Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks

Morphological characterization of the hippocampus: a first database in Ecuador

Introduction

The hippocampal volume is a well-known biomarker to detect and diagnose neurological, psychiatric, and psychological diseases. However, other morphological descriptors are not analyzed. Furthermore, not available databases, or studies, were found with information related to the hippocampal morphology from Latin-American patients living in the Andean highlands.

Methods

The hippocampus is manually segmented by two medical imaging specialists on normal brain magnetic resonance images. Then, its morphological qualitative and quantitative descriptors (volume, sphericity, roundness, diameter, volume-surface ratio, and aspect ratio) are computed via 3D digital level-set-based mathematical representation. Furthermore, other morphological descriptors and their possible correlation with the hippocampal volume is analyzed.

Results

We introduce a first database with the hippocampus' morphological characterization of 63 patients from Quito, Ecuador, male and female, aged between 18 and 95 years old.

Discussion

This study provides new research opportunities to neurologists, psychologists, and psychiatrists, to further understand the hippocampal morphology of Andean and Latin American patients.

Bidirectional relationship between late-onset epilepsy (LOE) and dementia: A systematic review and meta-analysis of cohort studies

OBJECTIVE

To explore the bidirectional relationship of late-onset epilepsy (LOE) with dementia and Alzheimer's disease (AD).

METHODS

Using the common electronic databases, including PubMed, Cochrane Library databases and EMBASE, we systematically reviewed published cohort studies that assessed the risk of LOE in individuals comorbid with dementia or AD, and those with dementia or AD comorbid with LOE that had been published up to 31 March 2023. The data extraction process was carried out independently by two authors. The summary adjusted relative ratio (aRR) was calculated by employing Rev Man 5.3 for the inclusion of studies. To investigate the origins of heterogeneity, we conducted both subgroup and sensitivity analyses. In the presence of heterogeneity, a random-effects model was employed. To evaluate potential publication bias, we utilized the funnel plot and conducted Begg's and Egger's tests.

RESULTS

We included 20 eligible studies in the final analysis after a rigorous screening process. Pooled results indicated that LOE was association with an increased risk of all-cause dementia (aRR: 1.34, 95% confidence interval [CI]: 1.13-1.59) and AD (aRR: 2.49, 95% CI: 1.16-5.32). In addition, the pooled effect size for LOE associated with baseline AD and all-cause dementia were 3.51 (95% CI: 3.47-3.56) and 2.53 (95% CI: 2.39-2.67), respectively. Both sensitivity and subgroup analyses showed that these positive correlations persisted. According to the results of the Egger's and Begg's tests, as well as visual inspection of funnel plots, none of the studies appeared to be biased by publication.

CONCLUSION

The findings suggested that LOE is a potential risk factor for dementia and AD, and vice versa, dementia and AD are both potential risk indicators for LOE. Since there is substantial heterogeneity among the cohorts analyzed and more cohort studies should be conducted to confirm the correlations found in the current study.

A novel cross-layer dual encoding-shared decoding network framework with spatial self-attention mechanism for hippocampus segmentation

Accurate segmentation of the hippocampus from the brain magnetic resonance images (MRIs) is a crucial task in the neuroimaging research, since its structural integrity is strongly related to several neurodegenerative disorders, such as Alzheimer's disease (AD). Automatic segmentation of the hippocampus structures is challenging due to the small volume, complex shape, low contrast and discontinuous boundaries of hippocampus. Although some methods have been developed for the hippocampus segmentation, most of them paid too much attention to the hippocampus shape and volume instead of considering the spatial information. Additionally, the extracted features are independent of each other, ignoring the correlation between the global and local information. In view of this, here we proposed a novel cross-layer dual Encoding-Shared Decoding network framework with Spatial self-Attention mechanism (called ESDSA) for hippocampus segmentation in human brains. Considering that the hippocampus is a relatively small part in MRI, we introduced the spatial self-attention mechanism in ESDSA to capture the spatial information of hippocampus for improving the segmentation accuracy. We also designed a cross-layer dual encoding-shared decoding network to effectively extract the global information of MRIs and the spatial information of hippocampus. The spatial features of hippocampus and the features extracted from the MRIs were combined to realize the hippocampus segmentation. Results on the baseline T1-weighted structural MRI data show that the performance of our ESDSA is superior to other state-of-the-art methods, and the dice similarity coefficient of ESDSA achieves 89.37%. In addition, the dice similarity coefficient of the Spatial Self-Attention mechanism (SSA) strategy and the dual Encoding-Shared Decoding (ESD) strategy is 9.47%, 5.35% higher than that of the baseline U-net, respectively, indicating that the strategies of SSA and ESD can effectively enhance the segmentation accuracy of human brain hippocampus.

