Protecting Prostate Cancer Classification From Rectal Artifacts via Targeted Adversarial Training.

Magnetic resonance imaging (MRI)-based deep neural networks (DNN) have been widely developed to perform prostate cancer (PCa) classification. However, in real-world clinical situations, prostate MRIs can be easily impacted by rectal artifacts, which have been found to lead to incorrect PCa classification. Existing DNN-based methods typically do not consider the interference of rectal artifacts on PCa classification, and do not design specific strategy to address this problem. In this study, we proposed a novel Targeted adversarial training with Proprietary Adversarial Samples (TPAS) strategy to defend the PCa classification model against the influence of rectal artifacts. Specifically, based on clinical prior knowledge, we generated proprietary adversarial samples with rectal artifact-pattern adversarial noise, which can severely mislead PCa classification models optimized by the ordinary training strategy. We then jointly exploited the generated proprietary adversarial samples and original samples to train the models. To demonstrate the effectiveness of our strategy, we conducted analytical experiments on multiple PCa classification models. Compared with ordinary training strategy, TPAS can effectively improve the single- and multi-parametric PCa classification at patient, slice and lesion level, and bring substantial gains to recent advanced models. In conclusion, TPAS strategy can be identified as a valuable way to mitigate the influence of rectal artifacts on deep learning models for PCa classification.

[Clinical characteristics analysis of 4 cases with acute flaccid myelitis in children].

Objective: To summarize the clinical manifestations, diagnosis, treatment and prognosis of acute flaccid myelitis (AFM) in children. Methods: Clinical characteristics of 4 AFM cases from Department of Neurology, Children's Hospital Affiliated to Capital Institute of Pediatrics, from September 2018 to November 2022, were analyzed retrospectively. Results: The age of 4 children with AFM was 7 years, 4 years and 3 months, 7 years and 1 month, 6 years and 5 months, respectively. There were 2 boys and 2 girls. Prodromal infection status showed 3 children of respiratory tract infection and 1 child of digestive tract infection. The main manifestation was asymmetrical limb weakness after infection, and the affected limb range was from monoplegia to quadriplegia. Cranial nerve injury was involved in 1 child, no encephalopathy. Magnetic resonance imaging in the spinal cord of all 4 children showed long T1 and T2 signals, mainly involving gray matter. Cerebrospinal fluid cell-protein separation was observed in 2 children. Pathogen detected in 1 child pharyngeal swab was enterovirus D68. Antibody IgM to adenovirus was positive in the blood of 1 child. Antibody IgG against Echo and Coxsackie B virus were positive in the blood of another child. After glucocorticoid, human immunoglobulin or simple symptomatic treatment and at the same time under later rehabilitation training, muscle strength recovered to different degrees, but there were disabilities left in 3 children. Conclusions: AFM should be considered in children with acute and asymmetrical flaccid paralysis accompanied by abnormal magnetic resonance imaging signal in the central region of spinal cord, especially post-infection. The effective treatment is limited and the prognosis is poor.

Bilateral transient osteoporosis of the hip: a neglected cause of hip pain during pregnancy.

Transient osteoporosis of the hip (TOH) is an important but often neglected cause of hip pain, which can gradually lead to debilitating mobility and carries risks such as fracture or avascular necrosis. A 39-year-old woman presented to the Rheumatology department two weeks post-cesarean delivery, reporting the onset of left mechanical hip pain since the 33rd week of pregnancy. After delivery, similar complaints emerged on the right side. Hip X-ray showed a decrease in bone density in the left hip. Later, Magnetic Resonance Imaging revealed bilateral bone marrow edema in both proximal femurs. The diagnosis of TOH was established, and the patient was treated with conservative measures. Seven months later, she was asymptomatic. Pregnancy is a recognized risk factor for TOH, especially in the last trimester. It is an important differential diagnosis to consider in cases of hip pain in pregnant or newly breastfeeding women.

[A study of the correlation between gray matter atrophy in multiple sclerosis and impairment of cognitive function domains].

