Blood-CSF barrier integrity in amyotrophic lateral sclerosis.

The integrity of the blood-CSF barrier plays a major role in inflammation, but also in shielding the central nervous system from external and systemic - potentially toxic - factors. Here we report results of measurements of the albumin quotient - which is thought to mirror the integrity of the blood/CSF barrier - in 1059 amyotrophic lateral sclerosis patients. The results were compared with groups of patients suffering from Alzheimer´s disease, facial palsy and tension headache. The albumin quotient, an accepted measure of the blood/CSF barrier integrity, was not significantly different from control populations. In addition, we found that the albumin quotient correlated with survival of the patients; this effect was mainly driven by male patients and influenced by age, BMI and diabetes mellitus. We conclude that the blood/CSF barrier is intact in this large cohort of ALS patients and that the albumin quotient correlates with survival. Whether this is important for the pathogenesis of the disease, requires mechanistic studies.

Categorization of the amyotrophic lateral sclerosis population via the clinical determinant of post-onset ΔFS for study design and medical practice.

The amyotrophic lateral sclerosis (ALS) functional rating scale-revised (ALSFRS-R) has become the most widely utilized measure of disease severity in patients with ALS, with change in ALSFRS-R from baseline being a trusted primary outcome measure in ALS clinical trials. This is despite the scale having several established limitations, and although alternative scales have been proposed, it is unlikely that these will displace ALSFRS-R in the foreseeable future. Here, we discuss the merits of delta FS (ΔFS), the slope or rate of ALSFRS-R decline over time, as a relevant tool for innovative ALS study design, with an as yet untapped potential for optimization of drug effectiveness and patient management. In our view, categorization of the ALS population via the clinical determinant of post-onset ΔFS is an important study design consideration. It serves not only as a critical stratification factor and basis for patient enrichment but also as a tool to explore differences in treatment response across the overall population; thereby, facilitating identification of responder subgroups. Moreover, because post-onset ΔFS is derived from information routinely collected as part of standard patient care and monitoring, it provides a suitable patient selection tool for treating physicians. Overall, post-onset ΔFS is a very attractive enrichment tool that is, can and should be regularly incorporated into ALS trial design.

Coping as a resource to allow for psychosocial adjustment in fatal disease: results from patients with amyotrophic lateral sclerosis.

Background: Amyotrophic lateral sclerosis (ALS) is a fatal disorder, which imposes a severe emotional burden on patients. Appropriate coping mechanisms may alleviate this burden and facilitate wellbeing, with social support known to be a successful coping strategy. This observational study aimed to determine the interplay of general coping traits of hope for success and fear of failure, coping behavior of social activity, and patients' wellbeing. Methods: In this cross-sectional study, patients with ALS from a clinical-epidemiological registry in Southwestern Germany were interviewed regarding coping traits (achievement-motivated behavior: hope for success and fear of failure), coping behavior of social activity, and psychosocial adjustment, determined using measures of depressiveness, anxiety [both measured by Hospital Anxiety and Depression Scale (HADS)], and quality of life [Anamnestic Comparative Self-Assessment (ACSA)]. Demographics, clinical [ALS Functional Rating Scale revised version (ALSFRS-R)], and survival data were recorded. Results: A total of 868 patients [60.70% male patients, mean age: 64.70 (±10.83) years, mean ALSFRS-R: 37.36 ± 7.07] were interviewed. Anxiety in patients was found to be associated with a high fear of failure. In contrast, a generally positive attitude in patients exemplified in high hopes for success was associated with better wellbeing. Finally, coping behavior of social activity explained up to 65% of the variance of depressiveness among the patients with ALS. Conclusion: In this study, we present evidence that the wellbeing of patients with ALS is not an immediate fatalistic consequence of physical degradation but rather determined by coping traits and behavior, which may be trained to substantially increase the wellbeing of patients with ALS.

Development of an algorithm for identifying paraneoplastic ischemic stroke in association with lung, pancreatic, and colorectal cancer.