Hippocampus segmentation after brain tumor resection via postoperative region synthesis

PURPOSE

Accurately segmenting the hippocampus is an essential step in brain tumor radiotherapy planning. Some patients undergo brain tumor resection beforehand, which can significantly alter the postoperative regions' appearances and intensity of the 3D MR images. However, there are limited tumor resection patient images for deep neural networks to be effective.

METHODS

We propose a novel automatic hippocampus segmentation framework via postoperative image synthesis. The variational generative adversarial network consists of intensity alignment and a weight-map-guided feature fusion module, which transfers the postoperative regions to the preoperative images. In addition, to further boost the performance of hippocampus segmentation, We design a joint training strategy to optimize the image synthesis network and the segmentation task simultaneously.

RESULTS

Comprehensive experiments demonstrate that our proposed method on the dataset with 48 nasopharyngeal carcinoma patients and 67 brain tumor patients observes consistent improvements over state-of-the-art methods.

CONCLUSION

The proposed postoperative image synthesis method act as a novel and powerful scheme to generate additional training data. Compared with existing deep learning methods, it achieves better accuracy for hippocampus segmentation of brain tumor patients who have undergone brain tumor resection. It can be used as an automatic contouring tool for hippocampus delineation in hippocampus-sparing radiotherapy.

Automated hippocampal segmentation algorithms evaluated in stroke patients

Deep learning segmentation algorithms can produce reproducible results in a matter of seconds. However, their application to more complex datasets is uncertain and may fail in the presence of severe structural abnormalities-such as those commonly seen in stroke patients. In this investigation, six recent, deep learning-based hippocampal segmentation algorithms were tested on 641 stroke patients of a multicentric, open-source dataset ATLAS 2.0. The comparisons of the volumes showed that the methods are not interchangeable with concordance correlation coefficients from 0.266 to 0.816. While the segmentation algorithms demonstrated an overall good performance (volumetric similarity [VS] 0.816 to 0.972, DICE score 0.786 to 0.921, and Hausdorff distance [HD] 2.69 to 6.34), no single out-performing algorithm was identified: FastSurfer performed best in VS, QuickNat in DICE and average HD, and Hippodeep in HD. Segmentation performance was significantly lower for ipsilesional segmentation, with a decrease in performance as a function of lesion size due to the pathology-based domain shift. Only QuickNat showed a more robust performance in volumetric similarity. Even though there are many pre-trained segmentation methods, it is important to be aware of the possible decrease in performance for the segmentation results on the lesion side due to the pathology-based domain shift. The segmentation algorithm should be selected based on the research question and the evaluation parameter needed. More research is needed to improve current hippocampal segmentation methods.

Validation of a novel path planner for stereotactic neurosurgical interventions-A retrospective clinical study

BACKGROUND

The gold standard workflow for targeting structures in the brain involves manual path planning. This preoperative manual path planning is very time-intensive and laborious, especially when some outcome measures such as maximum ablation and penetration depth has to be optimised.

METHODS

Our novel path planner generates an optimal path which maximises the hippocampus penetration and distance from critical structures using a precomputed cost map and a reward map.

RESULTS

The average penetration ratio for 12 cases is 88.13 ± 23.23% for a resolution of 1° and a safety margin of 1 mm. Average run time for the path planner based on 1° resolution was 1.99 ± 0.68 min.

CONCLUSIONS

Results show that the algorithm can generate safe and clinically relevant paths with a quantitative representation of the penetration depth and is faster than the average reported time for manual path planning.