Objective: To quantify cerebral cortical and deep gray matter atrophy in patients with multiple sclerosis (MS) and explore its correlation with impairment in domains of cognitive function. Methods: Twenty patients with MS and 16 healthy controls (HC) matched for age, sex, and education level were included. Using FreeSurfer software, based on 3D-MRI technology, the differences in cortical thickness and deep gray matter volume between the two groups were comparatively analyzed. A neuropsychological scale that included six domains of cognitive function was scored on both study groups to analyze the correlation between cortical thickness and volume of deep gray matter in MS patients with impairment in cognitive function domains. Results: Impairment in domains of cognitive function: cognitive impairment was present in 60% MS patients in this study, mainly manifesting as impairment of verbal memory, verbal fluency, visuospatial memory, and information processing speed function (all P<0.05). Of these, the majority had impaired visuospatial memory function (55.0%), and the least number of patients had impaired information processing speed (15.0%). Changes in cortical thickness: compared with the HC group, the MS group showed that cortical atrophy was mainly concentrated in the frontoparietal region, including significant thinning of cortical thickness in the left inferior parietal gyrus, right superior frontal gyrus, and the right superior parietal gyrus (all P<0.05). Among them, atrophy of the left inferior parietal gyrus was significantly positively correlated with the impairment of verbal memory, verbal fluency, and information processing speed (all P<0.05). There was a significant positive correlation between the right superior frontal gyrus atrophy and verbal memory, verbal fluency, and visuospatial memory impairment (all P<0.05). Changes in deep gray matter volume: compared with the HC group, deep gray matter volume in the MS group decreased significantly in the bilateral thalamus, bilateral putamen, bilateral pallidum (all P<0.01), and right nucleus accumbens (P<0.05). Among them, left thalamus atrophy was significantly positively correlated with visuospatial memory impairment (r=0.45, P=0.046), and left putamen atrophy was both significantly positively correlated with visuospatial memory (r=0.45, P=0.047) and information processing speed impairment (r=0.50, P=0.026). Conclusions: Early structural brain changes in MS are dominated by gray matter atrophy. Deep gray matter is more prominent than cortical atrophy.

[Clinical, imaging, and pathological characteristics of 35 cases of mitochondrial encephalomyopathy, lactic acidosis, and stroke-like episodes syndrome].

Objective: To summarize the clinical, imaging, and pathological characteristics of mitochondrial encephalomyopathy, lactic acidosis, and stroke-like episodes syndrome (MELAS) to improve the diagnosis of this rare disease. Methods: A retrospective case series was conducted to collect the clinical data and results of genetic testing, muscle biopsy, and imaging studies including computed tomography (CT), magnetic resonance imaging (MRI), and magnetic resonance spectroscopy (MRS) of 35 patients with MELAS admitted to the Nanjing Drum Tower Hospital from 2012 to 2021. Descriptive statistical analysis including mean, standard deviation, and frequency percentage were carried out. Results: The average age of onset of the patients was 30.2±2.3 years; the prevalence of family history was 20%. The two main initial symptoms were limb weakness and convulsions. The clinical manifestations of the neuromuscular system were proximal muscle weakness and exercise intolerance. The endocrine system is the most affected outside the neuromuscular system, with diabetes being the most common condition. Among the five patients who underwent brain CT, four showed hypodense lesions and two had calcified lesions. Brain MRI in 26 patients showed that the lesions more often affected the parietal lobe, basal ganglia, temporal lobe, occipital lobe, and frontal lobe than the infratentorial areas. Twelve of these individuals exhibited different levels of brain atrophy. Among the 10 patients who underwent 1H-MRS, nine showed a decrease in N-acetylaspartate (NAA) levels, eight exhibited abnormal lactate elevation (Lac peaks), whereas six had both reduced NAA levels and the presence of Lac peaks. Thirty-one patients underwent genetic testing; among them, 25 were found to have the mt.3243A>G mutation, while the remaining six exhibited rare gene alterations. Muscle biopsies were performed in 21 patients, and 15 showed abnormal mitochondrial proliferation manifested by ragged red fibers and defective oxidative phosphorylation manifested by cytochrome C oxidase (COX) enzyme-deficient muscle fibers. Conclusion: The clinical manifestations of MELAS syndrome are variable and complex, and early atypical symptoms could be missed or misdiagnosed. A detailed clinical history, imaging MRS analysis, muscle biopsy, and genetic testing are necessary to confirm the accurate diagnosis of MELAS.

Advances in Computational Biology for Diagnosing Neurodegenerative Diseases: A Comprehensive Review.

