Magnetic Resonance Features Research Articles

CMR characterisation of patients with heart failure and left bundle branch block

Abstract Introduction Cardiac magnetic resonance (CMR) is recommended internationally for tissue characterisation, volumetric assessment and assessment of prior myocardial infarction (1). Patients with left bundle branch block (LBBB) form a significant sub-group of individuals, however, there is limited data available to accurate determine whether LBBB is associated with any CMR-definable phenotypes. Aim We aimed to identify the distinctive cardiac magnetic resonance (CMR) features of patients with left bundle branch block (LBBB) and heart failure with reduced ejection fraction (HFrEF) of presumed non-ischaemic aetiology. Methods Participants from the MATCH (MyocArdial Tissue CHaracteristics in patients with heart failure according to glycaemic status) registry were prospectively enrolled. Exclusion criteria included: LVEF >40% at initial evaluation, established diagnosis of coronary artery disease, known presence of structural heart disease, suspected myocarditis, congenital heart disease and significantly impaired renal function. Following identification of HF, guideline-directed medical therapy was initiated based on the decision of the treating physician. LV recovery was defined as achieving ≥10% absolute improvement to a level of 40% or greater of LVEF from baseline evaluation upon the date of CMR quantification. Electrocardiograms were analysed to establish the presence or absence of LBBB. Results A total of 391 patients were recruited including 115 (29.4%) presenting with LBBB. Compared to controls, LBBB patients exhibited larger left ventricles and smaller right ventricles, but no differences were observed with respect to LVEF (35.8±12 vs. 38± 12 %, p=0.105) or right ventricular ejection fraction (RVEF). The prevalence of ischaemic scar (18.3% vs 21%, p=0.54), non-ischaemic fibrosis (25.2% vs 32.6%, p=0.15) and inducible ischaemia (6.1% vs. 7.6%, p=0.6) was comparable in patients with LBBB and those without. The overall rate of LV recovery was not significantly different between LBBB and non-LBBB patients (27.8% vs. 33%, p=0.32) from their baseline evaluation to the time of CMR assessment (70 [42 - 128] days). In the multivariate logistic regression, reduced LVEF remained an independent predictor of LV non-recovery in patients with LBBB, even after adjusting for gender and QRS duration (OR 0.93, 95%CI 0.87 – 0.99, p=0.03). In contrast, this association was not observed among patients without LBBB, whereas ischaemic scar was the primary predictor of LV non-recovery (OR 4.31, 95%CI 1.85 – 10.04, p=0.0007). Conclusion In this study patients presenting with a combination of HFrEF and LBBB had a larger LV cavity and smaller RV cavity than those without LBBB. However, there were no differences in the prevalence of ischaemic scar, non-ischaemic scar of inducible ischaemia according to the presence of absence of LBBB. Rates of LV recovery were similar between LBBB and non-LBBB patients.Clinical CMR ParametersSegmental Distributions

Predictive Model Based on Texture Analysis of Noncontrast Cardiac Magnetic Resonance Images for the Prognostic Evaluation of Cardiac Amyloidosis.

We aimed to develop a predictive model based on textural features of noncontrast cardiac magnetic resonance (CMR) imaging for risk stratification toward adverse events in patients with cardiac amyloidosis (CA). A cohort of 78 patients with CA was grouped into training (n = 54) and validation (n = 24) sets at a ratio of 7:3. A total of 275 textural features were extracted from the CMR images. MaZda and a support vector machine (SVM) were used for feature selection and model construction. An SVM model incorporating radiological and textural features was built to predict endpoint events by evaluating the area under the curve. In the entire cohort, 52 patients experienced major adverse cardiovascular events and 26 patients did not. By combining 2 radiological features and 8 texture features, extracted from cine and T2-weighted imaging images, the SVM model achieved area under the curves of the receiver operating characteristic and precision-recall curves of 0.930 and 0.962 in the training cohort and that of 0.867 and 0.941 in the validated cohort, respectively. The Kaplan-Meier curve of this SVM model criterion significantly stratified the CA outcomes (log-rank test, P < 0.0001). The SVM model based on radiological and textural features derived from noncontrast CMR images can be a reliable biomarker for adverse events prognostication in patients with CA.