Background: Paraneoplastic ischemic stroke has a poor prognosis. We have recently reported an algorithm based on the number of ischemic territories, C-reactive protein (CRP), lactate dehydrogenase (LDH), and granulocytosis to predict the underlying active cancer in a case-control setting. However, co-occurrence of cancer and stroke might also be merely incidental. Objective: To detect cancer-associated ischemic stroke in a large, unselected cohort of consecutive stroke patients by detailed analysis of ischemic stroke associated with specific cancer subtypes and comparison to patients with bacterial endocarditis. Methods: Retrospective single-center cohort study of consecutive 1612 ischemic strokes with magnetic resonance imaging, CRP, LDH, and relative granulocytosis data was performed, including identification of active cancers, history of now inactive cancers, and the diagnosis of endocarditis. The previously developed algorithm to detect paraneoplastic cancer was applied. Tumor types associated with paraneoplastic stroke were used to optimize the diagnostic algorithm. Results: Ischemic strokes associated with active cancer, but also endocarditis, were associated with more ischemic territories as well as higher CRP and LDH levels. Our previous algorithm identified active cancer-associated strokes with a specificity of 83% and sensitivity of 52%. Ischemic strokes associated with lung, pancreatic, and colorectal (LPC) cancers but not with breast and prostate cancers showed more frequent and prominent characteristics of paraneoplastic stroke. A multiple logistic regression model optimized to identify LPC cancers detected active cancer with a sensitivity of 77.8% and specificity of 81.4%. The positive predictive value (PPV) for all active cancers was 13.1%. Conclusion: Standard clinical examinations can be employed to identify suspect paraneoplastic stroke with an adequate sensitivity, specificity, and PPV when it is considered that the association of ischemic stroke with breast and prostate cancers in the stroke-prone elderly population might be largely incidental.

TUBA4A downregulation as observed in ALS post-mortem motor cortex causes ALS-related abnormalities in zebrafish.

Disease-associated variants of TUBA4A (alpha-tubulin 4A) have recently been identified in familial ALS. Interestingly, a downregulation of TUBA4A protein expression was observed in familial as well as sporadic ALS brain tissue. To investigate whether a decreased TUBA4A expression could be a driving factor in ALS pathogenesis, we assessed whether TUBA4A knockdown in zebrafish could recapitulate an ALS-like phenotype. For this, we injected an antisense oligonucleotide morpholino in zebrafish embryos targeting the zebrafish TUBA4A orthologue. An antibody against synaptic vesicle 2 was used to visualize motor axons in the spinal cord, allowing the analysis of embryonic ventral root projections. Motor behavior was assessed using the touch-evoked escape response. In post-mortem ALS motor cortex, we observed reduced TUBA4A levels. The knockdown of the zebrafish TUBA4A orthologue induced a motor axonopathy and a significantly disturbed motor behavior. Both phenotypes were dose-dependent and could be rescued by the addition of human wild-type TUBA4A mRNA. Thus, TUBA4A downregulation as observed in ALS post-mortem motor cortex could be modeled in zebrafish and induced a motor axonopathy and motor behavior defects reflecting a motor neuron disease phenotype, as previously described in embryonic zebrafish models of ALS. The rescue with human wild-type TUBA4A mRNA suggests functional conservation and strengthens the causal relation between TUBA4A protein levels and phenotype severity. Furthermore, the loss of TUBA4A induces significant changes in post-translational modifications of tubulin, such as acetylation, detyrosination and polyglutamylation. Our data unveil an important role for TUBA4A in ALS pathogenesis, and extend the relevance of TUBA4A to the majority of ALS patients, in addition to cases bearing TUBA4A mutations.

AI-assisted automatic MRI-based tongue volume evaluation in motor neuron disease (MND).

PURPOSE: Motor neuron disease (MND) causes damage to the upper and lower motor neurons including the motor cranial nerves, the latter resulting in bulbar involvement with atrophy of the tongue muscle. To measure tongue atrophy, an operator independent automatic segmentation of the tongue is crucial. The aim of this study was to apply convolutional neural network (CNN) to MRI data in order to determine the volume of the tongue. METHODS: A single triplanar CNN of U-Net architecture trained on axial, coronal, and sagittal planes was used for the segmentation of the tongue in MRI scans of the head. The 3D volumes were processed slice-wise across the three orientations and the predictions were merged using different voting strategies. This approach was developed using MRI datasets from 20 patients with 'classical' spinal amyotrophic lateral sclerosis (ALS) and 20 healthy controls and, in a pilot study, applied to the tongue volume quantification to 19 controls and 19 ALS patients with the variant progressive bulbar palsy (PBP). RESULTS: Consensus models with softmax averaging and majority voting achieved highest segmentation accuracy and outperformed predictions on single orientations and consensus models with union and unanimous voting. At the group level, reduction in tongue volume was not observed in classical spinal ALS, but was significant in the PBP group, as compared to controls. CONCLUSION: Utilizing single U-Net trained on three orthogonal orientations with consequent merging of respective orientations in an optimized consensus model reduces the number of erroneous detections and improves the segmentation of the tongue. The CNN-based automatic segmentation allows for accurate quantification of the tongue volumes in all subjects. The application to the ALS variant PBP showed significant reduction of the tongue volume in these patients and opens the way for unbiased future longitudinal studies in diseases affecting tongue volume.

