A Critical Appraisal of the Hippocampal Subfield Segmentation Package in FreeSurfer.
Ontology highlight
ABSTRACT:
SUBMITTER: Wisse LE
PROVIDER: S-EPMC4174865 | biostudies-literature | 2014
REPOSITORIES: biostudies-literature
Publications
A Critical Appraisal of the Hippocampal Subfield Segmentation Package in FreeSurfer.
Wisse Laura E M LE Biessels Geert Jan GJ Geerlings Mirjam I MI
Frontiers in aging neuroscience 20140925
Similar Datasets
Project description:Background and purposeHigh resolution 7T MRI is increasingly used to investigate hippocampal subfields in vivo, but most studies rely on manual segmentation which is labor intensive. We aimed to evaluate an automated technique to segment hippocampal subfields and the entorhinal cortex at 7T MRI.Materials and methodsThe cornu ammonis (CA)1, CA2, CA3, dentate gyrus, subiculum, and entorhinal cortex were manually segmented, covering most of the long axis of the hippocampus on 0.70-mm(3) T2-weighted 7T images of 26 participants (59 ± 9 years, 46% men). The automated segmentation of hippocampal subfields approach was applied and evaluated by using leave-one-out cross-validation.ResultsComparison of automated segmentations with corresponding manual segmentations yielded a Dice similarity coefficient of >0.75 for CA1, the dentate gyrus, subiculum, and entorhinal cortex and >0.54 for CA2 and CA3. Intraclass correlation coefficients were >0.74 for CA1, the dentate gyrus, and subiculum; and >0.43 for CA2, CA3, and the entorhinal cortex. Restricting the comparison of the entorhinal cortex segmentation to a smaller range along the anteroposterior axis improved both intraclass correlation coefficients (left: 0.71; right: 0.82) and Dice similarity coefficients (left: 0.78; right: 0.77). The accuracy of the automated segmentation versus a manual rater was lower, though only slightly for most subfields, than the intrarater reliability of an expert manual rater, but it was similar to or slightly higher than the accuracy of an expert-versus-manual rater with ∼170 hours of training for almost all subfields.ConclusionsThis work demonstrates the feasibility of using a computational technique to automatically label hippocampal subfields and the entorhinal cortex at 7T MRI, with a high accuracy for most subfields that is competitive with the labor-intensive manual segmentation. The software and atlas are publicly available: http://www.nitrc.org/projects/ashs/.
| S-EPMC4907820 | biostudies-literature
Project description:Like neocortical structures, the archicortical hippocampus differs in its folding patterns across individuals. Here, we present an automated and robust BIDS-App, HippUnfold, for defining and indexing individual-specific hippocampal folding in MRI, analogous to popular tools used in neocortical reconstruction. Such tailoring is critical for inter-individual alignment, with topology serving as the basis for homology. This topological framework enables qualitatively new analyses of morphological and laminar structure in the hippocampus or its subfields. It is critical for refining current neuroimaging analyses at a meso- as well as micro-scale. HippUnfold uses state-of-the-art deep learning combined with previously developed topological constraints to generate uniquely folded surfaces to fit a given subject's hippocampal conformation. It is designed to work with commonly employed sub-millimetric MRI acquisitions, with possible extension to microscopic resolution. In this paper, we describe the power of HippUnfold in feature extraction, and highlight its unique value compared to several extant hippocampal subfield analysis methods.
