Developmental change of brain volume in Rett syndrome in Taiwan.

OBJECTIVE: Rett syndrome (RTT) is characterized by neurological regression. This pioneering study investigated the effect of age on brain volume reduction by analyzing magnetic resonance imaging findings in participants with RTT, ranging from toddlers to adults. METHODS: Functional evaluation and neuroimaging were performed. All scans were acquired using a Siemens Tim Trio 3 T scanner with a 32-channel head coil. RESULTS: The total intracranial volume and cerebral white matter volume significantly increased with age in the control group compared with that in the RTT group (p < 0.05). Cortical gray matter volume reduction in the RTT group continued to increase in bilateral parietal lobes and left occipital lobes (p < 0.05). The differences in cortical gray matter volume between typically developing brain and RTT-affected brain may tend to continuously increase until adulthood in both temporal lobes although not significant after correction for multiple comparison. CONCLUSIONS: A significant reduction in brain volume was observed in the RTT group. Cortical gray matter volume in the RTT group continued to reduce in bilateral parietal lobes and left occipital lobes. These results provide a baseline for future studies on the effect of RTT treatment and related neuroscience research.

A Semi-Automatic Magnetic Resonance Imaging Annotation Algorithm Based on Semi-Weakly Supervised Learning.

The annotation of magnetic resonance imaging (MRI) images plays an important role in deep learning-based MRI segmentation tasks. Semi-automatic annotation algorithms are helpful for improving the efficiency and reducing the difficulty of MRI image annotation. However, the existing semi-automatic annotation algorithms based on deep learning have poor pre-annotation performance in the case of insufficient segmentation labels. In this paper, we propose a semi-automatic MRI annotation algorithm based on semi-weakly supervised learning. In order to achieve a better pre-annotation performance in the case of insufficient segmentation labels, semi-supervised and weakly supervised learning were introduced, and a semi-weakly supervised learning segmentation algorithm based on sparse labels was proposed. In addition, in order to improve the contribution rate of a single segmentation label to the performance of the pre-annotation model, an iterative annotation strategy based on active learning was designed. The experimental results on public MRI datasets show that the proposed algorithm achieved an equivalent pre-annotation performance when the number of segmentation labels was much less than that of the fully supervised learning algorithm, which proves the effectiveness of the proposed algorithm.

Estimation of the rupture point of the craniovertebral junction intradural arteriovenous fistula with vessel wall magnetic resonance image and its pathological findings: A case report.

Background: Arteriovenous fistulas (AVFs) of the craniocervical junction (CCJ) and intradural AVFs are often associated with aneurysms and varics, and it is sometimes difficult to identify the ruptured point on radiological images. We report a case in which vessel wall magnetic resonance image (VW-MRI) was useful for identifying the ruptured point at the CCJ AVF. Case Description: A 70-year-old man presented with a sudden onset of headache. He had Glasgow Coma Scale E4V5M6, world federation of neurosurgical societies (WFNS) Grade I. Fisher group 3 subarachnoid hemorrhage and hydrocephalus were found on head computed tomography. Cerebral angiography showed a spinal AVF at the C1 level of the cervical spine. Magnetic resonance image-enhanced motion sensitized driven equilibrium (MSDE-method showed an enhancing effect in part of the AVF draining vein, but the vascular architecture of this lesion was indeterminate. We performed continuous ventricular drainage for acute hydrocephalus and antihypertensive treatment. Cerebral angiography was performed 30days after the onset of the disease, and was revealed an aneurysmal structure in a portion of the AVF draining vein, which VW-MRI initially enhanced. On the 38th day after onset, he underwent direct surgery to occlude the AV fistula and dissect the aneurysmal structure. Histopathology showed that the aneurysmal structure was varices with lymphocytic infiltration, and hemosiderin deposition was observed near the varices. Conclusion: Recently, VW-MRI has been reported to show an association between the enhancement of varices in dural AVF and rupture cases. VW-MRI, especially the enhanced MSDE method, may be useful in estimating the ruptured point in arteriovenous shunt disease.