The central pattern of weakness of ALS: Morphological correlates in whole-body muscle MRI.

OBJECTIVE: Monosynaptically cortically innervated α-motoneurons are early and strongly involved in amyotrophic lateral sclerosis (ALS). Consequently, the muscles that receive the strongest direct corticomotoneuronal input are the clinically most affected. To objectify this concept in vivo through morphological image correlates, whole-body magnetic resonance imaging (MRI) with muscle signal analysis was performed in patients with ALS compared to healthy controls. METHODS: Modified Dixon-based whole-body MRI was acquired in patients with ALS (n = 33) and matched healthy controls (n = 30). Manual labeling of limb muscle MRI was performed, and a specific subset of nine muscles, selected as pairs of muscle groups with different corticomotoneuronal input, was analyzed per subject based on their volume, fat fraction, and functional remaining muscle area (fRMA). RESULTS: Statistical analysis of 978 muscles in total revealed significantly decreased volumes, decreased fRMA, and increased fat fraction in the muscles of patients with ALS compared to controls. The clinical degree of pareses of directly innervated muscles was significantly worse than that of less directly innervated muscles in each comparison. The muscles receiving stronger direct corticomotoneuronal input showed more pronounced morphological involvement compared to those with less monosynaptic corticomotoneuronal input (fRMA, significant in three pairwise comparisons). INTERPRETATION: In conclusion, whole-body MRI-based muscle analysis provided additional evidence for a characteristic pattern of pareses in ALS. This technical approach (parameterization and quantification of muscle alterations from MRI) to patients with ALS could pave the way for the future establishment of a diagnostic algorithm of muscle MRI for ALS and may serve as a biomarker.

Quantification of blood glial fibrillary acidic protein using a second-generation microfluidic assay. Validation and comparative analysis with two established assays.

OBJECTIVES: Increased levels of glial fibrillary acidic protein (GFAP) in blood have been identified as a valuable biomarker for some neurological disorders, such as Alzheimer's disease and multiple sclerosis. However, most blood GFAP quantifications so far were performed using the same bead-based assay, and to date a routine clinical application is lacking. METHODS: In this study, we validated a novel second-generation (2nd gen) Ella assay to quantify serum GFAP. Furthermore, we compared its performance with a bead-based single molecule array (Simoa) and a homemade GFAP assay in a clinical cohort of neurological diseases, including 210 patients. RESULTS: Validation experiments resulted in an intra-assay variation of 10 %, an inter-assay of 12 %, a limit of detection of 0.9 pg/mL, a lower limit of quantification of 2.8 pg/mL, and less than 20 % variation in serum samples exposed to up to five freeze-thaw cycles, 120 h at 4 °C and room temperature. Measurement of the clinical cohort using all assays revealed the same pattern of GFAP distribution in the different diagnostic groups. Moreover, we observed a strong correlation between the 2nd gen Ella and Simoa (r=0.91 (95 % CI: 0.88-0.93), p<0.0001) and the homemade immunoassay (r=0.77 (95 % CI: 0.70-0.82), p<0.0001). CONCLUSIONS: Our results demonstrate a high reliability, precision and reproducibility of the 2nd gen Ella assay. Although a higher assay sensitivity for Simoa was observed, the new microfluidic assay might have the potential to be used for GFAP analysis in daily clinical workups due to its robustness and ease of use.

Primary lateral sclerosis: application and validation of the 2020 consensus diagnostic criteria in an expert opinion-based PLS cohort.

