Optimization and validation of automated hippocampal subfield segmentation across the lifespan

Abstract

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.

Keywords: MRI; aging; development; hippocampus; morphometry; validation; volume.

Figure 1

Illustration of the anatomic‐geometric heuristic for manual morphometry. (a) A representative slice of anterior hippocampal body following the visualization of the uncal sulcus. To facilitate tracing, the T₂‐weighted contrast has been inverted to mimic a T₁‐weighted image. (b) Placement of the ellipse and bisecting lines (the major and minor axes of the ellipse). (c) The minor axis bisecting the ellipse marks the point from which a vertical line is dropped to create a boundary separating the subiculum from CA1/2, and CA 1/2 from CA3–4/DG, as shown in (d). Bottom: 3‐D illustrations of sagittal (e) and oblique coronal (f) views of manual subfield labeling in the HC body from one EL participant [Color figure can be viewed at http://wileyonlinelibrary.com]

Figure 2

List of atlases generated and applied at different stages of validation work. Red Xs indicate atlases used at intermediate stages of the validation efforts, and green check marks indicate atlases used in reported analyses. The original atlases generated with the “slice heuristics” function in ASHS was only performed on the EL and LL samples, with no lifespan atlas generated. The optimization procedure included demarcation of subfields on one to two slices anterior and posterior, and was originally limited only to subfields and not ERC. Following inspection of the output from that atlas, additional demarcation was performed to similarly extend the labeling of ERC as well [Color figure can be viewed at http://wileyonlinelibrary.com]

Figure 3

Results of validation attempts for four comparisons between manual and automated approaches in ASHS, including the sample‐specific atlas without optimization (red), the Lifespan atlas without optimization (orange), the sample‐specific atlas following optimization (yellow), and the Lifespan atlas following optimization (green). Error bars represent 95% confidence intervals. (a) ICC(2) values for the Early Lifespan sample (top) and the Late Lifespan sample (bottom). (b) DSC values for the Early Lifespan sample (top) and the Late Lifespan sample (bottom) [Color figure can be viewed at http://wileyonlinelibrary.com]

Figure 4

Illustration of ASHS segmentation errors in the initial, nonoptimized validation attempt. Left column depicts correct, manual segmentation, and right column shows faulty segmentations. (a) Whereas manual segmentation (left) does not include this slice in the range, ASHS (right) includes multiple, erroneously included voxels in ERC, as indicated by the yellow arrow. (b) Manual segmentation of ERC (left) in comparison with omitted segmentation by ASHS (right). (c) Manual segmentation includes only ERC (left) as visible presence of uncus (indicated by the white arrow) indicates no body segmentation on this slice. In contrast, ASHS (right) includes segmentation of ERC and body subregions. (d) Overextension of ERC by ASHS in several voxels (right, as indicated by the yellow arrow), where ERC should no longer be segmented following the first body slice (left). (e) Following the disappearance of the lamina quadrigemina, subfields are no longer segmented by the manual approach (left), but are both included, and mis‐segmented by ASHS (right) [Color figure can be viewed at http://wileyonlinelibrary.com]

Figure 5

Illustration of labeling by manual demarcation, optimized ASHS in the lifespan atlas, and the difference between the two. Numbers in white represent z‐axis/slice number. The leftmost column shows the unlabeled T₂‐weighted, high‐resolution image on all slices included in manual labeling. Although this reflects the original contrast, manually demarcation was performed on images with inverted contrast (T₁‐weighted appearance). The middle columns show manual and automated demarcation of ERC and hippocampal subfields. The rightmost column shows the difference between ASHS and manual segmentation, and was generated by image subtraction between the two methods. As illustrated by the difference images (right column), the discrepancies between the two methods are most apparent at the edges of the subregional labels [Color figure can be viewed at http://wileyonlinelibrary.com]

Figure 6

Bland‐Altman plots of agreement between manual and automated methods for Early Lifespan (EL) and Late Lifespan (LL) samples, using the ASHS customized lifespan atlas, following optimization procedures, with regression lines fitted to the data. On all plots, the Y‐axis represents the difference between ASHS automated and manual morphometry and the X‐axis represents the combined mean of the two methods. The solid black horizontal lines indicate the mean difference between methods, and the dashed lines represent the 95% confidence interval or two standard deviations above and below the mean difference. Negative regression slopes indicate proportional bias: the automatic procedure overestimates smaller volumes and underestimated the larger volumes, relative to manual segmentation

Figure 7

Comparison of bias from Bland–Altman plots across atlases, optimization methods, and HC subfields for Early lifespan sample (open bars) and the Late lifespan sample (filled bars). Error bars represent the 95% CI of the bias statistic