Magnetic resonance imaging findings in patients with dropped head syndrome.

BACKGROUND: Dropped head syndrome (DHS) is difficult to diagnose only by clinical examination. Although characteristic images on X-rays of DHS have been studied, changes in soft tissue of the disease have remained largely unknown. Magnetic resonance imaging (MRI) is useful for evaluating soft tissue, and we therefore performed this study with the purpose of investigating the characteristic signal changes of DHS on MRI by a comparison with those of cervical spondylosis. METHODS: The study involved 35 patients diagnosed with DHS within 6 months after the onset and 32 patients with cervical spondylosis as control. The signal changes in cervical extensor muscles, interspinous tissue, anterior longitudinal ligament (ALL) and Modic change on MRI were analyzed. RESULTS: Signal changes of cervical extensor muscles were 51.4% in DHS and 6.3% in the control group, those of interspinous tissue were 85.7% and 18.8%, and those of ALL were 80.0% and 21.9%, respectively, suggesting that the frequency of signal changes of cervical extensor muscles, interspinous tissue and ALL was significantly higher in the DHS group (p < 0.05). The presence of Modic change of acute phase (Modic type I) was also significantly higher in the DHS group than in the control group (p < 0.001). CONCLUSION: MRI findings of DHS within 6 months after the onset presented the characteristic signal changes in cervical extensor muscles, interspinous tissue, ALL and Modic change. Evaluation of MRI signal changes is useful for an objective evaluation of DHS.

Pre-and post-surgical non-functional pituitary adenomas and their relationship with high levels of serum glucose.

OBJECTIVES: This clinical, analytical, retro-prospective, auto-controlled, not randomized, and not blinded study, aimed to investigate the association of changes in the serum glucose levels with the pre-and-post changes in the size tumor in mm3 in the Non-Functional pituitary adenomas. METHODS: Pre-and post-surgical MRI, as well as the measurements in the serum glucose levels and immunohistochemical techniques were performed in all the patients in the study, with a mean followed-up until 208.57 days. A comparison was made between the reductions in tumor size of hormonally active pituitary adenomas (HSPAs) vs NFPAs. RESULTS: Seventy-four patients were included in this study, of whom, 46 were NFPAs. The decrease in the NFPAs tumor size after surgery was statistically significant (P ≤ 0.0001). The Mean of the differences of both type of tumors in mm3 were -9552 ± 10287. Pre-surgery, the mean of the HSPAs were 8.923 ± 2.078; and the NFPAs were 14.161 ± 1.912. The differences in the tumor size were statistically significant (p = 0.039). Post-surgical, the mean of the HSPAs were 2.079 ± 971, with a (p = 0.14): and the NFPAs were 4.609 ± 1.205. After surgery of the NFPAs, most of the patients-maintained serum levels ≤ 100 mg/dL, with a statistical significance (P ≤ 0.0003). CONCLUSION: This study demonstrates for the first time the correlation between the presence of pre-and post- surgical changes in the NFPAs, with modifications in the levels of serum glucose, and the comparison, pre- and post-surgical between the tumor size of HSPAs and NFPAs.

Three-dimensional magnetic resonance imaging-based statistical shape analysis and machine learning-based prediction of patellofemoral instability.

This study performed three-dimensional (3D) magnetic resonance imaging (MRI)-based statistical shape analysis (SSA) by comparing patellofemoral instability (PFI) and normal femur models, and developed a machine learning (ML)-based prediction model. Twenty (19 patients) and 31 MRI scans (30 patients) of femurs with PFI and normal femurs, respectively, were used. Bone and cartilage segmentation of the distal femurs was performed and subsequently converted into 3D reconstructed models. The pointwise distance map showed anterior elevation of the trochlea, particularly at the central floor of the proximal trochlea, in the PFI models compared with the normal models. Principal component analysis examined shape variations in the PFI group, and several principal components exhibited shape variations in the trochlear floor and intercondylar width. Multivariate analysis showed that these shape components were significantly correlated with the PFI/non-PFI distinction after adjusting for age and sex. Our ML-based prediction model for PFI achieved a strong predictive performance with an accuracy of 0.909 ± 0.015, and an area under the curve of 0.939 ± 0.009 when using a support vector machine with a linear kernel. This study demonstrated that 3D MRI-based SSA can realistically visualize statistical results on surface models and may facilitate the understanding of complex shape features.