Diabetic Charcot neuroarthropathy: A threat to both limb and life.

Diabetic Charcot neuroarthropathy (DCN), first described in 1936, occurs in less than 1% of diabetic patients, but in those diabetic subjects with distal symmetrical polyneuropathy, the overall incidence increases to 30% and the risk is even greater in those with type 1 diabetes. Factors that precipitate DCN are trauma, ischaemia due to arterio-venous shunting, increased osteoclastic activity and inflammation. DCN usually presents with a painless swollen foot and/or ankle which is 'hot to the touch'. These clinical findings are soon followed by characteristic magnetic resonance imaging (MRI) abnormalities and later X-ray changes. The joints that are most typically involved in chronological order are the tarsometatarsals followed by the naviculocuniform, sub-tarsal, talonavicular and metatarsal and tarsophalangeal. The cornerstone of therapy is prolonged (3-12 months) offloading with immobilization. Bisphosphonates may possibly accelerate recovery, whereas other unproven possible therapies include rhPTH, 1-34, calcitonin and methylprednisolone, which are not only ineffective but in some cases may also prolong the time to healing. Denosumab is potentially an efficacious, if unproven, therapy to accelerate healing. The risk of amputation is high and increases in the presence of a foot ulcer. DCN is associated with manifestations of autonomic neuropathy, including cardiac denervation, so that the risks of a cardiac event and heart failure are increased with DCN. Mortality is also increased with DCN, especially in the presence of a foot ulcer. To avoid the recurrence of DCN and especially to lower the risk of the recurrence of a foot ulcer recurrence reconstructive, surgery may be needed.

Prediction of high-risk prostate cancer based on the habitat features of biparametric magnetic resonance and the omics features of contrast-enhanced ultrasound

Rationale and objectivesTo predict high-risk prostate cancer (PCa) by combining the habitat features of biparametric magnetic resonance imaging (bp-MRI) with the omics features of contrast-enhanced ultrasound (CEUS). Materials and methodsThis study retrospectively collected patients with PCa confirmed by histopathology from January 2020 to June 2023. All patients underwent bp-MRI and CEUS of the prostate, followed by a targeted and transrectal systematic prostate biopsy. The cases were divided into the intermediate-low-risk group (Gleason score ≤7, n = 59) and high-risk group (Gleason score ≥8, n = 33). Radiomics prediction models, namely, MRI_habitat, CEUS_intra, and MRI-CEUS models, were developed based on the habitat features of bp-MRI, the omics features of CEUS, and a merge of features of the two, respectively. Predicted probabilities, called radscores, were then obtained. Clinical-radiological indicators were screened to construct clinic models, which generated clinic scores. The omics–clinic model was constructed by combining the radscore of MRI-CEUS and the clinic score. The predictive performance of all the models was evaluated using the receiver operating characteristic curve. ResultsThe area under the curve (AUC) values of the MRI-CEUS model were 0.875 and 0.842 in the training set and test set, respectively, which were higher than those of the MR_habitat (training set: 0.846, test set: 0.813), CEUS_intra (training set: 0.801, test set: 0.743), and clinic models (training set: 0.722, test set: 0.611). The omics–clinic model achieved a higher AUC (train set: 0.986, test set: 0.898). ConclusionsThe combination of the habitat features of bp-MRI and the omics features of CEUS can help predict high-risk PCa.

Erythrocyte nano-ghosts with dual optical and magnetic resonance characteristics.

