First, input MRI images are preprocessed and cropped around the left and right hippocampi. Second, a U-Net neural network architecture (nnUNet; Isensee et al., 2021) is used to segment hippocampal …
This architecture was automatically configured as the 3D_fullres network, using the 128 × 256 × 128 (0.3 × 0.3 × 0.3 mm3) hippocampal subregion images as training data. All conv3D blocks have stride …
The same topologically defined subfields were applied in unfolded space to all subjects (top), which are also overlaid on quantitative MRI plots (black lines). The dentate gyrus (DG) is represented …
Distortions were greatest in the tail of the hippocampus where its proximal-distal distance becomes quite narrow.
(A) Side-by-side comparison of results obtained from each method from one representative individual from the Human Connectome Project-Aging (HCP-A) datasets, which was not seen during training. (B) …
All three methods showed a moderate correlation with age, as expected based on previous literature. Volumetric comparison of each method to HippUnfold directly revealed that there is a strong …
Sagittal and coronal slices and 3D models are shown for one representative subject. Note that for HippUnfold hippocampal subfields are the same for all individuals in unfolded space, but for ASHS …
Sagittal and coronal slices and 3D models are shown for one representative subject. Note that the 3D model of a fully manual segmentation shows clear anterior and posterior digitations which were …
All values are compared to ground truth manually defined tissues followed by unfolded subfield definition (manual unfold) to determine how small differences in grey matter parcellation propagate …
(A) Sample subjects’ HippUnfold subfield segmentation in native resolution. The first two rows come from the same subjects but using different input data modalities. (B) HippUnfold results from a 7 …
Methods employed include those proposed here (HippUnfold), the same processing but with manual segmentation (similar to previous work; DeKraker et al., 2020) (manual unfold), Freesurfer v7.2.0 (FS7) …
Name | Modalities | Resolution | Sample size (L+R) | Methods employed |
---|---|---|---|---|
HCP-YA | T1w, T2w | 0.7 × 0.7 × 0.7 mm3 | n=590 (training) | HippUnfold Manual unfold |
n=148 (testing) | HippUnfold Manual unfold FS7 | |||
HCP-A | T1w T2w SPACE T2w TSE | 0.8 × 0.8 × 0.8 mm3 0.8 × 0.8 × 0.8 mm3 0.4 × 0.4 × 2.0 mm3 | n=1312 for T1w, T2w SPACE n=200 for T2w TSE (FS7, ASHS) n=200 for T1w (HippUnfold) | HippUnfold FS7 ASHS |
7T-TSE (from ASHS atlas) | T2w | 0.4 × 0.4 × 1.0 mm3 | n=70 | HippUnfold Manual subfields |
HippUnfold Documentation.
This document fully describes the HippUnfold installation, command-line interface, options, outputs, and provides several useful pieces of information including worked examples and useful tips on viewing data in other common platforms.
Side-by-side snapshot comparison of Human Connectome Project-Aging (HCP-A) segmentations results from HippUnfold, Freesurfer (FS7), and Automatic Segmentation of Hippocampal Subfields (ASHS) from the left hemisphere.
Snapshots were taken at the conronal centroid, centroid + 15 slices, centroid + 30 slices, and the sagittal centroid.
Side-by-side snapshot comparison of Human Connectome Project-Aging (HCP-A) segmentations results from HippUnfold, Freesurfer (FS7), and Automatic Segmentation of Hippocampal Subfields (ASHS) from the right hemisphere.
Snapshots were taken at the conronal centroid, centroid + 15 slices, centroid + 30 slices, and the sagittal centroid.
Detailed mathematical formulation of algorithms used throughout HippUnfold.