Evaluation of the shrinkage process of a neck remnant after stent-coil treatment of a cerebral aneurysm using silent magnetic resonance angiography and computational fluid dynamics analysis: illustrative case.

BACKGROUND: Silent magnetic resonance angiography (MRA) mitigates metal artifacts, facilitating clear visualization of neck remnants after stent and coil embolization of cerebral aneurysms. This study aims to scrutinize hemodynamics at the neck remnant by employing silent MRA and computational fluid dynamics. OBSERVATIONS: The authors longitudinally tracked images of a partially thrombosed anterior communicating artery aneurysm's neck remnant, which had been treated with stent-assisted coil embolization, using silent MRA over a decade. Computational fluid dynamics delineated the neck remnant's reduction process, evaluating hemodynamic parameters such as flow rate, wall shear stress magnitude and vector, and streamlines. The neck remnant exhibited diminishing surface area, volume, neck size, dome depth, and aspect ratio. Its reduction correlated with a decline in the flow rate ratio of the remnant dome to the inflow parent artery. Analysis delineated regions within the contracting neck remnant characterized by consistently low average wall shear stress magnitude and variation, accompanied by notable variations in wall shear stress vector directionality. LESSONS: Evaluation of neck remnants after stent-coil embolization is possible through silent MRA and computational fluid dynamics. Predicting the neck remnant reduction may be achievable through hemodynamic parameter analysis.

Magnetic Resonance Observation of Cartilage Repair Tissue (MOCART) Scores > 55 at 6 Months Postoperative Predict Ability to Achieve Patient Acceptable Symptomatic State at Minimum 1 Year Postoperative Following Autologous Chondrocyte Implantation for Grade IV Chondral Defects About the Patellofemoral Joint.

PURPOSE: The primary aim is to evaluate the relationship between MOCART scores and patient satisfaction, as evaluated by achievement of (1) the Patient Acceptable Symptomatic State (PASS) and (2) the minimal clinically important difference (MCID) for Knee Injury and Osteoarthritis Score Quality of Life (KOOS QoL), for patients undergoing autologous chondrocyte implantation (ACI) for focal Grade IV patellofemoral chondral defects. The secondary aim is to determine the threshold MOCART score which predicts the ability to meet the PASS and the MCID for KOOS QoL. METHODS: Patients undergoing ACI for grade IV patellofemoral chondral defects by a single surgeon from 2017 to 2020 were identified by search of the EMR. To determine PASS status, patients were asked, "Do you consider your current level of symptoms to be acceptable?" KOOS QoL scores were also collected. Patients with 6-month postoperative knee MRI, PASS scores, and minimum 2-year follow-up data were included. Paired t tests and Wilcoxon Rank-Sum tests were used to evaluate the relationship between MOCART scores and (1) PASS achievement and (2) achievement of the MCID for KOOS QoL (12.8). RESULTS: Thirty-four patients were included, with a median age of 35.1 years [IQR: 24.6, 37.1], and BMI of 24.0 kg/m2 [IQR: 21.5, 28.1]. The median time to postoperative MRI was 6.7 months [IQR: 5.8, 7.9], and average follow-up time was 3.7 ± 1.2 years. Twenty-five patients (74%) achieved PASS, and 18 patients (out of 27 who had postop KOOS QoL Scores, 67%) achieved the MCID for KOOS QoL. Patients who achieved PASS had higher average MOCART scores (61.8 ± 16.0) than those who did not achieve PASS (45.0 ± 12.8, p=0.011), whereas patients who achieved the MCID for KOOS QoL did not have higher MOCART scores than those who did not achieve the MCID (61.9 ± 18.3 versus 53.3 ± 17.1, P = 0.25). There was no relationship between age, sex, lesion size, and lesion location and ability to achieve PASS or MCID for KOOS QoL (p>0.05). A threshold MOCART value of 55 was associated with the highest AUC on ROC analysis for likelihood of achieving PASS (0.778) and MCID for KOOS QoL (0.667). CONCLUSION: Higher MOCART scores are associated with an increased likelihood of achieving PASS following patellofemoral ACI. Moreover, MOCART scores > 55 predict the ability to achieve PASS and the MCID for KOOS QoL following patellofemoral ACI. LEVEL OF EVIDENCE: IV.