Fluorescent organic dyes provide imaging capabilities at cellular and sub-cellular levels. However, a common problem associated with some of the existing dyes such as the US FDA-approved indocyanine green (ICG) is their weak fluorescence emission. Alternative dyes with greater emission characteristics would be useful in various imaging applications. Complementing optical imaging, magnetic resonance (MR) imaging enables deep tissue imaging. Nano-sized delivery systems containing dyes with greater fluorescence emission as well as MR contrast agents present a promising dual-mode platform with high optical sensitivity and deep tissue imaging for image-guided surgical applications. We have engineered a nano-sized platform, derived from erythrocyte ghosts (EGs), with dual near-infrared fluorescence and MR characteristics by co-encapsulation of a brominated carbocyanine dye and gadobenate dimeglumine (Gd-BOPTA). We have investigated the use of three brominated carbocyanine dyes (referred to as BrCy106, BrCy111, and BrCy112) with various degrees of bromination, structural symmetry, and acidic modifications for encapsulation by nano-sized EGs (nEGs) and compared their resulting optical characteristics with nEGs containing ICG. We find that asymmetric dyes (BrCy106 and BrCy112) with one dibromobenzene ring offer greater fluorescence emission characteristics. For example, the relative fluorescence quantum yield ( ) for nEGs fabricated using of BrCy112 is -fold higher than nEGs fabricated using the same concentrations of ICG. The dual-mode nEGs containing BrCy112 and Gd-BOPTA show a nearly twofold increase in their as compared with their single optical mode counterpart. Cytotoxicity is not observed upon incubation of SKOV3 cells with nEGs containing BrCy112. Erythrocyte nano-ghosts with dual optical and MR characteristics may ultimately prove useful in various biomedical imaging applications such as image-guided tumor surgery where MR imaging can be used for tumor staging and mapping, and fluorescence imaging can help visualize small tumor nodules for resection.

A Characteristic Magnetic Resonance Imaging Finding to Identify Morton Neuroma: The Slug Sign.

Morton neuroma is a common cause of forefoot pain and sensory disturbances, but it is difficult to identify on magnetic resonance imaging (MRI). The aim of this study was to verify the usefulness of a characteristic MRI finding (slug sign) for identifying Morton neuroma and to clarify the relationship between excised neuroma characteristics and preoperative MRI findings. Twenty-two web spaces were retrospectively assessed from the second and third intermetatarsal spaces of 11 feet of 10 patients (7 women and 3 men, aged average 59.5 years) who underwent surgical excision of Morton neuroma between 2017 and 2022. Asymptomatic web spaces were used as control. Neuromas with 2 branches of the plantar digital nerves on axial T1-weighted MRI (MRI-T1WI) were considered the slug sign. We investigated the preoperative presence of the slug sign in Morton neuroma and asymptomatic control web spaces. We also investigated the relationship between the maximum transverse diameter of the excised specimen and that estimated on coronal MRI-T1WI. A total of 15 Morton neuromas were excised and assessed. The slug signs were present in 10 intermetatarsal spaces in 15 web spaces with Morton neuroma whereas the sign was found in 1 intermetatarsal space in 7 asymptomatic web spaces. The sensitivity and specificity for the slug sign to diagnose Morton neuroma was 66.7% and 85.7%, respectively. The positive and negative predictive values were 90.9% and 54.5%, respectively. The mean maximum transverse diameter of excised neuromas was 4.7 mm. The mean maximum transverse diameter of neuromas on coronal MRI-T1WI was 3.4 mm. A significant positive correlation was found between the maximum transverse diameters of excised specimens and diameters estimated on coronal MRI-T1WI (r = 0.799, P < .001). The slug sign may be a useful indicator of Morton neuroma on MRI to confirm nerve involvement after bifurcation. Level IV, retrospective series.

The role of immunoglobulin in cerebrospinal fluid on the differential diagnosis of autoimmune encephalitis and viral encephalitis in children