| S-EPMC9831605 | biostudies-literature
Project description:The accurate segmentation of in vivo magnetic resonance imaging (MRI) data is a crucial prerequisite for the reliable assessment of disease progression, patient stratification or the establishment of putative imaging biomarkers. This is especially important for the hippocampal formation, a brain area involved in memory formation and often affected by neurodegenerative or psychiatric diseases. FreeSurfer, a widely used automated segmentation software, offers hippocampal subfield delineation with multiple input options. While a single T1-weighted (T1) sequence is regularly used by most studies, it is also possible and advised to use a high-resolution T2-weighted (T2H) sequence or multispectral information. In this investigation it was determined whether there are differences in volume estimations depending on the input images and which combination of these deliver the most reliable results in each hippocampal subfield. 41 healthy participants (age = 25.2 years ± 4.2 SD) underwent two structural MRIs at three Tesla (time between scans: 23 days ± 11 SD) using three different structural MRI sequences, to test five different input configurations (T1, T2, T2H, T1 and T2, and T1 and T2H). We compared the different processing pipelines in a cross-sectional manner and assessed reliability using test-retest variability (%TRV) and the dice coefficient. Our analyses showed pronounced significant differences and large effect sizes between the processing pipelines in several subfields, such as the molecular layer (head), CA1 (head), hippocampal fissure, CA3 (head and body), fimbria and CA4 (head). The longitudinal analysis revealed that T1 and multispectral analysis (T1 and T2H) showed overall higher reliability across all subfields than T2H alone. However, the specific subfields had a substantial influence on the performance of segmentation results, regardless of the processing pipeline. Although T1 showed good test-retest metrics, results must be interpreted with caution, as a standard T1 sequence relies heavily on prior information of the atlas and does not take the actual fine structures of the hippocampus into account. For the most accurate segmentation, we advise the use of multispectral information by using a combination of T1 and high-resolution T2-weighted sequences or a T2 high-resolution sequence alone.
| S-EPMC8480394 | biostudies-literature
Project description:Automated segmentation of hippocampal (HC) subfields from magnetic resonance imaging (MRI) is gaining popularity, but automated procedures that afford high speed and reproducibility have yet to be extensively validated against the standard, manual morphometry. We evaluated the concurrent validity of an automated method for hippocampal subfields segmentation (automated segmentation of hippocampal subfields, ASHS; Yushkevich et al., ) using a customized atlas of the HC body, with manual morphometry as a standard. We built a series of customized atlases comprising the entorhinal cortex (ERC) and subfields of the HC body from manually segmented images, and evaluated the correspondence of automated segmentations with manual morphometry. In samples with age ranges of 6-24 and 62-79 years, 20 participants each, we obtained validity coefficients (intraclass correlations, ICC) and spatial overlap measures (dice similarity coefficient) that varied substantially across subfields. Anterior and posterior HC body evidenced the greatest discrepancies between automated and manual segmentations. Adding anterior and posterior slices for atlas creation and truncating automated output to the ranges manually defined by multiple neuroanatomical landmarks substantially improved the validity of automated segmentation, yielding ICC above 0.90 for all subfields and alleviating systematic bias. We cross-validated the developed atlas on an independent sample of 30 healthy adults (age 31-84) and obtained good to excellent agreement: ICC (2) = 0.70-0.92. Thus, with described customization steps implemented by experts trained in MRI neuroanatomy, ASHS shows excellent concurrent validity, and can become a promising method for studying age-related changes in HC subfield volumes.
| S-EPMC5861710 | biostudies-literature
Project description:The hippocampus is composed of distinct anatomical subregions that participate in multiple cognitive processes and are differentially affected in prevalent neurological and psychiatric conditions. Advances in high-field MRI allow for the non-invasive identification of hippocampal substructure. These approaches, however, demand time-consuming manual segmentation that relies heavily on anatomical expertise. Here, we share manual labels and associated high-resolution MRI data (MNI-HISUB25; submillimetric T1- and T2-weighted images, detailed sequence information, and stereotaxic probabilistic anatomical maps) based on 25 healthy subjects. Data were acquired on a widely available 3 Tesla MRI system using a 32 phased-array head coil. The protocol divided the hippocampal formation into three subregions: subicular complex, merged Cornu Ammonis 1, 2 and 3 (CA1-3) subfields, and CA4-dentate gyrus (CA4-DG). Segmentation was guided by consistent intensity and morphology characteristics of the densely myelinated molecular layer together with few geometry-based boundaries flexible to overall mesiotemporal anatomy, and achieved excellent intra-/inter-rater reliability (Dice index ≥90/87%). The dataset can inform neuroimaging assessments of the mesiotemporal lobe and help to develop segmentation algorithms relevant for basic and clinical neurosciences.
