Assessing CT-based Volumetric Analysis via Transfer Learning with MRI and Manual Labels for Idiopathic Normal Pressure Hydrocephalus.

Background: Brain computed tomography (CT) is an accessible and commonly utilized technique for assessing brain structure. In cases of idiopathic normal pressure hydrocephalus (iNPH), the presence of ventriculomegaly is often neuroradiologically evaluated by visual rating and manually measuring each image. Previously, we have developed and tested a deep-learning-model that utilizes transfer learning from magnetic resonance imaging (MRI) for CT-based intracranial tissue segmentation. Accordingly, herein we aimed to enhance the segmentation of ventricular cerebrospinal fluid (VCSF) in brain CT scans and assess the performance of automated brain CT volumetrics in iNPH patient diagnostics. Methods: The development of the model used a two-stage approach. Initially, a 2D U-Net model was trained to predict VCSF segmentations from CT scans, using paired MR-VCSF labels from healthy controls. This model was subsequently refined by incorporating manually segmented lateral CT-VCSF labels from iNPH patients, building on the features learned from the initial U-Net model. The training dataset included 734 CT datasets from healthy controls paired with T1-weighted MRI scans from the Gothenburg H70 Birth Cohort Studies and 62 CT scans from iNPH patients at Uppsala University Hospital. To validate the model's performance across diverse patient populations, external clinical images including scans of 11 iNPH patients from the Universitatsmedizin Rostock, Germany, and 30 iNPH patients from the University of Alabama at Birmingham, United States were used. Further, we obtained three CT-based volumetric measures (CTVMs) related to iNPH. Results: Our analyses demonstrated strong volumetric correlations (ϱ=0.91, p<0.001) between automatically and manually derived CT-VCSF measurements in iNPH patients. The CTVMs exhibited high accuracy in differentiating iNPH patients from controls in external clinical datasets with an AUC of 0.97 and in the Uppsala University Hospital datasets with an AUC of 0.99. Discussion: CTVMs derived through deep learning, show potential for assessing and quantifying morphological features in hydrocephalus. Critically, these measures performed comparably to gold-standard neuroradiology assessments in distinguishing iNPH from healthy controls, even in the presence of intraventricular shunt catheters. Accordingly, such an approach may serve to improve the radiological evaluation of iNPH diagnosis/monitoring (i.e., treatment responses). Since CT is much more widely available than MRI, our results have considerable clinical impact.

Higher levels of neurofilament light chain and total tau in CSF are associated with negative outcome after shunt surgery in patients with normal pressure hydrocephalus.

BACKGROUND: Lumbar punctures are a common examination in the work-up of patients with idiopathic normal pressure hydrocephalus (iNPH) and cerebrospinal fluid (CSF) biomarkers should therefore be available for use in selection of shunt candidates. The aim of this study was to investigate if CSF biomarkers are associated with outcome after shunt surgery alone or in combination with comorbidity and imaging markers, and investigate associations between CSF biomarkers and symptoms. METHODS: Preoperative CSF biomarkers were analyzed in 455 patients operated with shunt surgery for iNPH at a single center during 2011-2018. Symptoms before and 12 months after shunt surgery were graded with the Swedish iNPH scale. Neurofilament light chain protein (NfL), total tau (T-tau), phosphorylated tau (P-tau) and amyloid beta1-42 (Aß1-42) CSF levels were measured. Evans' index and disproportionately enlarged subarachnoid space hydrocephalus were measured on preoperative CT-scans. Preoperative evaluation and follow-up 12 months after shunt surgery were available in 376 patients. RESULTS: Higher levels of NfL and T-tau were associated with less improvement after shunt surgery (ß = - 3.10, p = 0.016 and ß = - 2.45, p = 0.012, respectively). Patients whose symptoms deteriorated after shunt surgery had higher preoperative levels of NfL (1250 ng/L [IQR:1020-2220] vs. 1020 [770-1649], p < 0.001) and T-tau (221 ng/L [IQR: 159-346] vs. 190 [135-261], p = 0.0039) than patients with postoperative improvement on the iNPH scale. Among the patients who improved ≥ 5 levels on the iNPH scale (55%), NfL was abnormal in 22%, T-tau in 14%, P-tau in 6% and Aß1-42 in 45%, compared with normal reference limits. The inclusion of CSF biomarkers, imaging markers and comorbidity in multivariate predictive Orthogonal Projections to Latent Structures (OPLS) models to did not improve predictability in outcome after shunt surgery. CONCLUSIONS: Higher levels of T-tau and NfL were associated with a less favorable response to shunt surgery, suggesting a more active neurodegeneration in this group of patients. However, CSF levels of these biomarkers can be elevated also in patients who respond to shunt surgery. Thus, none of these CSF biomarkers, alone or used in combination, are suitable for excluding patients from surgery.