BackgroundA case-control study was conducted to analyze the role of cerebrospinal fluid immunoglobulin in the differential diagnosis of autoimmune encephalitis and viral encephalitis in children.MethodsOne hundred and twenty patients with autoimmune encephalitis (AE) treated in our hospital from February 2021 to February 2022 were included as the observation group (AE group). 100 patients with viral encephalitis (VE group) were selected as the control group. The clinical data of all patients were collected and analyzed retrospectively. Immunoglobulin G (IgG) and immunoglobulin A (IgA)in cerebrospinal fluid of the two patients were measured by immune turbidimetry. Immunoglobulin M (IgM), and the diagnostic value of immunoglobulin in cerebrospinal fluid (CSF) in patients with AE was analyzed by receiver working curve (ROC).ResultsThe level of IgG in the cerebrospinal fluid of the AE group was higher than that of the VE group, and the level of IgM was lower than that of the VE group, and the difference was statistically significant (P < 0.05). There was no significant difference in IgA levels between the two groups (P > 0.05). In terms of Magnetic Resonance (MR) features, the paraventricular, hippocampal, occipital and parietal lobes were more involved in AE patients, frontal and temporal lobes were more involved in VE patients, and paraventricular and occipital lobes were involved in MS. The proportion of bilateral extensive lesions in both groups was significantly higher than 50%. The proportions of patients in the AE group involving the lateral ventricle, insula, and parietal lobes were significantly higher than those in the VE group, and the proportions involving the basal ganglia, temporal lobes, and frontal lobes were significantly lower than those in the VE group, and the differences were statistically significant (All P < 0.05). The Area Under Curve (AUC) of IgG, IgA and IgM alone in the diagnosis of AE were 0.795(0.587–0.762), 0.602(0.502–0.631) and 0.627(0.534–0.708), respectively with the sensitivity values of 81.24% and 65.608, respectively and the specificity values of 65.08%, 57.54% and 75.01% respectively. The AUC of IgA + IgM in the diagnosis of AE was 0.733(0.617–0.849), and the sensitivity and specificity are 62.58% and 75.07% respectively. The AUC of IgA + IgG in the diagnosis of AE was 0.823(0.730–0.917), and the sensitivity and specificity were 81.24% and 67.54% respectively. The AUC of IgG + IgM in the diagnosis of AE was 0.886(0.814 ~ 0.958), and the sensitivity and specificity were 84.48% and 77.59% respectively. The AUC of IgA + IgM + IgG in the diagnosis of AE was 0.924 (0.868–0.981) with the sensitivity of 93.82%, and the specificity of 77.56%.ConclusionThe level of immunoglobulin in cerebrospinal fluid can be used as an effective reference index for the diagnosis of AE. The combined detection of IgA, IgM and IgG can improve the accuracy, sensitivity and specificity of AE.

Ectopic Pituitary Neuroendocrine Tumors/Adenomas Around the Sella Turcica

Functional or non-secretory ectopic pituitary neuroendocrine tumors (PitNET) can form around the sella turcica during the development of the adenohypophysis by differentiating and detaching from the pharyngeal roof. These tumors usually appear in the sphenoid sinus, clivus, cavernous sinus, infundibulum, and suprasellar cistern. Ectopic PitNETs typically display the characteristic magnetic resonance imaging findings of pituitary adenomas. However, preoperative diagnosis of PitNETs is usually challenging because of the variety of clinical and imaging presentations, locations, and sizes. Ectopic suprasellar PitNETs resemble mass lesions in the pituitary stalk. Ectopic cavernous sinus of PitNETs are typically microadenomas in the medial wall. Ectopic sphenoclival tumors are characterized by more aggressive tumor activity than the other ectopic PitNETs. Although ectopic PitNETs are exceedingly rare, they should be considered as a differential diagnosis for masses around the sella turcica. Treatment of the disease should be individualized and may include medical care, surgical resection, gamma-knife radiosurgery, and radiotherapy.

Clinicoradiological features of cerebral microbleeds diagnosed on magnetic resonance neuroimaging.

Cerebral microbleeds (MBs) are recently described entity on magnetic resonance (MR) neuroimaging and are considered one of the markers of small vessel disease. We aimed to study the clinicoradiological features of cerebral MBs that were diagnosed in MR neuroimaging. We studied 109 South Indian patients, who presented to a tertiary care institution for MR neuroimaging with cerebral MBs as diagnosed on MR neuroimaging based on either the gradient T2* imaging or susceptibility-weighted imaging. The clinical details and coexisting MR features of infarcts, macrohemorrhages, lacunar infarcts, and white matter leukoaraiosis were evaluated and analyzed. Of 109 patients, 79 were males and 30 were females. Associated clinical comorbidities noted include hypertension (62.39%), diabetes (23.85%), and alcoholism (31.19%) apart from the history of anti-platelet/anti-coagulant usage (15.5%), previous cardiac disease (12.84%), and previous stroke/transient ischemic attacks (9.17%). Other co-existing neuroimaging abnormalities noted include cortical infarcts (27.52%), old hemorrhages (29.36%), lacunar infarcts (56.88%), and white matter leukaraiosis (67.89%). The clinicoradiological features of cerebral MBs in South Indian patients are similar to other Asian and Western studies with significant coexistence of clinical comorbidities and imaging features of small vessel changes. Further studies with a larger sample are needed to correlate the grade of MBs to the individual risk of these clinicoradiological characteristics.