The numerous and varied forms of neurodegenerative illnesses provide a considerable challenge to contemporary healthcare. The emergence of artificial intelligence has fundamentally changed the diagnostic picture by providing effective and early means of identifying these crippling illnesses. As a subset of computational intelligence, machine-learning algorithms have become very effective tools for the analysis of large datasets that include genetic, imaging, and clinical data. Moreover, multi-modal data integration, which includes information from brain imaging (MRI, PET scans), genetic profiles, and clinical evaluations, is made easier by computational intelligence. A thorough knowledge of the course of the illness is made possible by this consolidative method, which also facilitates the creation of predictive models for early medical evaluation and outcome prediction. Furthermore, there has been a great deal of promise shown by the use of artificial intelligence to neuroimaging analysis. Sophisticated image processing methods combined with machine learning algorithms make it possible to identify functional and structural anomalies in the brain, which often act as early indicators of neurodegenerative diseases. This chapter examines how computational intelligence plays a critical role in improving the diagnosis of neurodegenerative diseases such as Parkinson's, Alzheimer's, etc. To sum up, computational intelligence provides a revolutionary approach for improving the identification of neurodegenerative illnesses. In the battle against these difficult disorders, embracing and improving these computational techniques will surely pave the path for more individualized therapy and more therapies that are successful.

[MRI-Based Assessment of Hepatic Iron Overload and Steatosis in Patients Undergoing Hemodialysis:Current Status,Challenges,and Perspectives].

Long-term treatment of anemia involving frequent blood transfusions and intravenous iron administration increases the risks of hepatic iron overload and steatosis in the patients undergoing hemodialysis.Pathological accumulation of iron damages hepatocytes,not only elevating the risks of progressive hepatic fibrosis and cirrhosis but also potentially accelerating the process of hepatic steatosis.Iron overload and steatosis may interact with each other,exacerbating liver damage and ultimately leading to further deterioration of hepatic fibrosis and cirrhosis.MRI characterized by non-invasiveness and high repeatability,enables the simultaneous quantitative assessment of hepatic iron and fat content,providing crucial information for early diagnosis and intervention of liver diseases.In recent years,researchers have achieved significant advances in the application of MRI in the diagnosis and treatment of liver diseases.MRI can accurately reflect the extent of hepatic iron overload and steatosis in patients and predict the risk of liver diseases.This article reviews the latest advances,challenges,and perspectives in the application of MRI in assessing hepatic iron overload and steatosis in the patients undergoing hemodialysis,aiming to offer valuable references for clinical practice.

Is there a relationship between low back pain and ligamentum flavum hypertrophy?

OBJECTIVE: A condition known as ligamentum flavum (LF) hypertrophy occurs when the ligamentum flavum (LF) swells as a result of pressures applied to the spine. Among the elderly population, lumbar spinal stenosis is a major cause of pain and disabilities. Numerous studies indicate that lumbar spinal stenosis etiology involves the ligamentum flavum in a major way. This study looks into the relationship between low back pain and ligamentum flavum thickening. PATIENTS AND METHODS: The imaging tests and case histories of all patients with low back pain who had consecutive magnetic resonance imaging exams performed at the Prince Sattam University and King Khalid hospitals in Al Kharj City will serve as the basis for this retrospective observational study. A radiologist utilized the Pfirrmann grading system, which is based on spinal levels starting from the first lumbar to the first sacral vertebrae, to measure the thickness of the ligamentum flavum in all cases who underwent magnetic resonance imaging (MRI). A correlation between age, hypertrophy of LF, and low back pain was investigated. RESULTS: There were 79 participants in the study, ages ranging from 21 to 82, 49 of which were men. The patients' average age was 54 years, and 62% of them were men. We found no appreciable variations in LF thickness according to gender. At the L4-L5 and L5-S1 levels, the left LF was noticeably thicker than the right. Moreover, there was a significant difference (p < 0.05) in the bilateral LF thicknesses at L5-S1 compared to the comparable sides at L4-L5. CONCLUSIONS: By evaluating the thickness of LF on magnetic resonance images, we discovered that it may be closely associated with the etiology of pain processes in the spine.

Neuroimaging and clinical features of bilateral Wallerian degeneration of middle cerebellar peduncles subsequent to pontine infarction.