Pattern Clustering of Symmetric Regional Cerebral Edema on Brain MRI in Patients with Hepatic Encephalopathy.

Purpose: Metabolic abnormalities in hepatic encephalopathy (HE) cause brain edema or demyelinating disease, resulting in symmetric regional cerebral edema (SRCE) on MRI. This study aimed to investigate the usefulness of the clustering analysis of SRCE in predicting the development of brain failure. Materials and Methods: MR findings and clinical data of 98 consecutive patients with HE were retrospectively analyzed. The correlation between the 12 regions of SRCE was calculated using the phi (Φ) coefficient, and the pattern was classified using hierarchical clustering using the φ2 distance measure and Ward's method. The classified patterns of SRCE were correlated with clinical parameters such as the model for end-stage liver disease (MELD) score and HE grade. Results: Significant associations were found between 22 pairs of regions of interest, including the red nucleus and corpus callosum (Φ = 0.81, p < 0.001), crus cerebri and red nucleus (Φ = 0.72, p < 0.001), and red nucleus and dentate nucleus (Φ = 0.66, p < 0.001). After hierarchical clustering, 24 cases were classified into Group I, 35 into Group II, and 39 into Group III. Group III had a higher MELD score (p = 0.04) and HE grade (p = 0.002) than Group I. Conclusion: Our study demonstrates that the SRCE patterns can be useful in predicting hepatic preservation and the occurrence of cerebral failure in HE.

Simulation of acquisition shifts in T2 weighted fluid-attenuated inversion recovery magnetic resonance images to stress test artificial intelligence segmentation networks.

Purpose: To provide a simulation framework for routine neuroimaging test data, which allows for "stress testing" of deep segmentation networks against acquisition shifts that commonly occur in clinical practice for T2 weighted (T2w) fluid-attenuated inversion recovery magnetic resonance imaging protocols. Approach: The approach simulates "acquisition shift derivatives" of MR images based on MR signal equations. Experiments comprise the validation of the simulated images by real MR scans and example stress tests on state-of-the-art multiple sclerosis lesion segmentation networks to explore a generic model function to describe the F1 score in dependence of the contrast-affecting sequence parameters echo time (TE) and inversion time (TI). Results: The differences between real and simulated images range up to 19% in gray and white matter for extreme parameter settings. For the segmentation networks under test, the F1 score dependency on TE and TI can be well described by quadratic model functions (R2>0.9). The coefficients of the model functions indicate that changes of TE have more influence on the model performance than TI. Conclusions: We show that these deviations are in the range of values as may be caused by erroneous or individual differences in relaxation times as described by literature. The coefficients of the F1 model function allow for a quantitative comparison of the influences of TE and TI. Limitations arise mainly from tissues with a low baseline signal (like cerebrospinal fluid) and when the protocol contains contrast-affecting measures that cannot be modeled due to missing information in the DICOM header.

Do MRI Results Represent Functional Outcomes Following Arthroscopic Repair of an Isolated Meniscus Tear in Young Patients?-A Prospective Comparative Cohort Study.

