Agreement Between Automated and Manual MRI Volumetry in Alzheimer's Disease: A Systematic Review and Meta-Analysis

Evaluation of registration-based vs. manual segmentation of rhesus macaque brain MRIs

With increasing numbers of magnetic resonance imaging (MRI) datasets becoming publicly available, researchers and clinicians alike have turned to automated methods of segmentation to enable population-level analyses of these data. Although prior research has evaluated the extent to which automated methods recapitulate "gold standard" manual segmentation methods in the human brain, such an evaluation has not yet been carried out for segmentation of MRIs of the macaque brain. Macaques offer the important opportunity to bridge gaps between microanatomical studies using invasive methods like tract tracing, neural recordings, and high-resolution histology and non-invasive macroanatomical studies using methods like MRI. As such, it is important to evaluate whether automated tools derive data of sufficient quality from macaque MRIs to bridge these gaps. We tested the relationship between automated registration-based segmentation using an open source and actively maintained NHP imaging analysis pipeline (AFNI) and gold standard manual segmentation of 4 structures (2 cortical: anterior cingulate cortex and insula; 2 subcortical: amygdala and caudate) across 37 rhesus macaques (Macaca mulatta). We identified some variability in the strength of correlation between automated and manual segmentations across neural regions and differences in relationships with demographic variables like age and sex between the two techniques.

An improved 3D-UNet-based brain hippocampus segmentation model based on MR images

OBJECTIVE

Accurate delineation of the hippocampal region via magnetic resonance imaging (MRI) is crucial for the prevention and early diagnosis of neurosystemic diseases. Determining how to accurately and quickly delineate the hippocampus from MRI results has become a serious issue. In this study, a pixel-level semantic segmentation method using 3D-UNet is proposed to realize the automatic segmentation of the brain hippocampus from MRI results.

METHODS

Two hundred three-dimensional T1-weighted (3D-T1) nongadolinium contrast-enhanced magnetic resonance (MR) images were acquired at Hangzhou Cancer Hospital from June 2020 to December 2022. These samples were divided into two groups, containing 175 and 25 samples. In the first group, 145 cases were used to train the hippocampus segmentation model, and the remaining 30 cases were used to fine-tune the hyperparameters of the model. Images for twenty-five patients in the second group were used as the test set to evaluate the performance of the model. The training set of images was processed via rotation, scaling, grey value augmentation and transformation with a smooth dense deformation field for both image data and ground truth labels. A filling technique was introduced into the segmentation network to establish the hippocampus segmentation model. In addition, the performance of models established with the original network, such as VNet, SegResNet, UNetR and 3D-UNet, was compared with that of models constructed by combining the filling technique with the original segmentation network.

RESULTS

The results showed that the performance of the segmentation model improved after the filling technique was introduced. Specifically, when the filling technique was introduced into VNet, SegResNet, 3D-UNet and UNetR, the segmentation performance of the models trained with an input image size of 48 × 48 × 48 improved. Among them, the 3D-UNet-based model with the filling technique achieved the best performance, with a Dice score (Dice score) of 0.7989 ± 0.0398 and a mean intersection over union (mIoU) of 0.6669 ± 0.0540, which were greater than those of the original 3D-UNet-based model. In addition, the oversegmentation ratio (OSR), average surface distance (ASD) and Hausdorff distance (HD) were 0.0666 ± 0.0351, 0.5733 ± 0.1018 and 5.1235 ± 1.4397, respectively, which were better than those of the other models. In addition, when the size of the input image was set to 48 × 48 × 48, 64 × 64 × 64 and 96 × 96 × 96, the model performance gradually improved, and the Dice scores of the proposed model reached 0.7989 ± 0.0398, 0.8371 ± 0.0254 and 0.8674 ± 0.0257, respectively. In addition, the mIoUs reached 0.6669 ± 0.0540, 0.7207 ± 0.0370 and 0.7668 ± 0.0392, respectively.

CONCLUSION

The proposed hippocampus segmentation model constructed by introducing the filling technique into a segmentation network performed better than models built solely on the original network and can improve the efficiency of diagnostic analysis.

Towards validation in clinical routine: a comparative analysis of visual MTA ratings versus the automated ratio between inferior lateral ventricle and hippocampal volumes in Alzheimer's disease diagnosis

PURPOSE

To assess the performance of the inferior lateral ventricle (ILV) to hippocampal (Hip) volume ratio on brain MRI, for Alzheimer's disease (AD) diagnostics, comparing it to individual automated ILV and hippocampal volumes, and visual medial temporal lobe atrophy (MTA) consensus ratings.