Comparison of Semi-Quantitative Scoring and Artificial Intelligence Aided Digital Image Analysis of Chromogenic Immunohistochemistry.

Semi-quantitative scoring is a method that is widely used to estimate the quantity of proteins on chromogen-labelled immunohistochemical (IHC) tissue sections. However, it suffers from several disadvantages, including its lack of objectivity and the fact that it is a time-consuming process. Our aim was to test a recently established artificial intelligence (AI)-aided digital image analysis platform, Pathronus, and to compare it to conventional scoring by five observers on chromogenic IHC-stained slides belonging to three experimental groups. Because Pathronus operates on grayscale 0-255 values, we transformed the data to a seven-point scale for use by pathologists and scientists. The accuracy of these methods was evaluated by comparing statistical significance among groups with quantitative fluorescent IHC reference data on subsequent tissue sections. The pairwise inter-rater reliability of the scoring and converted Pathronus data varied from poor to moderate with Cohen's kappa, and overall agreement was poor within every experimental group using Fleiss' kappa. Only the original and converted that were obtained from Pathronus original were able to reproduce the statistical significance among the groups that were determined by the reference method. In this study, we present an AI-aided software that can identify cells of interest, differentiate among organelles, protein specific chromogenic labelling, and nuclear counterstaining after an initial training period, providing a feasible and more accurate alternative to semi-quantitative scoring.

Dementia with Lewy bodies - a clinicopathological update.

Dementia is one of the major burdens of our aging society. According to certain predictions, the number of patients will double every 20 years. Although Alzheimer's disease (AD), as the most frequent neurodegenerative dementia, has been extensively analysed, less is known about dementia with Lewy bodies (DLB). Neuropathological hallmarks of DLB are the deposition of intracellular Lewy bodies (LB) and Lewy neurites (LN). DLB belongs to the α-synucleinopathies, as the major component of these inclusions is pathologically aggregated α-synuclein. Depending on the localisation of LBs and LNs in the central nervous system cognitive and motor symptoms can occur. In our work, we will systematically review the possible etiology and epidemiology, pathological (both macroscopic and microscopic) features, structural and functional imaging findings, with a special emphasis on the clinico-pathological correlations. Finally, we summarize the latest clinical symptoms-based diagnostic criteria and the novel therapeutic approaches. Since DLB is frequently accompanied with AD pathology, highlighting possible differential diagnostic approaches is an integral part of our paper. Although our present knowledge is insufficient, the rapid development of diagnostic and research methods provide hope for better diagnosis and more efficient treatment, contributing to a better quality of life.

Biological function of Lemur tyrosine kinase 2 (LMTK2): implications in neurodegeneration.

Neurodegenerative disorders are frequent, incurable diseases characterised by abnormal protein accumulation and progressive neuronal loss. Despite their growing prevalence, the underlying pathomechanism remains unclear. Lemur tyrosine kinase 2 (LMTK2) is a member of a transmembrane serine/threonine-protein kinase family. Although it was described more than a decade ago, our knowledge on LMTK2's biological functions is still insufficient. Recent evidence has suggested that LMTK2 is implicated in neurodegeneration. After reviewing the literature, we identified three LMTK2-mediated mechanisms which may contribute to neurodegenerative processes: disrupted axonal transport, tau hyperphosphorylation and enhanced apoptosis. Moreover, LMTK2 gene expression is decreased in an Alzheimer's disease mouse model. According to these features, LMTK2 might be a promising therapeutic target in near future. However, further investigations are required to clarify the exact biological functions of this unique protein.