A benchmark for hypothalamus segmentation on T1-weighted MR images

The hypothalamus is a small brain structure that plays essential roles in sleep regulation, body temperature control, and metabolic homeostasis. Hypothalamic structural abnormalities have been reported in neuropsychiatric disorders, such as schizophrenia, amyotrophic lateral sclerosis, and Alzheimer's disease. Although mag- netic resonance (MR) imaging is the standard examination method for evaluating this region, hypothalamic morphological landmarks are unclear, leading to subjec- tivity and high variability during manual segmentation. Due to these limitations, it is common to find contradicting results in the literature regarding hypothalamic volumetry. To the best of our knowledge, only two automated methods are available in the literature for hypothalamus segmentation, the first of which is our previous method based on U-Net. However, both methods present performance losses when predicting images from different datasets than those used in training. Therefore, this project presents a benchmark consisting of a diverse T1-weighted MR image dataset comprising 1381 subjects from IXI, CC359, OASIS, and MiLI (the latter created specifically for this benchmark). All data were provided using automatically generated hypothalamic masks and a subset containing manually annotated masks. As a baseline, a method for fully automated segmentation of the hypothalamus on T1-weighted MR images with a greater generalization ability is presented. The pro- posed method is a teacher-student-based model with two blocks: segmentation and correction, where the second corrects the imperfections of the first block. After using three datasets for training (MiLI, IXI, and CC359), the prediction performance of the model was measured on two test sets: the first was composed of data from IXI, CC359, and MiLI, achieving a Dice coefficient of 0.83; the second was from OASIS, a dataset not used for training, achieving a Dice coefficient of 0.74. The dataset, the baseline model, and all necessary codes to reproduce the experiments are available at https://github.com/MICLab-Unicamp/HypAST and https://sites.google.com/ view/calgary-campinas-dataset/hypothalamus-benchmarking. In addition, a leaderboard will be maintained with predictions for the test set submitted by anyone working on the same task.

A Precise Computational Method for Hippocampus Segmentation from MRI of Brain to Assist Physicians in the Diagnosis of Alzheimer’s Disease

Hippocampus segmentation on magnetic resonance imaging is more significant for diagnosis, treatment and analyzing of neuropsychiatric disorders. Automatic segmentation is an active research field. Previous state-of-the-art hippocampus segmentation methods train their methods on healthy or Alzheimer’s disease patients from public datasets. It arises the question whether these methods are capable for recognizing the hippocampus in a different domain. Therefore, this study proposes a precise computational method for hippocampus segmentation from MRI of brain to assist physicians in the diagnosis of Alzheimer’s disease (HCS-MRI-DAD-LBP). Initially, the input images are pre-processed by Trimmed mean filter for image quality enhancement. Then the pre-processed images are given to ROI detection, ROI detection utilizes Weber’s law which determines the luminance factor of the image. In the region extraction process, Chan–Vese active contour model (ACM) and level sets are used (UACM). Finally, local binary pattern (LBP) is utilized to remove the erroneous pixel that maximizes the segmentation accuracy. The proposed model is implemented in MATLAB, and its performance is analyzed with performance metrics, like precision, recall, mean, variance, standard deviation and disc similarity coefficient. The proposed HCS-MRI-DAD-LBP method attains in OASIS dataset provides high disc similarity coefficient of 12.64%, 10.11% and 1.03% compared with the existing methods, like HCS-DAS-MLT, HCS-DAS-RNN and HCS-DAS-GMM and in ADNI dataset provides high precision of 20%, 9.09% and 1.05% compared with existing methods like HCS-MRI-DAD-CNN-ADNI, HCS-MRI-DAD-MCNN-ADNI and HCS-MRI-DAD-CNN-RNN-ADNI, respectively.

State-of-the-art techniques using pre-operative brain MRI scans for survival prediction of glioblastoma multiforme patients and future research directions

Objective

Glioblastoma multiforme (GBM) is a grade IV brain tumour with very low life expectancy. Physicians and oncologists urgently require automated techniques in clinics for brain tumour segmentation (BTS) and survival prediction (SP) of GBM patients to perform precise surgery followed by chemotherapy treatment.