Pathological and imaging features, treatment, and prognosis of primary intraventricular lymphoma: A review of cases from a single center

PurposeThe purpose of this retrospective study was to analyze the imaging and pathological features, treatment, and prognosis of patients with primary intraventricular lymphomas (PIL) in order to enhance physicians' understanding of the diagnosis and treatment of PIL. MethodsA retrospective analysis was conducted on 13 cases of PIL that were hospitalized in our institution. Clinical and imaging data of the patients were collected and compared with the pathology data to summarize and analyze the qualitative diagnostic value of magnetic resonance (MR) features. ResultsAmong the enrolled patients, there were nine males and four females, with an average age of (56 ± 9.0) years. The major clinical features observed in PIL patients were headache and dizziness. All 13 patients underwent plain and contrast-enhanced MR scans, revealing multiple foci in 7 cases and single foci in 6 cases. The lesions were located in the lateral ventricle in 10 cases, the third ventricle in 4 cases, and the fourth ventricle in 4 cases. Plain MR scans demonstrated an isointense or slightly hypointense signal on T1-weighted imaging (T1WI) and an isointense or slightly hyperintense signal on T2-weighted imaging (T2WI). Contrast-enhanced scans showed uniform and consistent enhancement of the tumors. Surgical treatment was performed in all patients, and postoperative pathology confirmed the presence of diffuse large B-cell lymphoma. ConclusionsPIL exhibits specific imaging and pathological features, with diffuse large B-cell lymphoma being the main pathological type. Pathological examination and immunophenotype analysis serve as the gold standards for PIL diagnosis.

CMR characterization of patients with heart failure and left bundle branch block

Abstract Aims We aimed to identify the distinctive cardiovascular magnetic resonance (CMR) features of patients with left bundle branch block (LBBB) and heart failure with reduced ejection fraction (HFrEF) of presumed non-ischaemic aetiology. The secondary aim was to determine whether these individuals exhibit characteristics that could potentially serve as predictors of left ventricular ejection fraction (LVEF) recovery as compared with patients without LBBB. Methods and results We prospectively recruited patients with HFrEF (LVEF ≤ 40%) on echocardiography who were referred for early CMR examination. Patients with an established diagnosis of coronary artery disease and known structural or congenital heart disease were excluded. LV recovery was defined as achieving ≥10% absolute improvement to ≥40% in LVEF between baseline evaluation to CMR. A total of 391 patients were recruited including 115 (29.4%) with LBBB. Compared with HF patients without LBBB, those with LBBB exhibited larger left ventricles and smaller right ventricles, but no differences were observed with respect to LVEF (35.8 ± 12 vs. 38 ± 12%, P = 0.105). The overall rate of LV recovery from baseline echocardiogram to CMR (70 [42–128] days) was not significantly different between LBBB and non-LBBB patients (27.8% vs. 31.5%, P = 0.47). Reduced LVEF remained an independent predictor of LV non-recovery only in patients with LBBB. Conclusion Patients presenting with HFrEF and LBBB had larger LV cavities and smaller RV cavities than those without LBBB but no difference in prevalence of scar or ischaemia. The rates of LV recovery were similar between both groups, which supports current guidelines to defer device therapy until 3–6 months of guideline-directed medical therapy, rather than early CMR and device implantation.