METHODS

One-hundred-twelve subjects (mean age ± SD, 66.85 ± 13.64 years) with varying degrees of cognitive decline underwent MRI using a Philips Ingenia 3T. The MTA scale by Scheltens, rated on coronal 3D T1-weighted images, was determined by three experienced radiologists, blinded to diagnosis and sex. Automated volumetry was computed by icobrain dm (v. 5.10) for total, left, right hippocampal, and ILV volumes. The ILV/Hip ratio, defined as the percentage ratio between ILV and hippocampal volumes, was calculated and compared against a normative reference population (n = 1903). Inter-rater agreement, association, classification accuracy, and clinical interpretability on patient level were reported.

RESULTS

Visual MTA scores showed excellent inter-rater agreement. Ordinal logistic regression and correlation analyses demonstrated robust associations between automated brain segmentations and visual MTA ratings, with the ILV/Hip ratio consistently outperforming individual hippocampal and ILV volumes. Pairwise classification accuracy showed good performance without statistically significant differences between the ILV/Hip ratio and visual MTA across disease stages, indicating potential interchangeability. Comparison to the normative population and clinical interpretability assessments showed commensurability in classifying MTA "severity" between visual MTA and ILV/Hip ratio measurements.

CONCLUSION

The ILV/Hip ratio shows the highest correlation to visual MTA, in comparison to automated individual ILV and hippocampal volumes, offering standardized measures for diagnostic support in different stages of cognitive decline.

Amnestic Syndrome in Memory Clinics: Similar Morphological Brain Patterns in Older Adults with and without Alzheimer's Disease

Background

Amnestic syndrome of the hippocampal type (ASHT) in Memory Clinics is a presentation common to Alzheimer's disease (AD). However, ASHT can be found in other neurodegenerative disorders.

Objective

To compare brain morphometry including hippocampal volumes between amnestic older adults with and without AD pathology and investigate their relationship with memory performance and cerebrospinal fluid (CSF) biomarkers.

Methods

Brain morphometry of 92 consecutive patients (72.5±6.8 years old; 39% female) with Free and Cued Selective Recall Reminding Test (FCSRT) total recall < 40/48 was assessed with an automated algorithm and compared between AD and non-AD patients, as defined by CSF biomarkers.

Results

AD and non-AD patients presented comparable brain morphology. Total recall was associated to hippocampal volume irrespectively from AD pathology.

Conclusions

Brain morphometry, including hippocampal volumes, is similar between AD and non-AD older adults with ASHT evaluated in a Memory Clinic, underlying the importance of using molecular biomarkers for the diagnosis of AD.

Medial Temporal Lobe Atrophy in Predementia Alzheimer's Disease: A Longitudinal Multi-Site Study Comparing Staging and A/T/N in a Clinical Research Cohort

BACKGROUND

Atrophy of the medial temporal lobe (MTL) is a biological characteristic of Alzheimer's disease (AD) and can be measured by segmentation of magnetic resonance images (MRI).

OBJECTIVE

To assess the clinical utility of automated volumetry in a cognitively well-defined and biomarker-classified multi-center longitudinal predementia cohort.

METHODS

We used Automatic Segmentation of Hippocampal Subfields (ASHS) to determine MTL morphometry from MRI. We harmonized scanner effects using the recently developed longitudinal ComBat. Subjects were classified according to the A/T/N system, and as normal controls (NC), subjective cognitive decline (SCD), or mild cognitive impairment (MCI). Positive or negative values of A, T, and N were determined by cerebrospinal fluid measurements of the Aβ42/40 ratio, phosphorylated and total tau. From 406 included subjects, longitudinal data was available for 206 subjects by stage, and 212 subjects by A/T/N.

RESULTS

Compared to A-/T-/N- at baseline, the entorhinal cortex, anterior and posterior hippocampus were smaller in A+/T+orN+. Compared to NC A- at baseline, these subregions were also smaller in MCI A+. Longitudinally, SCD A+ and MCI A+, and A+/T-/N- and A+/T+orN+, had significantly greater atrophy compared to controls in both anterior and posterior hippocampus. In the entorhinal and parahippocampal cortices, longitudinal atrophy was observed only in MCI A+ compared to NC A-, and in A+/T-/N- and A+/T+orN+ compared to A-/T-/N-.

CONCLUSION

We found MTL neurodegeneration largely consistent with existing models, suggesting that harmonized MRI volumetry may be used under conditions that are common in clinical multi-center cohorts.