Automated and manual hippocampal segmentation techniques: Comparison of results, reproducibility and clinical applicability

Hippocampal subfield volumes in mild cognitive impairment and alzheimer's disease: a systematic review and meta-analysis

The hippocampus is a complex structure that consists of several subfields with distinct and specialized functions. Although numerous studies have been performed to explore hippocampal atrophy at the sub-regional level in mild cognitive impairment (MCI) and Alzheimer's disease (AD), the results have been inconsistent especially for whether and which subfields can be served as the most potential biomarkers in MCI and AD. Herein, we used a meta-analytic approach to synthesize the extant literatures on hippocampal subfields in MCI and AD through PubMed, Web of Science, and Embase (PROSPERO CRD42021257586). As a result, a total of twenty studies using Freesurfer 5 and Freesurfer 6 were included in this investigation. These studies revealed that at the sub-regional level, hippocampal subfield volume reductions in MCI and AD were not restricted to specific subfields, and subiculum and presubiculum had the largest z-scores across most comparisons. However, none of the subfield performed much better in discriminating MCI and HC, AD and MCI, AD and HC as compared to whole hippocampus volume. These results suggested that we should explore the changes in the hippocampal subfields in subtypes of MCI or even at an earlier stage, that is subjective cognitive impairment.

Automated identification of piglet brain tissue from MRI images using Region-based Convolutional Neural Networks

Magnetic resonance imaging is an important tool for characterizing volumetric changes of the piglet brain during development. Typically, an early step of an imaging analysis pipeline is brain extraction, or skull stripping. Brain extractions are usually performed manually; however, this approach is time-intensive and can lead to variation between brain extractions when multiple raters are used. Automated brain extractions are important for reducing the time required for analyses and improving the uniformity of the extractions. Here we demonstrate the use of Mask R-CNN, a Region-based Convolutional Neural Network (R-CNN), for automated brain extractions of piglet brains. We validate our approach using Nested Cross-Validation on six sets of training/validation data drawn from 32 pigs. Visual inspection of the extractions shows acceptable accuracy, Dice coefficients are in the range of 0.95-0.97, and Hausdorff Distance values in the range of 4.1-8.3 voxels. These results demonstrate that R-CNNs provide a viable tool for skull stripping of piglet brains.

Diagnostic Utility of Hippocampal Volumetric Data in a Memory Disorder Clinic Setting

BACKGROUND

Hippocampal volumetric data are widely used in research but are rarely examined in clinical populations in regard to aiding diagnosis or correlating with objective memory test scores.

OBJECTIVE

To replicate and expand on the few prior clinical examinations of the utility of hippocampal volumetric data. We evaluated MRI volumetric data to determine (a) the degree of hippocampal loss across diagnostic groups compared with a cognitively intact group, (b) if total or lateralized hippocampal volumes predict diagnostic group membership, and (c) how total and lateralized volumes correlate with memory tests.

METHOD

We retrospectively examined hippocampal volumetric data and memory test scores for 294 individuals referred to a memory clinic.

RESULTS

Individuals with mild cognitive impairment or Alzheimer disease had smaller hippocampal volumes compared with cognitively intact individuals. The raw and normalized total and lateralized hippocampal volumes were essentially equal for predicting diagnostic group membership, and notably low hippocampal volumes evidenced greater specificity than sensitivity. All of the volumetric data correlated with the memory test scores, with the total and left hippocampal volumes accounting for the slightly more variance in the diagnostic groups.

CONCLUSION

The diagnostic groups exhibited hippocampal volume loss, which can be a potential biomarker for neurodegenerative disease in clinical practice. However, solely using hippocampal volumetric data to predict diagnostic group membership or memory test failure was not supported. While extreme hippocampal volume loss was rare in the cognitively intact group, the sensitivity of these volumetric data suggests a need for supplementation by other tools when making a diagnosis.

Altered Hippocampal Resting-state Functional Connectivity in Highly Superior Autobiographical Memory

Individuals with Highly Superior Autobiographical Memory (HSAM) provide the opportunity to investigate the neurobiological substrates of enhanced memory performance. While previous studies started to assess the neural correlates of memory retrieval in HSAM, here we assessed for the first time the intrinsic connectivity of a core memory region, the hippocampus, with the whole brain, in 8 HSAM subjects (HSAMs) and 21 controls during resting-state functional neuroimaging. We found in HSAMs vs. controls disrupted hippocampal resting-state functional connectivity (rsFC) with high-level control regions belonging to the saliency network (the anterior cingulate cortex and the left and right insulae), and to the ventral fronto-parietal attentional network (the temporo-parietal junction and the inferior frontal gyrus), also involved with salience detection. Conversely, HSAMs showed enhanced hippocampal rsFC with sensory regions along the fusiform gyrus and the inferior temporal cortex. This altered pattern of hippocampal rsFC might be interpreted as a reduced capability of HSAMs to discriminate and select salient information, with a subsequent increase in the probability to encode and consolidate sensory information irrespective of their task-relevancy. Ultimately, these findings provide evidence that HSAM might be paradoxically enabled by an altered hippocampal rsFC that bypasses regions involved with salience detection in favor of specialized sensory regions.

