Knowledge-based localization of hippocampus in human brain MRI

Hippocampus substructure segmentation using morphological vision transformer learning

The hippocampus plays a crucial role in memory and cognition. Because of the associated toxicity from whole brain radiotherapy, more advanced treatment planning techniques prioritize hippocampal avoidance, which depends on an accurate segmentation of the small and complexly shaped hippocampus. To achieve accurate segmentation of the anterior and posterior regions of the hippocampus from T1 weighted (T1w) MR images, we developed a novel model, Hippo-Net, which uses a cascaded model strategy. The proposed model consists of two major parts: (1) a localization model is used to detect the volume-of-interest (VOI) of hippocampus. (2) An end-to-end morphological vision transformer network (Franchietal2020Pattern Recognit.102107246, Ranemetal2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW) pp 3710-3719) is used to perform substructures segmentation within the hippocampus VOI. The substructures include the anterior and posterior regions of the hippocampus, which are defined as the hippocampus proper and parts of the subiculum. The vision transformer incorporates the dominant features extracted from MR images, which are further improved by learning-based morphological operators. The integration of these morphological operators into the vision transformer increases the accuracy and ability to separate hippocampus structure into its two distinct substructures. A total of 260 T1w MRI datasets from medical segmentation decathlon dataset were used in this study. We conducted a five-fold cross-validation on the first 200 T1w MR images and then performed a hold-out test on the remaining 60 T1w MR images with the model trained on the first 200 images. In five-fold cross-validation, the Dice similarity coefficients were 0.900 ± 0.029 and 0.886 ± 0.031 for the hippocampus proper and parts of the subiculum, respectively. The mean surface distances (MSDs) were 0.426 ± 0.115 mm and 0.401 ± 0.100 mm for the hippocampus proper and parts of the subiculum, respectively. The proposed method showed great promise in automatically delineating hippocampus substructures on T1w MR images. It may facilitate the current clinical workflow and reduce the physicians' effort.

External cortical landmarks for localization of the hippocampus: Application for temporal lobectomy and amygdalohippocampectomy

Background:

Accessing the hippocampus for amygdalohippocampectomy and minimally invasive procedures, such as depth electrode placement, require an accurate knowledge regarding the location of the hippocampus.

Methods:

The authors removed 10 human cadaveric brains from the cranium and observed the relationships between the lateral temporal neocortex and the underlying hippocampus. They then measured the distance between the hippocampus and superficial landmarks. The authors also validated their study using magnetic resonance imaging (MRI) scans of 10 patients suffering from medial temporal lobe sclerosis where the distance from the hippocampal head to the anterior temporal tip was measured.

Results:

In general, the length of the hippocampus was along the inferior temporal sulcus and inferior aspect of the middle temporal gyrus. Although the hippocampus tended to be more superiorly located in female specimens and on the left side, this did not reach statistical significance. The length of the hippocampus tended to be shorter in females, but this too failed to reach statistical significance. The mean distance from the anterior temporal tip to the hippocampal head was identical in the cadavers and MRIs of patients with medial temporal lobe sclerosis.

Conclusions:

Additional landmarks for localizing the underlying hippocampus may be helpful in temporal lobe surgery. Based on this study, there are relatively constant anatomical landmarks between the hippocampus and overlying temporal cortex. Such landmarks may be used in localizing the hippocampus during amygdalohippocampectomy and depth electrode implantation in verifying the accuracy of image-guided methods and as adjuvant methodologies when these latter technologies are not used or are unavailable.

Superficial cortical landmarks for localization of the hippocampus: Application for temporal lobectomy and amygdalohippocampectomy

Background:

Accessing the hippocampus for amygdalohippocampectomy and procedures such as depth electrode placement requires accurate knowledge regarding the location of the hippocampus.

Methods:

The authors removed 10 human cadaveric brains (20 sides) from their crania, noted relationships between the lateral temporal neocortex and underlying hippocampus, and measured the distance between the hippocampus and superficial landmarks.

Results:

Mean distances were as follows: 3.8 cm from the tip of the temporal lobe to the head of the hippocampus; 6.5 cm from the tip of the temporal lobe to the junction of the fornix and hippocampus; and 3.5 cm between the tail and head of the hippocampus. The head of the hippocampus ranged from 0 to 5 mm inferior to the inferior temporal sulcus. The tail of the hippocampus ranged from 2.2 to 7 mm superior to the inferior temporal sulcus. In two specimens, the tail was deep to the superior temporal sulcus. Generally the length of the hippocampus was along the inferior temporal sulcus and inferior aspect of the middle temporal gyrus. The hippocampus tended to be more superiorly located and shorter in females and left sides, but this was not statistically significant.