Clinical Case of Cor Triatriatum

Cor Triatriatum is utterly rare congenital heart disease, which has characteristic magnetic resonance and echocardiographic symptoms. Complexity of the diagnostics is an asymptomatic clinical flow, so timely diagnostics and therapy will help to defer possible complications and improve the quality of the life of these patients.

High-Quality Fusion and Visualization for MR-PET Brain Tumor Images via Multi-Dimensional Features.

The fusion of magnetic resonance imaging and positron emission tomography can combine biological anatomical information and physiological metabolic information, which is of great significance for the clinical diagnosis and localization of lesions. In this paper, we propose a novel adaptive linear fusion method for multi-dimensional features of brain magnetic resonance and positron emission tomography images based on a convolutional neural network, termed as MdAFuse. First, in the feature extraction stage, three-dimensional feature extraction modules are constructed to extract coarse, fine, and multi-scale information features from the source image. Second, at the fusion stage, the affine mapping function of multi-dimensional features is established to maintain a constant geometric relationship between the features, which can effectively utilize structural information from a feature map to achieve a better reconstruction effect. Furthermore, our MdAFuse comprises a key feature visualization enhancement algorithm designed to observe the dynamic growth of brain lesions, which can facilitate the early diagnosis and treatment of brain tumors. Extensive experimental results demonstrate that our method is superior to existing fusion methods in terms of visual perception and nine kinds of objective image fusion metrics. Specifically, in the results of MR-PET fusion, the SSIM (Structural Similarity) and VIF (Visual Information Fidelity) metrics show improvements of 5.61% and 13.76%, respectively, compared to the current state-of-the-art algorithm. Our code is publicly available at: https://github.com/22385wjy/MdAFuse.

Comparative Evaluation of Machine Learning Models for Subtyping Triple-Negative Breast Cancer: A Deep Learning-Based Multi-Omics Data Integration Approach.

Objective: Triple-negative breast cancer (TNBC) poses significant diagnostic challenges due to its aggressive nature. This research develops an innovative deep learning (DL) model based on the latest multi-omics data to enhance the accuracy of TNBC subtype and prognosis prediction. The study focuses on addressing the constraints of prior studies by showcasing a model with substantial advancements in data integration, statistical performance, and algorithmic optimization. Methods: Breast cancer-related molecular characteristic data, including mRNA, miRNA, gene mutations, DNA methylation, and magnetic resonance imaging (MRI) images, were retrieved from the TCGA and TCIA databases. This study not only compared single-omics with multi-omics machine learning models but also applied Bayesian optimization to innovatively optimize the neural network structure of a DL model for multi-omics data. Results: The DL model for multi-omics data significantly outperformed single-omics models in subtype prediction, achieving a 98.0% accuracy in cross-validation, 97.0% in the validation set, and 91.0% in an external test set. Additionally, the MRI radiomics model showed promising performance, especially with the training set; however, a decrease in performance during transfer testing underscored the advantages of the DL model for multi-omics data in data consistency and digital processing. Conclusion: Our multi-omics DL model presents notable innovations in statistical performance and transfer learning capability, bearing significant clinical relevance for TNBC classification and prognosis prediction. While the MRI radiomics model proved effective, it requires further optimization for cross-dataset application to enhance accuracy and consistency. Our findings offer new insights into improving TNBC classification and prognosis through multi-omics data and DL algorithms.

Bickerstaff brainstem encephalitis, an uncommon presentation in a child: a case report

BackgroundThe typical clinical and radiological presentation of Bickerstaff brainstem encephalitis (BBE) has been highlighted in this case report.Case presentationBickerstaff encephalitis is a rare autoimmune inflammatory disorder and is considered a subtype of Guillain–Barré syndrome (GBS) along with Miller Fisher syndrome. The diagnosis of BBE is largely clinical, though laboratory tests and imaging can be of supportive value. We report a case of a 5-year-old child who presented with a classical clinical triad of BBE with characteristic magnetic resonance imaging (MRI) findings.ConclusionsBBE is a rare disease with very few cases being reported with typical clinical and radiological findings. Hence, we reported a typical case of BBE to make an addition to the available literature.