BACKGROUND: The use of postoperative MRI to assess the healing status of repaired menisci is a long-standing issue. This study evaluates and compares functional and MRI outcomes following an arthroscopic meniscus repair procedure with the aim of postoperative MRI diagnostic accuracy clarification in young patients. METHODS: A total of 35 patients under 18 years old who underwent isolated meniscus repair were included. The Pedi-IKDC score, Lysholm score, and Tegner activity index (TAS) were compared between the groups formed according to the Stroller and Crues three-grade classification of postoperative MRI-based evaluations. Grade 3 MRI views were classified as unhealed, grade 2 as partially healed, and grade 1 as fully healed within the repaired meniscus, whereas grade 3 cases were considered unsuccessful due to MRI evaluation. RESULTS: MRI assessment revealed 4 cases of grade 1 (11.4%), 14 cases of grade 2 (40.8%), and 17 cases of grade 3 (48.0%) lesions. Pedi-IKDC and TAS scores were significantly higher among MRI grade 2 patients than among MRI grade 3 patients (p < 0.05). Weak negative correlations between MRI grades and all functional scales were found (p < 0.05). ROC analysis showed that Pedi-IKDC and TAS scores could correctly classify 77% and 71% of MRI grade 3 patients, respectively. The optimal cut-off values to detect grade 3 patients were 88.74 for the Pedi-IKDC score and 4.5 for the TAS score. CONCLUSIONS: To conclude, established functional score cut-off values may help identify unhealed meniscus repair patients.

Subarachnoid Hemorrhage Confirmed by Magnetic Resonance Imaging in a Patient with Brain Death owing to Hypoxic Encephalopathy Following Suicide by Hanging.

Although true subarachnoid hemorrhage (SAH) is an atypical complication owing to suicide by hanging, pseudo-SAH can often develop because of hypoxic encephalopathy. Therefore, differentiating pseudo-SAH from true SAH using brain computed tomography (CT) is often challenging. In Japan, an individual's cause of brain death must be determined to be eligible for organ donation, regardless of whether true SAH is involved or not. Herein, we report a case of SAH confirmed by magnetic resonance imaging (MRI) in a patient with brain death owing to hypoxic encephalopathy following suicide by hanging. A 48-year-old man attempted suicide by hanging. Upon arrival at the hospital, he developed pulseless electrical activity with apnea. Although spontaneous circulation returned within a few minutes of his arrival, spontaneous breathing did not recover. The patient was in deep comatose state without response to pain stimulation, brainstem reflexes, or electrical activities on an electroencephalogram. Consequently, the patient met diagnostic criteria for clinical brain death based on the Japanese organ transplantation law. Brain CT revealed global hypoxic injury and high density in the basal cisterns and subarachnoid space. Brain MR T2*-weighted imaging revealed low intensity at the left Sylvian fissure underlying the hematoma. These findings indicated brain death owing to hypoxic encephalopathy following hanging, and incidental true SAH was confirmed by MRI. Donor surgery and organ transplantation were performed. Spontaneous SAH can often develop secondary to hanging, and brain MRI can effectively determine whether the cause of brain death involves true SAH.

Evaluation and mitigation of deformable image registration uncertainties for MRI-guided adaptive radiotherapy.

PURPOSE: We evaluate the performance of a deformable image registration (DIR) software package in registering abdominal magnetic resonance images (MRIs) and then develop a mechanical modeling method to mitigate detected DIR uncertainties. MATERIALS AND METHODS: Three evaluation metrics, namely mean displacement to agreement (MDA), DICE similarity coefficient (DSC), and standard deviation of Jacobian determinants (STD-JD), are used to assess the multi-modality (MM), contour-consistency (CC), and image-intensity (II)-based DIR algorithms in the MIM software package, as well as an in-house developed, contour matching-based finite element method (CM-FEM). Furthermore, we develop a hybrid FEM registration technique to modify the displacement vector field of each MIM registration. The MIM and FEM registrations were evaluated on MRIs obtained from 10 abdominal cancer patients. One-tailed Wilcoxon-Mann-Whitney (WMW) tests were conducted to compare the MIM registrations with their FEM modifications. RESULTS: For the registrations performed with the MIM-CC, MIM-MM, MIM-II, and CM-FEM algorithms, their average MDAs are 0.62 ± 0.27, 2.39 ± 1.30, 3.07 ± 2.42, 1.04 ± 0.72 mm, and average DSCs are 0.94 ± 0.03, 0.80 ± 0.12, 0.77 ± 0.15, 0.90 ± 0.11, respectively. The p-values of the WMW tests between the MIM registrations and their FEM modifications are less than 0.0084 for STD-JDs and greater than 0.87 for MDA and DSC. CONCLUSIONS: Among the three MIM DIR algorithms, MIM-CC shows the smallest errors in terms of MDA and DSC but exhibits significant Jacobian uncertainties in the interior regions of abdominal organs. The hybrid FEM technique effectively mitigates the Jacobian uncertainties in these regions.