| S-EPMC4640139 | biostudies-literature
Project description:Developing accurate subcortical volumetric quantification tools is crucial for neurodevelopmental studies, as they could reduce the need for challenging and time-consuming manual segmentation. In this study, the accuracy of two automated segmentation tools, FSL-FIRST (with three different boundary correction settings) and FreeSurfer, were compared against manual segmentation of the hippocampus and subcortical nuclei, including the amygdala, thalamus, putamen, globus pallidus, caudate and nucleus accumbens, using volumetric and correlation analyses in 80 5-year-olds. Both FSL-FIRST and FreeSurfer overestimated the volume on all structures except the caudate, and the accuracy varied depending on the structure. Small structures such as the amygdala and nucleus accumbens, which are visually difficult to distinguish, produced significant overestimations and weaker correlations with all automated methods. Larger and more readily distinguishable structures such as the caudate and putamen produced notably lower overestimations and stronger correlations. Overall, the segmentations performed by FSL-FIRST's default pipeline were the most accurate, whereas FreeSurfer's results were weaker across the structures. In line with prior studies, the accuracy of automated segmentation tools was imperfect with respect to manually defined structures. However, apart from amygdala and nucleus accumbens, FSL-FIRST's agreement could be considered satisfactory (Pearson correlation > 0.74, intraclass correlation coefficient (ICC) > 0.68 and Dice score coefficient (DSC) > 0.87) with highest values for the striatal structures (putamen, globus pallidus, caudate) (Pearson correlation > 0.77, ICC > 0.87 and DSC > 0.88, respectively). Overall, automated segmentation tools do not always provide satisfactory results, and careful visual inspection of the automated segmentations is strongly advised.
| S-EPMC9543285 | biostudies-literature
Project description:In this study, we developed a multi-scale Convolutional neural network based Automated hippocampal subfield Segmentation Toolbox (CAST) for automated segmentation of hippocampal subfields. Although training CAST required approximately three days on a single workstation with a high-quality GPU card, CAST can segment a new subject in less than 1 min even with GPU acceleration disabled, thus this method is more time efficient than current automated methods and manual segmentation. This toolbox is highly flexible with either a single modality or multiple modalities and can be easily set up to be trained with a researcher's unique data. A 3D multi-scale deep convolutional neural network is the key algorithm used in the toolbox. The main merit of multi-scale images is the capability to capture more global structural information from down-sampled images without dramatically increasing memory and computational burden. The original images capture more local information to refine the boundary between subfields. Residual learning is applied to alleviate the vanishing gradient problem and improve the performance with a deeper network. We applied CAST with the same settings on two datasets, one 7T dataset (the UMC dataset) with only the T2 image and one 3T dataset (the MNI dataset) with both T1 and T2 images available. The segmentation accuracy of both CAST and the state-of-the-art automated method ASHS, in terms of the dice similarity coefficient (DSC), were comparable. CAST significantly improved the reliability of segmenting small subfields, such as CA2, CA3, and the entorhinal cortex (ERC), in terms of the intraclass correlation coefficient (ICC). Both ASHS and manual segmentation process some subfields (e.g. CA2 and ERC) with high DSC values but low ICC values, consequently increasing the difficulty of judging segmentation quality. CAST produces very consistent DSC and ICC values, with a maximal discrepancy of 0.01 (DSC-ICC) across all subfields. The pre-trained model, source code, and settings for the CAST toolbox are publicly available.
| S-EPMC7442241 | biostudies-literature
Project description:Many segmentation algorithms in medical image analysis use Bayesian modeling to augment local image appearance with prior anatomical knowledge. Such methods often contain a large number of free parameters that are first estimated and then kept fixed during the actual segmentation process. However, a faithful Bayesian analysis would marginalize over such parameters, accounting for their uncertainty by considering all possible values they may take. Here we propose to incorporate this uncertainty into Bayesian segmentation methods in order to improve the inference process. In particular, we approximate the required marginalization over model parameters using computationally efficient Markov chain Monte Carlo techniques. We illustrate the proposed approach using a recently developed Bayesian method for the segmentation of hippocampal subfields in brain MRI scans, showing a significant improvement in an Alzheimer's disease classification task. As an additional benefit, the technique also allows one to compute informative "error bars" on the volume estimates of individual structures.