OBJECTIVE: Wallerian degeneration (WD) of the middle cerebellar peduncles (MCPs) following pontine infarction is a rare secondary degenerative neurological condition. Due to its infrequency, there is limited research on its characteristics. METHODS: This study aims to present three cases of WD of MCPs following pontine infarction and to analyze the prognosis, clinical manifestations, and neuroimaging features by amalgamating our cases with previously reported ones. RESULTS: The cohort consisted of 25 cases, comprising 18 men and 7 women aged 29 to 77 years (mean age: 66.2 years). The majority of patients (94%) exhibit risk factors for cerebrovascular disease, with hypertension being the primary risk factor. Magnetic resonance imaging (MRI) can detect WD of MCPs within a range of 21 days to 12 months following pontine infarction. This degeneration is characterized by bilateral symmetric hyperintensities on T2/FLAIR-weighted images (WI) lesions in the MCPs. Moreover, restricted diffusion, with hyperintensity on diffusion-weighted imaging (DWI) and low apparent diffusion coefficient (ADC) signal intensity may be observed as early as 21 days after the infarction. Upon detection of WD, it was observed that 20 patients (80%) remained asymptomatic during subsequent clinic visits, while four (16%) experienced a worsening of pre-existing symptoms. CONCLUSIONS: These findings underscore the importance of neurologists enhancing their understanding of this condition by gaining fresh insights into the neuroimaging characteristics, clinical manifestations, and prognosis of individuals with WD of bilateral MCPs.

Ventricular restoration in adults with huge congenital left ventricular aneurysm: report of two cases.

Congenital ventricular aneurysms (CVA) are rare cardiac anomalies that have been predominantly described in the Black population. They are characterized by an akinetic ventricular protrusion that is commonly located at the basal and apical segments. Although the diagnosis is often incidental and the majority of patients are asymptomatic, life-threatening events such as persistent ventricular arrhythmias, CVA rupture, and heart failure are not uncommon. However, no standardized therapy is currently available and good outcomes have been reported with both conservative and surgical management. We report the cases of two young Black African patients with huge symptomatic CVA lesions who underwent successful surgical repair with a ventricular restoration technique. Both cases were consulted for chest pain and dyspnea. Chest X-ray and transthoracic Doppler echocardiography suggested the diagnosis. Thoracic angioscanner and thoracic magnetic resonance imaging confirmed the diagnosis. Both patients underwent successful surgery. This case report aims to revisit the diagnostic and therapeutic approach to this rare pathology, in our professional environment.

The clinical and predictive value of 18F-FDG PET/CT metabolic patterns in a clinical Chinese cohort with autoimmune encephalitis.

AIMS: To investigate the diagnostic and predictive role of 18F-FDG PET/CT in patients with autoimmune encephalitis (AE) as a whole group. METHODS: Thrty-five patients (20 females and 15 males) with AE were recruited. A voxel-to-voxel semi-quantitative analysis based on SPM12 was used to analyze 18F-FDG PET/CT imaging data compared to healthy controls. Further comparison was made in different prognostic groups categorized by modified Rankin Scale (mRS). RESULTS: In total, 24 patients (68.6%) were tested positive neuronal antibodies in serum and/or CSF. Psychiatric symptoms and seizure attacks were major clinical symptoms. In the acute stage, 13 patients (37.1%) demonstrated abnormal brain MRI results, while 33 (94.3%) presented abnormal metabolism patterns. 18F-FDG PET/CT was more sensitive than MRI (p < 0.05). Patients with AE mainly presented mixed metabolism patterns compared to the matched controls, demonstrating hypermetabolism mainly in the cerebellum, BG, MTL, brainstem, insula, middle frontal gyrus, and relatively hypometabolism in the frontal cortex, occipital cortex, temporal gyrus, right parietal gyrus, left cingulate gyrus (p < 0.05, FWE corrected). After a median follow-up of 26 months, the multivariable analysis identified a decreased level of consciousness as an independent risk factor associated with poor outcome of AE (HR = 3.591, p = 0.016). Meanwhile, decreased metabolism of right superior frontal gyrus along with increased metabolism of the middle and upper brainstem was more evident in patients with poor outcome (p < 0.001, uncorrected). CONCLUSION: 18F-FDG PET/CT was more sensitive than MRI to detect neuroimaging abnormalities of AE. A mixed metabolic pattern, characterized by large areas of cortical hypometabolism with focal hypermetabolism was a general metabolic pattern. Decreased metabolism of right superior frontal gyrus with increased metabolism of the middle and upper brainstem may predict poor long-term prognosis of AE.