BACKGROUND: Validation of the 2020 consensus criteria for primary lateral sclerosis (PLS) is essential for their use in clinical practice and future trials. METHODS: In a large cohort of patients diagnosed with PLS by expert opinion prior to the new criteria with detailed clinical baseline evaluation (n=107) and longitudinal follow-up (n=63), we applied the new diagnostic criteria and analysed the clinical phenotype, electromyography (EMG), diagnostic accuracy and prognosis, adding neurofilaments and MRI as potential biomarkers. RESULTS: The criteria for definite PLS were met by 28% and those for probable PLS by 19%, whereas 53% did not meet the full criteria at baseline, mainly due to the time, EMG and region criteria. Patients not meeting the criteria had less generalised upper motor neuron involvement but were otherwise similar in demographic and clinical characteristics. All patients with definite and probable PLS maintained PLS diagnosis during follow-up, while four patients not meeting the criteria developed clinical lower motor neuron involvement. Definite PLS cases showed improved survival compared with probable PLS and patients who did not meet the criteria. Despite a clinical PLS phenotype, fibrillation potentials/positive sharp waves and fasciculations in one or more muscles were a frequent EMG finding, with the extent and prognostic significance depending on disease duration. Serum neurofilament light and a multiparametric MRI fibre integrity Z-score correlated with clinical parameters and were identified as potential biomarkers. CONCLUSION: Validation of the 2020 PLS consensus criteria revealed high diagnostic certainty and prognostic significance, supporting their value for research and clinical practice.

In-depth analysis of data from the RAS-ALS study reveals new insights in rasagiline treatment for amyotrophic lateral sclerosis.

BACKGROUND AND PURPOSE: In 2016, we concluded a randomized controlled trial testing 1 mg rasagiline per day add-on to standard therapy in 252 amyotrophic lateral sclerosis (ALS) patients. This article aims at better characterizing ALS patients who could possibly benefit from rasagiline by reporting new subgroup analysis and genetic data. METHODS: We performed further exploratory in-depth analyses of the study population and investigated the relevance of single nucleotide polymorphisms (SNPs) related to the dopaminergic system. RESULTS: Placebo-treated patients with very slow disease progression (loss of Amyotrophic Lateral Sclerosis Functional Rating Scale-Revised [ALSFRS-R] per month before randomization of ≤0.328 points) showed a per se survival probability after 24 months of 0.85 (95% confidence interval = 0.65-0.94). The large group of intermediate to fast progressing ALS patients showed a prolonged survival in the rasagiline group compared to placebo after 6 and 12 months (p = 0.02, p = 0.04), and a reduced decline of ALSFRS-R after 18 months (p = 0.049). SNP genotypes in the MAOB gene and DRD2 gene did not show clear associations with rasagiline treatment effects. CONCLUSIONS: These results underline the need to consider individual disease progression at baseline in future ALS studies. Very slow disease progressors compromise the statistical power of studies with treatment durations of 12-18 months using clinical endpoints. Analysis of MAOB and DRD2 SNPs revealed no clear relationship to any outcome parameter. More insights are expected from future studies elucidating whether patients with DRD2CC genotype (Rs2283265) show a pronounced benefit from treatment with rasagiline, pointing to the opportunities precision medicine could open up for ALS patients in the future.

One third of physicians discuss exit strategies with patients with amyotrophic lateral sclerosis: Results from nationwide surveys among German and Polish neurologists.

OBJECTIVE: This paper examines neurologists' approaches to exit strategies (ESs), such as euthanasia and physician-assisted suicide, in patients with amyotrophic lateral sclerosis (PALS) in two European countries. METHODS: In a nationwide anonymous survey, we collected responses from 237 Polish and 228 German neurologists, focusing on their practices and beliefs about ESs, as well as their viewpoints on life-sustaining measures (LSMs) (percutaneous endoscopic gastrostomy, non-invasive, and invasive ventilation). To analyze the data, we employed statistical methods, including Mann-Whitney U, Kruskal-Wallis, chi-square tests, Spearman's rank correlation, and multiple regression analysis. RESULTS: One third of the neurologists initiated the discussion about ESs with PALS. Half were ready to have this conversation upon patient's request. Age, gender, religiousness, and nationality were closely associated with this approach. One in 9 neurologists received a request to terminate an LSM, whereas 1 in 10 to implement an ES. German neurologists and palliative care trainees acquired both demands more commonly. Neurologists quoted a low quality of life, decreased mood, and being a burden to the family/closest ones as primary reasons for a wish to hasten death among PALS. Although the majority expressed a willingness to terminate an LSM at a request of the patient, most opposed the legalization of euthanasia. Younger and less religious individuals were more likely to favor accepting euthanasia. CONCLUSION: Neurologists vary significantly in their approaches to terminal care. Complex relationships exist among personal indices, shared beliefs, and current practices.

Longitudinal course of neurofilament light chain levels in amyotrophic lateral sclerosis-insights from a completed randomized controlled trial with rasagiline.

