes included perioperative criteria such as bleeding, use of retractors and duration, FLAIR hypersignal on 3-month MRI, and re-do surgeries. To assess white matter tract interruption, 3-month FLAIR hypersignal was superposed to a tractography atlas. Seventy patients were included, 57 (81%) in the transfrontal group and 13 (19%) in the interhemispheric group. There was no difference in the mean callosotomy length on 3-month MRI (12.3 mm ± 5.60 transfrontal vs 11.7 mm ± 3.92 interhemispheric, p = 0.79) on univariate and multivariate analyses. The callosotomy length was inferior by - 3.13 mm for tumors located exclusively in the third ventricle (p = 0.016), independent of the approach. Retractors were used more often in transfrontal approaches (60% vs 33%, p < 0.001). The extent of frontal FLAIR hypersignal was higher after transfrontal approach (14.1 mm vs 0.525 mm, p < 0.001), correlated to the use of retractors (p < 0.05). After the interhemispheric approach, no tract other than corpus callosum was interrupted, whereas, after the transfrontal approach, frontal arcuate fibers and projections from the thalamus were interrupted in all patients, the cingulum in 19 (33%), the superior fronto-occipital fasciculus in 15 (26%), and the superior longitudinal fasciculus in 2 (3%). Transfrontal and interhemispheric approaches to the third and lateral ventricles both lead to the same long-term damage to the corpus callosum, but the transfrontal approach interrupts several white matter tracts essential to cognitive tasks such as attention and planning, even in the non-dominant hemisphere. These results encourage all neurosurgeons to be familiar with both approaches and favor the interhemispheric approach when both can give access to the tumor with a comparable risk. Neuropsychological studies are necessary to correlate these anatomical findings to cognitive outcomes.