Optic nerve compression associated with visual cortex functional alteration in dysthyroid optic neuropathy: A combined orbital and brain imaging study.

AIMS: To investigate the alterations of the optic nerve and visual cortex in dysthyroid optic neuropathy (DON), a subgroup of thyroid eye disease (TED). METHODS: Multiple orbital imaging biomarkers related to optic nerve compression and the amplitude of low-frequency fluctuations (ALFF) of the brain were obtained from 47 patients with DON, 56 TED patients without DON (nDON), and 37 healthy controls (HC). Correlation analyses and diagnostic tests were implemented. RESULTS: Compared with HC, the nDON group showed alterations in orbital imaging biomarkers related to optic nerve compression in posterior segments, as well as ALFF of the right inferior temporal gyrus and left fusiform gyrus. DON differed from nDON group mainly in the modified muscle index of the posterior segment of optic nerve, and ALFF of orbital part of right superior frontal gyrus, right hippocampus, and right superior temporal gyrus. Orbital and brain imaging biomarkers were significantly correlated with each other. Diagnostic models attained an area under a curve of 0.80 for the detection of DON. CONCLUSION: The combined orbital and brain imaging study revealed alterations of the visual pathway in patients with TED and DON as well as provided diagnostic value. The initiation of alterations in the visual cortex in TED may precede the onset of DON.

Measuring functional connectivity in frequency-domain helps to better characterize brain function.

Resting-state functional connectivity (FC) is widely used in multivariate pattern analysis of functional magnetic resonance imaging (fMRI), including identifying the locations of putative brain functional borders, predicting individual phenotypes, and diagnosing clinical mental diseases. However, limited attention has been paid to the analysis of functional interactions from a frequency perspective. In this study, by contrasting coherence-based and correlation-based FC with two machine learning tasks, we observed that measuring FC in the frequency domain helped to identify finer functional subregions and achieve better pattern discrimination capability relative to the temporal correlation. This study has proven the feasibility of coherence in the analysis of fMRI, and the results indicate that modeling functional interactions in the frequency domain may provide richer information than that in the time domain, which may provide a new perspective on the analysis of functional neuroimaging.

Brain-age prediction: Systematic evaluation of site effects, and sample age range and size.

Structural neuroimaging data have been used to compute an estimate of the biological age of the brain (brain-age) which has been associated with other biologically and behaviorally meaningful measures of brain development and aging. The ongoing research interest in brain-age has highlighted the need for robust and publicly available brain-age models pre-trained on data from large samples of healthy individuals. To address this need we have previously released a developmental brain-age model. Here we expand this work to develop, empirically validate, and disseminate a pre-trained brain-age model to cover most of the human lifespan. To achieve this, we selected the best-performing model after systematically examining the impact of seven site harmonization strategies, age range, and sample size on brain-age prediction in a discovery sample of brain morphometric measures from 35,683 healthy individuals (age range: 5-90 years; 53.59% female). The pre-trained models were tested for cross-dataset generalizability in an independent sample comprising 2101 healthy individuals (age range: 8-80 years; 55.35% female) and for longitudinal consistency in a further sample comprising 377 healthy individuals (age range: 9-25 years; 49.87% female). This empirical examination yielded the following findings: (1) the accuracy of age prediction from morphometry data was higher when no site harmonization was applied; (2) dividing the discovery sample into two age-bins (5-40 and 40-90 years) provided a better balance between model accuracy and explained age variance than other alternatives; (3) model accuracy for brain-age prediction plateaued at a sample size exceeding 1600 participants. These findings have been incorporated into CentileBrain (https://centilebrain.org/#/brainAGE2), an open-science, web-based platform for individualized neuroimaging metrics.

Study on the Relationship Between MRI Functional Imaging and Multiple Immunohistochemical Features of Glioma: A Noninvasive and More Precise Glioma Management.