Methods

This study aims at examining the recent methodologies developed using automated learning and radiomics to automate the process of SP. Automated techniques use pre-operative raw magnetic resonance imaging (MRI) scans and clinical data related to GBM patients. All SP methods submitted for the multimodal brain tumour segmentation (BraTS) challenge are examined to extract the generic workflow for SP.

Results

The maximum accuracies achieved by 21 state-of-the-art different SP techniques reviewed in this study are 65.5 and 61.7% using the validation and testing subsets of the BraTS dataset, respectively. The comparisons based on segmentation architectures, SP models, training parameters and hardware configurations have been made.

Conclusion

The limited accuracies achieved in the literature led us to review the various automated methodologies and evaluation metrics to find out the research gaps and other findings related to the survival prognosis of GBM patients so that these accuracies can be improved in future. Finally, the paper provides the most promising future research directions to improve the performance of automated SP techniques and increase their clinical relevance.

Machine learning applications on neuroimaging for diagnosis and prognosis of epilepsy: A review

Machine learning is playing an increasingly important role in medical image analysis, spawning new advances in the clinical application of neuroimaging. There have been some reviews on machine learning and epilepsy before, and they mainly focused on electrophysiological signals such as electroencephalography (EEG) and stereo electroencephalography (SEEG), while neglecting the potential of neuroimaging in epilepsy research. Neuroimaging has its important advantages in confirming the range of the epileptic region, which is essential in presurgical evaluation and assessment after surgery. However, it is difficult for EEG to locate the accurate epilepsy lesion region in the brain. In this review, we emphasize the interaction between neuroimaging and machine learning in the context of epilepsy diagnosis and prognosis. We start with an overview of epilepsy and typical neuroimaging modalities used in epilepsy clinics, MRI, DWI, fMRI, and PET. Then, we elaborate two approaches in applying machine learning methods to neuroimaging data: (i) the conventional machine learning approach combining manual feature engineering and classifiers, (ii) the deep learning approach, such as the convolutional neural networks and autoencoders. Subsequently, the application of machine learning on epilepsy neuroimaging, such as segmentation, localization, and lateralization tasks, as well as tasks directly related to diagnosis and prognosis are looked into in detail. Finally, we discuss the current achievements, challenges, and potential future directions in this field, hoping to pave the way for computer-aided diagnosis and prognosis of epilepsy.

Relationship between hippocampal subfields and Verbal and Visual memory function in Mesial Temporal Lobe Epilepsy patients

OBJECTIVE

High-resolution protocols used in magnetic resonance imaging (MRI) currently enable the detailed analysis of the hippocampus along with its subfield segmentation. The relationship between episodic memory and the hippocampus is well established, and there is growing evidence that some specific memory processing steps are associated with individual hippocampal segments, but there are inconsistencies in the literature. We focused our analysis on hippocampal subfield volumetry and neuropsychological visual and verbal memory tests in patients with temporal lobe epilepsy (TLE) presenting with unilateral hippocampal atrophy.

METHODS

The study involved a cohort of 62 patients with unilateral TLE, including unilateral hippocampal atrophy (29 on the left side) based on MRI and unequivocal ipsilateral ictal onsets based on surface video electroencephalography recordings. The hippocampal subfield volumes were evaluated using FreeSurfer version 7.1. We used the Rey-Auditory Verbal Learning Test to evaluate short-term (A1), learning (ΣA1-A5), immediate (A6), and delayed (A7) recall of episodic verbal memory. We used the Rey-Osterrieth Complex Figure Test to evaluate the immediate and delayed recall of visual memory. We analyzed the correlations between the asymmetry index scores for the hippocampal subfield volumes of thecornu ammonis (CA)1, CA2/3, and CA4 and memory test performance.

RESULTS

Moderate associations were established between the CA2/3 asymmetry index scores and visual memory in TLE (both right and left hippocampal atrophy), as well as visual memory and CA4 in the right atrophy cases. The CA1 asymmetry index scores did not correlate with any of the memory test results. We did not find any significant correlation between verbal memory tests and specific hippocampal subfields.

CONCLUSIONS

The use of high-resolution MRI protocols andin vivo automated segmentation processing revealed moderate associations between hippocampal subfields and memory parameters. Further investigations are needed to establish the utility of these results for clinical decisions.