Comprehensive integrated analysis of MR and DCE-MR radiomics models for prognostic prediction in nasopharyngeal carcinoma

Although prognostic prediction of nasopharyngeal carcinoma (NPC) remains a pivotal research area, the role of dynamic contrast-enhanced magnetic resonance (DCE-MR) has been less explored. This study aimed to investigate the role of DCR-MR in predicting progression-free survival (PFS) in patients with NPC using magnetic resonance (MR)- and DCE-MR-based radiomic models. A total of 434 patients with two MR scanning sequences were included. The MR- and DCE-MR-based radiomics models were developed based on 289 patients with only MR scanning sequences and 145 patients with four additional pharmacokinetic parameters (volume fraction of extravascular extracellular space (ve), volume fraction of plasma space (vp), volume transfer constant (Ktrans), and reverse reflux rate constant (kep) of DCE-MR. A combined model integrating MR and DCE-MR was constructed. Utilizing methods such as correlation analysis, least absolute shrinkage and selection operator regression, and multivariate Cox proportional hazards regression, we built the radiomics models. Finally, we calculated the net reclassification index and C-index to evaluate and compare the prognostic performance of the radiomics models. Kaplan-Meier survival curve analysis was performed to investigate the model’s ability to stratify risk in patients with NPC. The integration of MR and DCE-MR radiomic features significantly enhanced prognostic prediction performance compared to MR- and DCE-MR-based models, evidenced by a test set C-index of 0.808 vs 0.729 and 0.731, respectively. The combined radiomics model improved net reclassification by 22.9%–52.6% and could significantly stratify the risk levels of patients with NPC (p = 0.036). Furthermore, the MR-based radiomic feature maps achieved similar results to the DCE-MR pharmacokinetic parameters in terms of reflecting the underlying angiogenesis information in NPC. Compared to conventional MR-based radiomics models, the combined radiomics model integrating MR and DCE-MR showed promising results in delivering more accurate prognostic predictions and provided more clinical benefits in quantifying and monitoring phenotypic changes associated with NPC prognosis.

NIMG-79. DIFFERENTIATION OF SUBTYPES IN AFULLY AUTOMATED DEEP LEARN TUMORS USING PREOPERATIVEM RIMAGES ING APPROACH FOR ACCURATE PRIMARY INTRACRANIAL

Abstract BACKGROUND Intracranial germ cell tumors (iGCTs) are divided into germinomas (GEs) and nongerminomatous germ cell tumors (NGGCTs), each having distinct treatments and prognoses. However, predictive biomarkers for differentiation are limited. Here, we aim to develop a deep learning (DL) model that can automatically differentiate GEs from NGGCTs using preoperative magnetic resonance (MR) images and analyzing how our model improved clinical decision making among five physicians. METHODS: This multicenter study included patients with pathology-confirmed iGCTs for the developed set (total n = 280), which was split into training (n = 200) and testing datasets (n= 80), and three independent validation datasets (n = 64), respectively. We developed a DL model based on 3D nnU-Net and preoperative MR images to differentiate GEs from NGGCTs. To evaluate the clinical value of the DL model, five physicians' accuracy and level of consistency in identifying tumor types were compared in the testing and three validation datasets, with and without referring to the DL model’s output. RESULTS The DL model achieved AUCs of 0.950, 0.921, 0.869, and 0.905 in the testing and three validation datasets, respectively, which is superior to using conventional information including MR features and clinical information (AUC=0.768, P=0.009). The physicians’ diagnostic performance improved from an average AUC of 0.695 without reference to the DL output to 0.842 using the DL output in the testing and independent validation datasets (21.2% improvement, P=0.014). CONCLUSIONS We developed and validated a DL model using a large dataset to accurately differentiate GEs from NGGCTs using preoperative MR images.

Three Signs to Help Detect Sjögren's Syndrome: Incidental Findings on Magnetic Resonance Imaging and Computed Tomography.

