Article Figures & Data
Figures
- Fig 1.
Training and segmentation pipelines in ASHS. Reprinted with permission from Yushkevich et al. 12 Copyright 2014 Wiley Periodicals.
- Fig 2.
Examples of results from the automated segmentation from the cross-validation experiment with the best (upper panel, left hemisphere), median (middle panel, left hemisphere), and worst performance (lower panel, right hemisphere). In each panel in the top row, the raw T2 image is shown; in the second row, the automated segmentation of hippocampal subfields is shown; and the third row, the manual segmentation is shown.
- Fig 3.
3D rendering of an automated (ASHS) and a manual segmentation.
Tables
Automated Segmentation Volume (Mean) (mL) Manual Segmentation Volume (Mean) (mL) Left Right Left Right CA1 1.43 ± 0.22 1.54 ± 0.24 1.42 ± 0.22 1.53 ± 0.23 CA2 0.054 ± 0.008a 0.066 ± 0.012a 0.060 ± 0.013 0.071 ± 0.013 CA3 0.10 ± 0.03a 0.09 ± 0.03a 0.12 ± 0.04 0.12 ± 0.05 CA2+3 0.15 ± 0.03a 0.16 ± 0.04a 0.18 ± 0.04 0.19 ± 0.05 DG 0.79 ± 0.12 0.79 ± 0.12 0.79 ± 0.12 0.80 ± 0.12 SUB 0.61 ± 0.09 0.64 ± 0.09 0.61 ± 0.14 0.65 ± 0.13 ERC 0.47 ± 0.07a 0.49 ± 0.07a 0.52 ± 0.11 0.53 ± 0.08 ↵a Significantly different from volumes generated by manual segmentation.
- Table 2:
ICC and DSC among automated and corresponding manual segmentations, intrarater reliability of a single manual rater, and interrater reliability of 2 independent manual raters
ICC and DSC of Automated vs Manual Rater (ASHS vs Rater 1) ICC and DSC of a Single Manual Rater (Rater 1)a ICC and DSC of 2 Independent Manual Raters (Rater 1 vs 2) DSC (mean ± SD) ICC DSC (mean ± SD) ICC DSC (mean ± SD) ICC Left Right Left Right Left Right Left Right Left Right Left Right CA1 0.84 ± 0.03 0.83 ± 0.02 0.93 0.97 0.86 ± 0.02 0.86 ± 0.03 0.98 0.98 0.82 ± 0.03 0.81 ± 0.02 0.73 0.94 CA2 0.64 ± 0.08 0.65 ± 0.09 0.55 0.67 0.66 ± 0.05 0.66 ± 0.10 0.83 0.74 0.65 ± 0.06 0.66 ± 0.05 0.34 0.88 CA3 0.58 ± 0.11 0.54 ± 0.13 0.43 0.45 0.70 ± 0.10 0.71 ± 0.08 0.82 0.85 0.57 ± 0.09 0.59 ± 0.10 0.60 0.60 CA2+3 0.66 ± 0.08 0.64 ± 0.10 0.42 0.49 0.73 ± 0.07 0.74 ± 0.07 0.80 0.81 0.65 ± 0.07 0.67 ± 0.06 0.52 0.63 DG 0.85 ± 0.03 0.84 ± 0.03 0.84 0.84 0.87 ± 0.02 0.87 ± 0.02 0.96 0.98 0.83 ± 0.03 0.81 ± 0.03 0.92 0.89 SUB 0.80 ± 0.03 0.78 ± 0.04 0.74 0.75 0.83 ± 0.03 0.81 ± 0.04 0.98 0.97 0.75 ± 0.03 0.71 ± 0.05 0.78 0.58 ERC 0.75 ± 0.07 0.75 ± 0.06 0.49 0.51 0.80 ± 0.06 0.79 ± 0.05 0.80 0.82 0.71 ± 0.05 0.72 ± 0.06 0.27 0.54 ↵a Retrieved from Wisse et al (2012).5 Note that an error was detected in the original script for calculating the DSC values. The corrected DSC values are displayed in the table and have also been published in a corrigendum to the original article.
Jump to section
Related Articles
Cited By...
- Visual Statistical Learning Alters Low-Dimensional Cortical Architecture
- Developing an anatomically valid segmentation protocol for anterior regions of the medial temporal lobe for neurodegenerative diseases
- Hippocampal subfield volume in relation to cerebrospinal fluid Amyloid-ss in early Alzheimers disease: Diagnostic Utility of 7T MRI
- Visual statistical learning is associated with changes in low-dimensional cortical architecture
- Automatic segmentation of medial temporal lobe subregions in multi-scanner, multi-modality MRI of variable quality
- Novel insights into hippocampal perfusion using high-resolution, multi-modal 7T MRI
- Organization of pRF size along the AP axis of the hippocampus is related to specialization for scenes
- Neurodesk: An accessible, flexible, and portable data analysis environment for reproducible neuroimaging
- Preserved cognition in elderly with intact rhinal cortex
- Activity in perirhinal and entorhinal cortex predicts perceived visual similarities among category exemplars with highest precision
- 7T Epilepsy Task Force Consensus Recommendations on the Use of 7T MRI in Clinical Practice
- Longitudinal Automatic Segmentation of Hippocampal Subfields (LASHiS) using Multi-Contrast MRI
- Dissociation of the Perirhinal Cortex and Hippocampus During Discriminative Learning of Similar Objects
- Building a high-resolution in vivo minimum deformation average model of the human hippocampus