Deep Learning Segmentation of Triple-Negative Breast Cancer (TNBC) Patient Derived Tumor Xenograft (PDX) and Sensitivity of Radiomic Pipeline to Tumor Probability Boundary

Simple Summary

Co-clinical trials are an emerging area of investigation in which a clinical trial is coupled with a corresponding preclinical trial to inform the corresponding clinical trial. The preclinical arm aids in assessing therapeutic efficacy, patient stratification, and designing optimal imaging strategies. There is much interest in harmonizing preclinical and clinical quantitative imaging pipelines. Radiomics is widely explored in clinical imaging to predict response to therapy. In preclinical imaging, high-throughput radiomic analysis is limited by manual delineation of tumor boundaries, which is labor intensive with poor reproducibility. Our proposed deep-learning-based system was trained to automatically segment tumors from multi-contrast MR images and extract radiomic features. The proposed method is highly reproducible with significant correlation in radiomic features. The deployment of this pipeline in the preclinical arm would provide high throughput and reproducible radiomic analysis.

Abstract

Preclinical magnetic resonance imaging (MRI) is a critical component in a co-clinical research pipeline. Importantly, segmentation of tumors in MRI is a necessary step in tumor phenotyping and assessment of response to therapy. However, manual segmentation is time-intensive and suffers from inter- and intra- observer variability and lack of reproducibility. This study aimed to develop an automated pipeline for accurate localization and delineation of TNBC PDX tumors from preclinical T1w and T2w MR images using a deep learning (DL) algorithm and to assess the sensitivity of radiomic features to tumor boundaries. We tested five network architectures including U-Net, dense U-Net, Res-Net, recurrent residual UNet (R2UNet), and dense R2U-Net (D-R2UNet), which were compared against manual delineation by experts. To mitigate bias among multiple experts, the simultaneous truth and performance level estimation (STAPLE) algorithm was applied to create consensus maps. Performance metrics (F1-Score, recall, precision, and AUC) were used to assess the performance of the networks. Multi-contrast D-R2UNet performed best with F1-score = 0.948; however, all networks scored within 1–3% of each other. Radiomic features extracted from D-R2UNet were highly corelated to STAPLE-derived features with 67.13% of T1w and 53.15% of T2w exhibiting correlation ρ ≥ 0.9 (p ≤ 0.05). D-R2UNet-extracted features exhibited better reproducibility relative to STAPLE with 86.71% of T1w and 69.93% of T2w features found to be highly reproducible (CCC ≥ 0.9, p ≤ 0.05). Finally, 39.16% T1w and 13.9% T2w features were identified as insensitive to tumor boundary perturbations (Spearman correlation (−0.4 ≤ ρ ≤ 0.4). We developed a highly reproducible DL algorithm to circumvent manual segmentation of T1w and T2w MR images and identified sensitivity of radiomic features to tumor boundaries.

Diagnostic Performance of Automated MRI Volumetry by icobrain dm for Alzheimer's Disease in a Clinical Setting: A REMEMBER Study

Background:

Magnetic resonance imaging (MRI) has become important in the diagnostic work-up of neurodegenerative diseases. icobrain dm, a CE-labeled and FDA-cleared automated brain volumetry software, has shown potential in differentiating cognitively healthy controls (HC) from Alzheimer’s disease (AD) dementia (ADD) patients in selected research cohorts.

Objective:

This study examines the diagnostic value of icobrain dm for AD in routine clinical practice, including a comparison to the widely used FreeSurfer software, and investigates if combined brain volumes contribute to establish an AD diagnosis.

Methods:

The study population included HC (n = 90), subjective cognitive decline (SCD, n = 93), mild cognitive impairment (MCI, n = 357), and ADD (n = 280) patients. Through automated volumetric analyses of global, cortical, and subcortical brain structures on clinical brain MRI T1w (n = 820) images from a retrospective, multi-center study (REMEMBER), icobrain dm’s (v.4.4.0) ability to differentiate disease stages via ROC analysis was compared to FreeSurfer (v.6.0). Stepwise backward regression models were constructed to investigate if combined brain volumes can differentiate between AD stages.