Objective: To investigate the performance of diffusion-tensor imaging (DTI) and hydrogen proton magnetic resonance spectroscopy (1H-MRS) parameters in predicting the immunohistochemistry (IHC) biomarkers of glioma. Methods: Patients with glioma confirmed by pathology from March 2015 to September 2019 were analyzed, the preoperative DTI and 1H-MRS images were collected, apparent diffusion coefficient (ADC) and fractional anisotropy (FA), in the lesion area were measured, the relative values relative ADC (rADC) and relative FA (rFA) were obtained by the ratio of them in the lesion area to the contralateral normal area. The peak of each metabolite in the lesion area of 1H-MRS image: N-acetylaspartate (NAA), choline (Cho), and creatine (Cr), and metabolite ratio: NAA/Cho, NAA/(Cho + Cr) were selected and calculated. The preoperative IHC data were collected including CD34, Ki-67, p53, S-100, syn, vimentin, NeuN, Nestin, and glial fibrillary acidic protein. Results: One predicting parameter of DTI was screened, the rADC of the Ki-67 positive group was lower than that of the negative group. Two parameters of 1H-MRS were found to have significant reference values for glioma grades, the NAA and Cr decreased as the grade of glioma increased, moreover, Ki-67 Li was negatively correlated with NAA and Cr. Conclusion: NAA and Cr have potential application value in predicting glioma grades and tumor proliferation activity. Only rADC has predictive value for Ki-67 expression among DTI parameters.

[Disseminated tuberculosis revealed by epididymal localization in an immunocompetent patient: a case report]. / Tuberculose disséminée révélée par une localisation épididymaire chez un patient immunocompétent: à propos d'un cas.

Epididymal tuberculosis is rare and often presents diagnostic difficulties. It may be indicative of a disseminated form of the infection, which is the case of our patient. A 19-year-old man, with no past medical history, was admitted for a swollen painful left scrotum that had been evolving for 8 months. He had undergone an orchiectomy and the anatomopathological examination was consistent with epididymal tuberculosis. The radiological investigations had revealed other localizations of the infection: lymphatic, pulmonary, parietal and osteoarticular tuberculosis. Anti-tuberculosis therapy was introduced. However, in the 4th month of treatment, the patient developed seizures. A cerebral magnetic resonance imaging was practiced, concluding to cerebral tuberculomas. Anti-tuberculosis treatment was continued associated to an anticonvulsant with a favourable outcome. The originality of our observation resides in the mode of revelation of a disseminated paucisymptomatic tuberculosis, by an epididymal localization, in an immunocompetent patient.

Paraneoplastic neuromyelitis optica spectrum disorder associated with ovarian dysgerminoma: a case report and literature review.

Neuromyelitis optica spectrum disorder (NMOSD) is a clinical syndrome characterized by attacks of acute optic neuritis and transverse myelitis. We report a case with paraneoplastic NMOSD that improved after immunosuppressive therapy, surgical resection, and chemotherapy. A 48-year-old woman initially presented with gradual binocular visual loss over the course of one week. The patient was evaluated using magnetic resonance imaging (MRI), computed tomography (CT), visual evoked potential (VEP), pathological biopsy, immunohistochemistry, and autoimmune antibody testing. The brain MRI findings were normal. The VEP revealed prolonged P100 latencies in the right eye and an absence of significant waves in the left eye. Positive serum AQP4-IgG antibodies were found. The patient was diagnosed as NMOSD. Then the patient responded well to treatment with methylprednisolone. An ovarian tumor was found in the patient using abdominal MRI and CT. The tumor was surgically resected, and a pathological biopsy revealed that it was ovarian dysgerminoma. The patient received four rounds of chemotherapy after surgery. One month after the final chemotherapy treatment, a positron emission tomography (PET) scan revealed no tumor. The vision of the patient gradually recovered and serum AQP4 was negative. Furthermore, we summarized the characteristics of patients diagnosed with paraneoplastic NMOSD associated with ovarian neoplasms in previous studies. This is a characteristic case of overlapping NMOSD and ovarian dysgerminoma, demonstrating the importance of tumor therapy in cases of paraneoplastic NMOSD.

Lobe-Based Hepatic Uptake Index of Gd-EOB-DTPA on Contrast-Enhanced MRI to Quantitatively Discriminate between Compensated and Decompensated Hepatitis B-Related Cirrhosis.