Conclusions:

Additional landmarks for localizing the underlying hippocampus may be helpful in temporal lobe surgery. Our study showed relatively constant anatomic landmarks between the hippocampus and overlying temporal cortex that may help localize the hippocampus during amygdalohippocampectomy and depth electrode implantation, verify the accuracy of image-guided methods, and used as adjuvant methodologies when these latter technologies are unavailable.

Automated algorithm to measure changes in medial temporal lobe volume in Alzheimer disease

BACKGROUND

The change in volume of anatomic structures is as a sensitive indicator of Alzheimer disease (AD) progression. Although several methods are available to measure brain volumes, improvements in speed and automation are required. Our objective was to develop a fully automated, fast, and reliable approach to measure change in medial temporal lobe (MTL) volume, including primarily hippocampus.

METHODS

The MTL volume defined in an atlas image was propagated onto each baseline image and a level set algorithm was applied to refine the shape and smooth the boundary. The MTL of the baseline image was then mapped onto the corresponding follow-up image to measure volume change (ΔMTL). Baseline and 24 months 3D T1-weighted images from the Alzheimer Disease Neuroimaging Initiative (ADNI) were randomly selected for 50 normal elderly controls (NECs), 50 subjects with mild cognitive impairment (MCI) and 50 subjects with AD to test the algorithm. The method was compared to the FreeSurfer segmentation tools.

RESULTS

The average ΔMTL (mean±SEM) was 68±35mm(3) in NEC, 187±38mm(3) in MCI and 300±34mm(3) in the AD group and was significantly different (p<0.0001) between all three groups. The ΔMTL was correlated with cognitive decline.

COMPARISON WITH EXISTING METHOD(S)

Results for the FreeSurfer software were similar but did not detect significant differences between the MCI and AD groups.

CONCLUSION

This novel segmentation approach is fully automated and provides a robust marker of brain atrophy that shows different rates of atrophy over 2 years between NEC, MCI, and AD groups.

Patch-based segmentation using expert priors: application to hippocampus and ventricle segmentation

Quantitative magnetic resonance analysis often requires accurate, robust, and reliable automatic extraction of anatomical structures. Recently, template-warping methods incorporating a label fusion strategy have demonstrated high accuracy in segmenting cerebral structures. In this study, we propose a novel patch-based method using expert manual segmentations as priors to achieve this task. Inspired by recent work in image denoising, the proposed nonlocal patch-based label fusion produces accurate and robust segmentation. Validation with two different datasets is presented. In our experiments, the hippocampi of 80 healthy subjects and the lateral ventricles of 80 patients with Alzheimer's disease were segmented. The influence on segmentation accuracy of different parameters such as patch size and number of training subjects was also studied. A comparison with an appearance-based method and a template-based method was also carried out. The highest median kappa index values obtained with the proposed method were 0.884 for hippocampus segmentation and 0.959 for lateral ventricle segmentation.

A time-saving and facilitating approach for segmentation of anatomically defined cortical regions: MRI volumetry

In this study, we present an accurate, reliable, robust, and time-efficient technique for a semi-automatic segmentation of neuroanatomically defined cortical structures in Magnetic Resonance Imaging (MRI) scans. It involves manual drawing of the border of a region of interest (ROI), supported by three-dimensional (3D) visualization techniques (rendering), and a subsequent automatic tracing of the gray matter voxels inside the ROI by means of an automatic tissue classifier. The approach has been evaluated on a set of MRI scans of 75 participants selected from the Maastricht Aging Study (MAAS) and applied to cortical brain structures for both the left and right hemispheres, viz., the inferior prefrontal cortex (PFC); the orbital PFC; the dorsolateral PFC; the anterior cingulate cortex; and the posterior cingulate cortex. The use of a 3D surface-rendered brain can be rotated in any direction was invaluable in identifying anatomical landmarks on the basis of gyral and sulcal topography. This resulted in a high accuracy (anatomical correctness) and reliability: the intra-rater intra-class correlation coefficient (ICC) was between 0.96 and 0.99. Furthermore, the obtained time savings were substantial, i.e., up to a factor of 7.5 compared with fully manual segmentations.