This study aimed to retrospectively investigate the prevalence of Sjögren's syndrome (SS) among patients with ranulas, parotid cysts, or parotid calcifications; identify the characteristic magnetic resonance imaging (MRI) or computed tomography (CT) findings of the lesions associated with SS; and compare the SS disease stages among SS patients with the three lesion types. A total of 228 patients with the lesions were classified into SS, possible SS, and non-SS groups. The prevalence of SS among patients with ranulas, parotid cysts, or parotid calcifications was 16%, 24%, and 40%, and the rates of either SS or possible SS were 25%, 41%, and 64%, respectively. SS was associated with (i) ranulas: ≤17 mm; (ii) parotid cysts: bilateral and multiple; and (iii) parotid calcifications: in females, bilateral, multiple, parenchymal, and no coexisting calcifications in other tissues. SS patients with ranulas were significantly younger and had lower submandibular gland stage scores on MRI/CT than those with other lesions. Additionally, in 58% and 15% of SS patients with ranulas and parotid calcifications, respectively, detection of the lesions led to the diagnosis of primary SS. Therefore, recognizing the prevalence of SS among patients with these lesions and the findings associated with SS can help detect undiagnosed SS.

Assessing the association between genetic and phenotypic features of dilated cardiomyopathy and outcome in patients with coronary artery disease.

To examine the relevance of genetic and cardiovascular magnetic resonance (CMR) features of dilated cardiomyopathy (DCM) in individuals with coronary artery disease (CAD). This study includes two cohorts. First, individuals with CAD recruited into the UK Biobank (UKB) were evaluated. Second, patients with CAD referred to a tertiary centre for evaluation with late gadolinium enhancement (LGE)-CMR were recruited (London cohort); patients underwent genetic sequencing as part of the research protocol and long-term follow-up. From 31 154 individuals with CAD recruited to UKB, rare pathogenic variants in DCM genes were associated with increased risk of death or major adverse cardiac events (hazard ratio 1.57, 95% confidence interval [CI] 1.22-2.01, p < 0.001). Of 1619 individuals with CAD included from the UKB CMR substudy, participants with a rare variant in a DCM-associated gene had lower left ventricular ejection fraction (LVEF) compared to genotype negative individuals (mean 47 ± 10% vs. 57 ± 8%, p < 0.001). Of 453 patients in the London cohort, 63 (14%) had non-infarct pattern LGE (NI-LGE) on CMR. Patients with NI-LGE had lower LVEF (mean 38 ± 18% vs. 48 ± 16%, p < 0.001) compared to patients without NI-LGE, with no significant difference in the burden of rare protein altering variants in DCM-associated genes between groups (9.5% vs. 6.7%, odds ratio 1.5, 95% CI 0.4-4.3, p = 0.4). NI-LGE was not independently associated with adverse clinical outcomes. Rare pathogenic variants in DCM-associated genes impact left ventricular remodelling and outcomes in stable CAD. NI-LGE is associated with adverse remodelling but is not an independent predictor of outcome and had no rare genetic basis in our study.

A unique case of a fulminant clonal CD8-positive T-cell lymphoproliferative disorder with CNS involvement

BackgroundThis is a unique case that describes the presentation, investigations, and disease trajectory of a fatal, clonal CD8-positive T-cell lymphoproliferative disorder in an otherwise healthy and immunocompetent patient with Epstein-Barr virus seronegative status. Central nervous system involving T-cell lymphoproliferative disorders are rare and typically encountered in the setting of immunocompromise. These disorders are often associated with aggressive cytomorphological features and characteristic magnetic resonance imaging patterns, which were not seen in this case.Case presentationHere we describe a case of a 65 year-old male presenting with neuropsychiatric symptoms, truncal ataxia, and falls who’s bone marrow, cerebrospinal fluid, and brain biopsy were consistent with a clonal CD8-positive T-cell lymphoproliferative disorder that did not meet existing World Health Organization criteria for classification as T-cell lymphoma. The patient was treated with intrathecal methotrexate resulting in transient improvement of his symptoms followed by disease progression and death related to aspiration.ConclusionsThis case highlights the importance of urgent and comprehensive work-up in patients with clinical features suggestive of lymphoma with central nervous system involvement, despite atypical imaging features and lack of cytomorphological features satisfying current World Health Organization classification criteria.