Narrative review of the utility of magnetic resonance imaging in radiotherapy for cervical cancer.

BACKGROUND AND OBJECTIVE: In radiotherapy (RT) for locally advanced cervical cancer, high soft tissue contrast on magnetic resonance imaging (MRI) can ensure accurate delineation of target volumes (TVs) and optimal dose distribution to the RT target and organs at risk (OAR). MRI-guided adaptive RT (MRIgART) is a novel technology that revises RT plans according to anatomical changes occurring throughout the treatment to improve target coverage and minimise OAR toxicity. This review aims to assess the evidence and gaps of MRI use in RT planning and MRIgART in the treatment of cervical cancer, as well as challenges in its clinical implementation. METHODS: Ovid Medline and PubMed were searched using keywords for MRI in RT for cervical cancer. After applying the inclusion and exclusion criteria, the initial search was deduced to 32 studies. A total of 37 final studies were reviewed, including eight additional articles from references. KEY CONTENT AND FINDINGS: In the primary studies, TVs and organ motion were assessed before, during, and after treatment. MRI was used to investigate dose distribution and therapeutic response to the treatment in association with its outcome. Lastly, rationales for MRIgART were evaluated. CONCLUSIONS: It was concluded that MRI enables accurate target delineation, assessment of organ motion and interfraction changes, and monitoring of treatment response through dynamic parameters. Enhanced target coverage and reduced OAR irradiation through MRIgART can improve local control and the overall outcome, although its rationales against the logistical challenges need to be evaluated on further research.

Inferior temporal quadrantanopia associated with pituitary adenomas and a potential mechanism of excessive optic nerve bending.

Background: Pituitary adenomas show typical visual field defects that begin superiorly and progress inferiorly. The cause of atypical visual field defects that start inferiorly remains unclear. This study aimed to understand this phenomenon using magnetic resonance imaging (MRI). Methods: A total of 220 patients with pituitary adenomas underwent a visual field assessment of both eyes. Preoperative visual fields were assessed and classified into two types: superior quadrantanopia (typical) and inferior quadrantanopia (atypical). Several parameters related to tumor characteristics and optic nerve compression were evaluated using MRI. Results: Of the 440 eyes examined, 174 (39.5%) had visual field defects. Of these, 28 (16.1%) had typical and 11 (6.3%) had atypical visual field defects. Patient age, tumor size, degree of cavernous sinus invasion, tumor pathology, and intratumor bleeding were similar between the two groups. The angle formed by the optic nerve in the optic canal and in the intracranial subarachnoid space at the exit of the optic canal (degree of optic nerve bending) was significantly larger in the atypical group than in the typical group (42.6° vs. 23.9°, P = 0.046). Conclusion: In some pituitary adenomas, visual field defects begin inferiorly. This may be caused by optic nerve compression on the superior surface by the bony margin of the optic canal exit. Therefore, pituitary adenomas should be considered in patients with atypical visual field defects.

Automatic segmentation of fat metaplasia on sacroiliac joint MRI using deep learning.