BACKGROUND AND PURPOSE: Rasagiline might be disease modifying in patients with amyotrophic lateral sclerosis (ALS). The aim was to evaluate the effect of rasagiline 2 mg/day on neurofilament light chain (NfL), a prognostic biomarker in ALS. METHODS: In 65 patients with ALS randomized in a 3:1 ratio to rasagiline 2 mg/day (n = 48) or placebo (n = 17) in a completed randomized controlled multicentre trial, NfL levels in plasma were measured at baseline, month 6 and month 12. Longitudinal changes in NfL levels were evaluated regarding treatment and clinical parameters. RESULTS: Baseline NfL levels did not differ between the study arms and correlated with disease progression rates both pre-baseline (r = 0.64, p < 0.001) and during the study (r = 0.61, p < 0.001). NfL measured at months 6 and 12 did not change significantly from baseline in both arms, with a median individual NfL change of +1.4 pg/mL (interquartile range [IQR] -5.6, 14.2) across all follow-up time points. However, a significant difference in NfL change at month 12 was observed between patients with high and low NfL baseline levels treated with rasagiline (high [n = 13], -6.9 pg/mL, IQR -20.4, 6.0; low [n = 18], +5.9 pg/mL, IQR -1.4, 19.7; p = 0.025). Additionally, generally higher longitudinal NfL variability was observed in patients with high baseline levels, whereas disease progression rates and disease duration at baseline had no impact on the longitudinal NfL course. CONCLUSION: Post hoc NfL measurements in completed clinical trials are helpful in interpreting NfL data from ongoing and future interventional trials and could provide hypothesis-generating complementary insights. Further studies are warranted to ultimately differentiate NfL response to treatment from other factors.

Neurological manifestation of HEV infection: still a rare disease entity?

Hepatitis E virus (HEV) infection is the most common form of viral hepatitis and is reported to cause neurological manifestation in up to 30% of diagnosed infections. We evaluated the medical reports of all patients (n = 29,994) who were discharged from the Department of Neurology of Ulm University between 01.01.2015 and 30.09.2022 to detect neurological manifestations of HEV. In addition, we retrospectively analyzed the serum samples of n = 99 patients representing different neurological diseases possibly related to HEV for anti-HEV-IgM and anti-HEV-IgG. At the time of discharge from hospital, the etiology of neurological symptoms in these patients was unclear. Overall, five cases of extrahepatic neurological manifestation of HEV (defined as anti-HEV-IgM and HEV-IgG positive) could be detected. An increase of both, anti-IgM- and anti-IgG-serum levels was significantly more common in neuralgic amyotrophy/plexus neuritis/radiculitis than in AIDP/CIDP (P = 0.01), meningitis/encephalitis (P = 0.02), idiopathic peripheral facial paralysis (P = 0.02) and tension headache (P = 0.02). In 15% (n = 15 out of 99) of retrospectively analyzed serum samples, conspicuous positive anti-HEV-IgG levels were detected. This finding was most common in AIDP/CIDP. In conclusion, results of this study indicate neurological manifestation of HEV to be a rare but still underestimated course of disease, occurring at any age and gender. Therefore, testing for HEV should be considered in patients with neurological symptoms of unknown origin, especially in those with neuralgic amyotrophy/plexus neuritis.

Patient-reported outcome parameters and disability worsening in progressive multiple sclerosis.