Results:

icobrain dm outperformed FreeSurfer in processing time (15–30 min versus 9–32 h), robustness (0 versus 67 failures), and diagnostic performance for whole brain, hippocampal volumes, and lateral ventricles between HC and ADD patients. Stepwise backward regression showed improved diagnostic accuracy for pairwise group differentiations, with highest performance obtained for distinguishing HC from ADD (AUC = 0.914; Specificity 83.0%; Sensitivity 86.3%).

Conclusion:

Automated volumetry has a diagnostic value for ADD diagnosis in routine clinical practice. Our findings indicate that combined brain volumes improve diagnostic accuracy, using real-world imaging data from a clinical setting.

Inflammation, hippocampal volume, and cognition in schizophrenia: results from the Northern Finland Birth Cohort 1966

Increased blood interleukin-6 (IL-6) levels are a replicated abnormality in schizophrenia, and may be associated with smaller hippocampal volumes and greater cognitive impairment. These findings have not been investigated in a population-based birth cohort. The general population Northern Finland Birth Cohort 1966 was followed until age 43. Subjects with schizophrenia were identified through the national Finnish Care Register. Blood IL-6 levels were measured in n = 82 subjects with schizophrenia and n = 5373 controls at age 31. Additionally, 31 patients with schizophrenia and 63 healthy controls underwent brain structural MRI at age 34, and cognitive testing at ages 34 and 43. Patients with schizophrenia had significantly higher median (interquartile range) blood IL-6 levels than controls (5.31, 0.85-17.20, versus 2.42, 0.54-9.36, p = 0.02) after controlling for potential confounding factors. In both schizophrenia and controls, higher blood IL-6 levels were predictors of smaller hippocampal volumes, but not cognitive performance at age 34. We found evidence for increased IL-6 levels in patients with midlife schizophrenia from a population-based birth cohort, and replicated associations between IL-6 levels and hippocampal volumes. Our results complement and extend the previous findings, providing additional evidence that IL-6 may play a role in the pathophysiology of schizophrenia and associated brain alterations.

Imaging Techniques in Alzheimer's Disease: A Review of Applications in Early Diagnosis and Longitudinal Monitoring

BACKGROUND

Alzheimer's disease (AD) is a progressive neurodegenerative disorder affecting many individuals worldwide with no effective treatment to date. AD is characterized by the formation of senile plaques and neurofibrillary tangles, followed by neurodegeneration, which leads to cognitive decline and eventually death.

INTRODUCTION

In AD, pathological changes occur many years before disease onset. Since disease-modifying therapies may be the most beneficial in the early stages of AD, biomarkers for the early diagnosis and longitudinal monitoring of disease progression are essential. Multiple imaging techniques with associated biomarkers are used to identify and monitor AD.

AIM

In this review, we discuss the contemporary early diagnosis and longitudinal monitoring of AD with imaging techniques regarding their diagnostic utility, benefits and limitations. Additionally, novel techniques, applications and biomarkers for AD research are assessed.

FINDINGS

Reduced hippocampal volume is a biomarker for neurodegeneration, but atrophy is not an AD-specific measure. Hypometabolism in temporoparietal regions is seen as a biomarker for AD. However, glucose uptake reflects astrocyte function rather than neuronal function. Amyloid-β (Aβ) is the earliest hallmark of AD and can be measured with positron emission tomography (PET), but Aβ accumulation stagnates as disease progresses. Therefore, Aβ may not be a suitable biomarker for monitoring disease progression. The measurement of tau accumulation with PET radiotracers exhibited promising results in both early diagnosis and longitudinal monitoring, but large-scale validation of these radiotracers is required. The implementation of new processing techniques, applications of other imaging techniques and novel biomarkers can contribute to understanding AD and finding a cure.

CONCLUSIONS

Several biomarkers are proposed for the early diagnosis and longitudinal monitoring of AD with imaging techniques, but all these biomarkers have their limitations regarding specificity, reliability and sensitivity. Future perspectives. Future research should focus on expanding the employment of imaging techniques and identifying novel biomarkers that reflect AD pathology in the earliest stages.

Imaging biomarkers in neurodegeneration: current and future practices

There is an increasing role for biological markers (biomarkers) in the understanding and diagnosis of neurodegenerative disorders. The application of imaging biomarkers specifically for the in vivo investigation of neurodegenerative disorders has increased substantially over the past decades and continues to provide further benefits both to the diagnosis and understanding of these diseases. This review forms part of a series of articles which stem from the University College London/University of Gothenburg course "Biomarkers in neurodegenerative diseases". In this review, we focus on neuroimaging, specifically positron emission tomography (PET) and magnetic resonance imaging (MRI), giving an overview of the current established practices clinically and in research as well as new techniques being developed. We will also discuss the use of machine learning (ML) techniques within these fields to provide additional insights to early diagnosis and multimodal analysis.