OBJECTIVE: To develop a deep learning (DL) model for segmenting fat metaplasia (FM) on sacroiliac joint (SIJ) MRI and further develop a DL model for classifying axial spondyloarthritis (axSpA) and non-axSpA. MATERIALS AND METHODS: This study retrospectively collected 706 patients with FM who underwent SIJ MRI from center 1 (462 axSpA and 186 non-axSpA) and center 2 (37 axSpA and 21 non-axSpA). Patients from center 1 were divided into the training, validation, and internal test sets (n = 455, 64, and 129). Patients from center 2 were used as the external test set. We developed a UNet-based model to segment FM. Based on segmentation results, a classification model was built to distinguish axSpA and non-axSpA. Dice Similarity Coefficients (DSC) and area under the curve (AUC) were used for model evaluation. Radiologists' performance without and with model assistance was compared to assess the clinical utility of the models. RESULTS: Our segmentation model achieved satisfactory DSC of 81.86% ± 1.55% and 85.44% ± 6.09% on the internal cross-validation and external test sets. The classification model yielded AUCs of 0.876 (95% CI: 0.811-0.942) and 0.799 (95% CI: 0.696-0.902) on the internal and external test sets, respectively. With model assistance, segmentation performance was improved for the radiological resident (DSC, 75.70% vs. 82.87%, p < 0.05) and expert radiologist (DSC, 85.03% vs. 85.74%, p > 0.05). CONCLUSIONS: DL is a novel method for automatic and accurate segmentation of FM on SIJ MRI and can effectively increase radiologist's performance, which might assist in improving diagnosis and progression of axSpA. CRITICAL RELEVANCE STATEMENT: DL models allowed automatic and accurate segmentation of FM on sacroiliac joint MRI, which might facilitate quantitative analysis of FM and have the potential to improve diagnosis and prognosis of axSpA. KEY POINTS: • Deep learning was used for automatic segmentation of fat metaplasia on MRI. • UNet-based models achieved automatic and accurate segmentation of fat metaplasia. • Automatic segmentation facilitates quantitative analysis of fat metaplasia to improve diagnosis and prognosis of axial spondyloarthritis.

Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network.

Convolutional neural networks (CNNs) have been used widely to predict biological brain age based on brain magnetic resonance (MR) images. However, CNNs focus mainly on spatially local features and their aggregates and barely on the connective information between distant regions. To overcome this issue, we propose a novel multi-hop graph attention (MGA) module that exploits both the local and global connections of image features when combined with CNNs. After insertion between convolutional layers, MGA first converts the convolution-derived feature map into graph-structured data by using patch embedding and embedding-distance-based scoring. Multi-hop connections between the graph nodes are modeled by using the Markov chain process. After performing multi-hop graph attention, MGA re-converts the graph into an updated feature map and transfers it to the next convolutional layer. We combined the MGA module with sSE (spatial squeeze and excitation)-ResNet18 for our final prediction model (MGA-sSE-ResNet18) and performed various hyperparameter evaluations to identify the optimal parameter combinations. With 2788 three-dimensional T1-weighted MR images of healthy subjects, we verified the effectiveness of MGA-sSE-ResNet18 with comparisons to four established, general-purpose CNNs and two representative brain age prediction models. The proposed model yielded an optimal performance with a mean absolute error of 2.822 years and Pearson's correlation coefficient (PCC) of 0.968, demonstrating the potential of the MGA module to improve the accuracy of brain age prediction.

Discrimination models with radiomics features derived from cardiovascular magnetic resonance images for distinguishing hypertensive heart disease from hypertrophic cardiomyopathy.

Background: Discriminating hypertrophic cardiomyopathy (HCM) and hypertensive heart disease (HHD) is challenging, because both are characterized by left ventricular hypertrophy (LVH). Radiomics might be effective to differentiate HHD from HCM. Therefore, this study aimed to investigate discriminators and build discrimination models between HHD and HCM using multiparametric cardiac magnetic resonance (CMR) findings and radiomics score (radscore) derived from late gadolinium enhancement (LGE) and cine images. Methods: In this single center, retrospective study, 421 HCM patients [median and interquartile range (IQR), 50.0 (38.0-59.0) years; male, 70.5%] from January 2017 to September 2021 and 200 HHD patients [median and IQR, 44.5 (35.0-57.0) years; male, 88.5%] from September 2015 to July 2022 were consecutively included and randomly stratified into a training group and a validation group at a ratio of 6:4. Multiparametric CMR findings were obtained using cvi42 software and radiomics features using Python software. After dimensional reduction, the radscore was calculated by summing the remaining radiomics features weighted by their coefficients. Multiparametric CMR findings and radscore that were statistically significant in univariate logistic regression were used to build combined discrimination models via multivariate logistic regression. Results: After multivariate logistic regression, the maximal left ventricular end diastolic wall thickness (LVEDWT), left ventricular ejection fraction (LVEF), presence of LGE, cine radscore and LGE radscore were identified as significant characteristics and used to build a combined discrimination model. This model achieved an area under the receiver operator characteristic curve (AUC) of 0.979 (0.968-0.990) in the training group and 0.981 (0.967-0.995) in the validation group, significantly better than the model using multiparametric CMR findings alone (P<0.001). Conclusions: Radiomics features derived from cardiac cine and LGE images can effectively discriminate HHD from HCM.