Purpose: To use hepatic uptake index (HUI) of liver lobes on gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) to discriminate between patients with hepatitis B-related cirrhosis in compensated and decompensated statuses. Methods: Forty-four consecutive patients with hepatitis B-related cirrhosis who underwent Gd-EOB-DTPA-enhanced MRI were divided into compensated and decompensated statuses based on clinical evaluation. Volume and signal intensity of individual lobes were retrospectively measured to calculate HUI of the right liver lobe (RHUI), medial (MHUI) and lateral (LHUI) left liver lobes, and caudate lobe (CHUI). Spearman's rank correlation analyses were performed to evaluate relationships of lobe-based HUI with Child-Pugh and model for end-stage liver disease (MELD) scoring system scores in compensated and decompensated statuses. The Mann-Whitney U-test was used to compare the lobe-based HUI between compensated and decompensated statuses. The performance of lobe-based HUI in distinguishing cirrhosis was evaluated using receiver operating characteristic (ROC) analysis, and the area under the ROC curve (AUC) was calculated as a measure of accuracy. Delong's method was used for statistical analysis to elucidate which HUI is optimal. Results: Compensated and decompensated liver cirrhosis were confirmed in 25 (56.82%) and 19 (43.18%) patients, respectively. According to Spearman's rank correlation analysis, RHUI, MHUI, LHUI, and CHUI were all significantly associated with Child-Pugh and MELD scores (all P values <0.05). Receiver operating characteristic analysis demonstrated that among all lobe-based HUI parameters, RHUI could best perform the previous discrimination with a cut-off of 485.73 and obtain an AUC of 0.867. The AUC of RHUI improved and was significantly different from that of MHUI, LHUI, and CHUI (P = 0.03, P = 0.007, and P < 0.001, respectively, Delong's test). Conclusions: The RHUI could help quantitatively discriminate hepatitis B-related cirrhosis between compensated and decompensated statuses.

Dynamicity of brain network organization & their community architecture as characterizing features for classification of common mental disorders from whole-brain connectome.

The urgency of addressing common mental disorders (bipolar disorder, attention-deficit hyperactivity disorder (ADHD), and schizophrenia) arises from their significant societal impact. Developing strategies to support psychiatrists is crucial. Previous studies focused on the relationship between these disorders and changes in the resting-state functional connectome's modularity, often using static functional connectivity (sFC) estimation. However, understanding the dynamic reconfiguration of resting-state brain networks with rich temporal structure is essential for comprehending neural activity and addressing mental health disorders. This study proposes an unsupervised approach combining spatial and temporal characterization of brain networks to classify common mental disorders using fMRI timeseries data from two cohorts (N = 408 participants). We employ the weighted stochastic block model to uncover mesoscale community architecture differences, providing insights into network organization. Our approach overcomes sFC limitations and biases in community detection algorithms by modelling the functional connectome's temporal dynamics as a landscape, quantifying temporal stability at whole-brain and network levels. Findings reveal individuals with schizophrenia exhibit less assortative community structure and participate in multiple motif classes, indicating less specialized network organization. Patients with schizophrenia and ADHD demonstrate significantly reduced temporal stability compared to healthy controls. This study offers insights into functional connectivity (FC) patterns' spatiotemporal organization and their alterations in common mental disorders, highlighting the potential of temporal stability as a biomarker.

Shared functional specialization in transformer-based language models and the human brain.

When processing language, the brain is thought to deploy specialized computations to construct meaning from complex linguistic structures. Recently, artificial neural networks based on the Transformer architecture have revolutionized the field of natural language processing. Transformers integrate contextual information across words via structured circuit computations. Prior work has focused on the internal representations ("embeddings") generated by these circuits. In this paper, we instead analyze the circuit computations directly: we deconstruct these computations into the functionally-specialized "transformations" that integrate contextual information across words. Using functional MRI data acquired while participants listened to naturalistic stories, we first verify that the transformations account for considerable variance in brain activity across the cortical language network. We then demonstrate that the emergent computations performed by individual, functionally-specialized "attention heads" differentially predict brain activity in specific cortical regions. These heads fall along gradients corresponding to different layers and context lengths in a low-dimensional cortical space.