OBJECTIVES: Detection and prediction of disability progression is a significant unmet need in people with progressive multiple sclerosis (PwPMS). Government and health agencies have deemed the use of patient-reported outcomes measurements (PROMs) in clinical practice and clinical trials a major strategic priority. Nevertheless, data documenting the clinical utility of PROMs in neurological diseases is scarce. This study evaluates if assessment of PROMs could track progression in PwPMS. METHODS: Emerging blood Biomarkers in Progressive Multiple Sclerosis (EmBioProMS) investigated PROMs (Beck depression inventory-II (BDI-II), multiple sclerosis impact scale-29 (MSIS-29), fatigue scale for motor and cognition (FSMC)) in PwPMS (primary [PPMS] and secondary progressive MS [SPMS]). PROMs were evaluated longitudinally and compared between participants with disability progression (at baseline; retrospective evidence of disability progression (EDP), and during follow up (FU); prospective evidence of confirmed disability progression (CDP)) and those without progression. In an independent cohort of placebo participants of the phase III ORATORIO trial in PPMS, the diagnostic and prognostic value of another PROMs score (36-Item Short Form Survey [SF-36]) regarding CDP was evaluated. RESULTS: EmBioProMS participants with EDP in the two years prior to inclusion (n = 136/227), or who suffered from CDP during FU (number of events= 88) had worse BDI-II, MSIS-29, and FSMC scores compared to PwPMS without progression. In addition, baseline MSIS29physical above 70th, 80th, and 90th percentiles predicted future CDP/ progression independent of relapse activity in EmBioProMS PPMS participants (HR of 3.7, 6.9, 6.7, p = 0.002, <0.001, and 0.001, respectively). In the placebo arm of ORATORIO (n = 137), the physical component score (PCS) of SF-36 worsened at week 120 compared to baseline, in cases who experienced progression over the preceding trial period (P = 0.018). Worse PCS at baseline was associated with higher hazard ratios of disability accumulation over the subsequent 120 weeks (HR: 2.01 [30th-], 2.11 [20th-], and 2.8 [10th percentile], P = 0.007, 0.012 and 0.005, respectively). CONCLUSIONS: PROMs could provide additional, practical, cost-efficient, and remotely accessible insight about disability progression in PMS through standardized, structured, and quantifiable patient feedback.

Serum glial fibrillary acidic protein and disability progression in progressive multiple sclerosis.

OBJECTIVE: Progression prediction is a significant unmet need in people with progressive multiple sclerosis (pwPMS). Studies on glial fibrillary acidic protein (GFAP) have either been limited to single center with relapsing MS or were based solely on Expanded Disability Status Scale (EDSS), which limits its generalizability to state-of-the-art clinical settings and trials applying combined outcome parameters. METHODS: Serum GFAP and NfL (neurofilament light chain) were investigated in EmBioProMS participants with primary (PP) or secondary progressive MS. Six months confirmed disability progression (CDP) was defined using combined outcome parameters (EDSS, timed-25-foot walk test (T25FW), and nine-hole-peg-test (9HPT)). RESULTS: 243 subjects (135 PPMS, 108 SPMS, age 55.5, IQR [49.7-61.2], 135 female, median follow-up: 29.3 months [17.9-40.9]) were included. NfL (age-) and GFAP (age- and sex-) adjusted Z scores were higher in pwPMS compared to HC (p < 0.001 for both). 111 (32.8%) CDP events were diagnosed in participants with ≥3 visits (n = 169). GFAP Z score >3 was associated with higher risk for CDP in participants with low NfL Z score (i.e., ≤1.0) (HR: 2.38 [1.12-5.08], p = 0.025). In PPMS, GFAP Z score >3 was associated with higher risk for CDP (HR: 2.88 [1.21-6.84], p = 0.016). Risk was further increased in PPMS subjects with high GFAP when NfL is low (HR: 4.31 [1.53-12.13], p = 0.006). INTERPRETATION: Blood GFAP may help identify pwPPMS at risk of progression. Combination of high GFAP and low NfL levels could distinguish non-active pwPMS with particularly high progression risk.

AI-assisted quantification of hypothalamic atrophy in amyotrophic lateral sclerosis by convolutional neural network-based automatic segmentation.

The hypothalamus is a small structure of the brain with an essential role in metabolic homeostasis, sleep regulation, and body temperature control. Some neurodegenerative diseases such as amyotrophic lateral sclerosis (ALS) and dementia syndromes are reported to be related to hypothalamic volume alterations. Despite its crucial role in human body regulation, neuroimaging studies of this structure are rather scarce due to work-intensive operator-dependent manual delineations from MRI and lack of automated segmentation tools. In this study we present a fully automatic approach based on deep convolutional neural networks (CNN) for hypothalamic segmentation and volume quantification. We applied CNN of U-Net architecture with EfficientNetB0 backbone to allow for accurate automatic hypothalamic segmentation in seconds on a GPU. We further applied our approach for the quantification of the normalized hypothalamic volumes to a large neuroimaging dataset of 432 ALS patients and 112 healthy controls (without the ground truth labels). Using the automated volumetric analysis, we could reproduce hypothalamic atrophy findings associated with ALS by detecting significant volume differences between ALS patients and controls at the group level. In conclusion, a fast and unbiased AI-assisted hypothalamic quantification method is introduced in this study (whose acceptance rate based on the outlier removal strategy was estimated to be above 95%) and made publicly available for researchers interested in the conduction of hypothalamus studies at a large scale.