| S-EPMC3719857 | biostudies-literature
Project description:Episodic memory function has been shown to depend critically on the hippocampus. This region is made up of a number of subfields, which differ in both cytoarchitectural features and functional roles in the mature brain. Recent neuroimaging work in children and adolescents has suggested that these regions may undergo different developmental trajectories-a fact that has important implications for how we think about learning and memory processes in these populations. Despite the growing research interest in hippocampal structure and function at the subfield level in healthy young adults, comparatively fewer studies have been carried out looking at subfield development. One barrier to studying these questions has been that manual segmentation of hippocampal subfields-considered by many to be the best available approach for defining these regions-is laborious and can be infeasible for large cross-sectional or longitudinal studies of cognitive development. Moreover, manual segmentation requires some subjectivity and is not impervious to bias or error. In a developmental sample of individuals spanning 6-30 years, we assessed the degree to which two semi-automated segmentation approaches-one approach based on Automated Segmentation of Hippocampal Subfields (ASHS) and another utilizing Advanced Normalization Tools (ANTs)-approximated manual subfield delineation on each individual by a single expert rater. Our main question was whether performance varied as a function of age group. Across several quantitative metrics, we found negligible differences in subfield validity across the child, adolescent, and adult age groups, suggesting that these methods can be reliably applied to developmental studies. We conclude that ASHS outperforms ANTs overall and is thus preferable for analyses carried out in individual subject space. However, we underscore that ANTs is also acceptable and may be well-suited for analyses requiring normalization to a single group template (e.g., voxelwise analyses across a wide age range). Previous work has supported the use of such methods in healthy young adults, as well as several special populations such as older adults and those suffering from mild cognitive impairment. Our results extend these previous findings to show that ASHS and ANTs can also be used in pediatric populations as young as six.
| S-EPMC6524646 | biostudies-literature
Project description:In patients with temporal lobe epilepsy (TLE), presurgical magnetic resonance imaging (MRI) often reveals hippocampal atrophy, while neuropathological assessment indicates the different types of hippocampal sclerosis (HS). Different HS types are not discriminated in MRI so far. We aimed to define the volume of each hippocampal subfield on MRI manually and to compare automatic and manual segmentations for the discrimination of HS types. The T2-weighted images from 14 formalin-fixed age-matched control hippocampi were obtained with 4.7T MRI to evaluate the volume of each subfield at the anatomical level of the hippocampal head, body, and tail. Formalin-fixed coronal sections at the level of the body of 14 control cases, as well as tissue samples from 24 TLE patients, were imaged with a similar high-resolution sequence at 3T. Presurgical three-dimensional (3D) T1-weighted images from TLE went through a FreeSurfer 6.0 hippocampal subfield automatic assessment. The manual delineation with the 4.7T MRI was identified using Luxol Fast Blue stained 10-μm-thin microscopy slides, collected at every millimeter. An additional section at the level of the body from controls and TLE cases was submitted to NeuN immunohistochemistry for neuronal density estimation. All TLE cases were classified according to the International League Against Epilepsy's (ILAE's) HS classification. Manual volumetry in controls revealed that the dentate gyrus (DG)+CA4 region, CA1, and subiculum accounted for almost 90% of the hippocampal volume. The manual 3T volumetry showed that all TLE patients with type 1 HS (TLE-HS1) had lower volumes for DG+CA4, CA2, and CA1, whereas those TLE patients with HS type 2 (TLE-HS2) had lower volumes only in CA1 (p ≤ 0.038). Neuronal cell densities always decreased in CA4, CA3, CA2, and CA1 of TLE-HS1 but only in CA1 of TLE-HS2 (p ≤ 0.003). In addition, TLE-HS2 had a higher volume (p = 0.016) and higher neuronal density (p < 0.001) than the TLE-HS1 in DG + CA4. Automatic segmentation failed to match the manual or histological findings and was unable to differentiate TLE-HS1 from TLE-HS2. Total hippocampal volume correlated with DG+CA4 and CA1 volumes and neuronal density. For the first time, we also identified subfield-specific pathology patterns in the manual evaluation of volumetric MRI scans, showing the importance of manual segmentation to assess subfield-specific pathology patterns.
| S-EPMC6256705 | biostudies-literature