Evolución neurológica en la lesión medular traumática en función del tamaño de la hemorragia intraparenquimatosa / Neurological evolution in traumatic spinal cord injury according to the size of the intraparenchymal hemorrhage

Introducción y objetivos: La presencia de hemorragia medular es considerada como un factor de mal pronóstico evolutivo en el estudio de la lesión medular traumática (LMT). No obstante, se ha sugerido en trabajos publicados que el pronóstico de los sangrados de menor tamaño no es tan negativo. El objetivo del presente trabajo es valorar la evolución neurológica en individuos con hemorragia intraparenquimatosa en función del tamaño de la misma. Material y métodos: Estudio observacional retrospectivo. Recopilados los pacientes ingresados por LMT aguda con estudio de resonancia, que objetivase una hemorragia medular entre los años 2010 y 2018. Se establecieron 2 grupos en función del tamaño del sangrado: microhemorragias (menor de 4mm) y macrohemorragias (superior a 4mm). Se comparó la exploración neurológica al ingreso y al alta atendiendo al grado AIS y el índice motor (IM). Resultados: Recogidos 46 casos, 17 microhemorragias y 29 macrohemorragias. El 70,6% de las primeras eran AIS A mientras que entre las macrohemorragias el porcentaje era del 89,6%. Al momento del alta se apreció una mejoría del grado AIS en el 40,0% de las microhemorragias por un 4,0% de las macrohemorragias (p=0,008). El IM inicial fue muy similar, 45,2±22,2 en las microhemorragias y 40,9±20,4 en las mayores (p=0,459), pero al alta era superior en el primer grupo: 60,4±20,5 por 42,7±22,8 (p=0,033). Ocho pacientes (17,4%) fallecieron durante el ingreso. Conclusiones: Existe relación entre el tamaño de la hemorragia intraparenquimatosa y el pronóstico neurológico de la LMT, presentando una mejor evolución las hemorragias menores de 4mm.(AU)

Introduction and objectives: The presence of spinal cord hemorrhage is considered as a poor prognostic factor in traumatic spinal cord injury (SCI). However, it has been suggested in published works that the prognosis of small hemorrhages is not so negative. The aim of this paper is to assess the neurological evolution in individuals with intraparenchymal hemorrhage according to its size. Material and methods: Retrospective observational study. Selected all the patients admitted for acute traumatic SCI between 2010 and 2018 with early magnetic resonance study and spinal cord hemorrhage. Two groups were established depending on the size of the bleeding: microhemorrhages (less than 4mm) and macrohemorrhages (greater than 4mm). The neurological examination at admission and discharge was compared according to the AIS grade and the motor score (MS). Results: Forty-six cases collected, 17 microhemorrhages and 29 macrohemorrhages. 70.6% of the microhemorrhages were AIS A while among macrohemorrhages the percentage was 89.6%. At the time of discharge, an improvement in the AIS grade was observed in 40.0% of the microhemorrhages compared to 4.0% of the macrohemorrhages (P=.008). Initial MS was similar, 45.2±22.2 in the microhemorrhages and 40.9±20.4 in the macrohemorrhages (P=.459), but at discharge it was higher in the first group: 60.4±20.5 for 42.7±22.8 (P=.033). Eight patients (17.4%) died during admission. Conclusions: There is a relationship between the size of the intraparenchymal hemorrhage and the neurological prognosis of SCI, with hemorrhages smaller than 4mm presenting a better evolution.(AU)