Improved Segmentation of the Intracranial and Ventricular Volumes in Populations with Cerebrovascular Lesions and Atrophy Using 3D CNNs

Deep Learning for Automated Ventricle and Periventricular Space Segmentation on CT and T1CE MRI in Neuro-Oncology Patients

PURPOSE

This study aims to create a deep learning (DL) model capable of accurately delineating the ventricles, and by extension, the periventricular space (PVS), following the 2021 EPTN Neuro-Oncology Atlas guidelines on T1-weighted contrast-enhanced MRI scans (T1CE). The performance of this DL model was quantitatively and qualitatively compared with an off-the-shelf model.

MATERIALS AND METHODS

An nnU-Net was trained for ventricle segmentation using both CT and T1CE MRI images from 78 patients. Its performance was compared to that of a publicly available pretrained segmentation model, SynthSeg. The evaluation was conducted on both internal (N = 18) and external (n = 18) test sets, with each consisting of paired CT and T1CE MRI images and expert-delineated ground truths (GTs). Segmentation accuracy was assessed using the volumetric Dice Similarity Coefficient (DSC), 95th percentile Hausdorff distance (HD95), surface DSC, and added path length (APL). Additionally, a local evaluation of ventricle segmentations quantified differences between manual and automatic segmentations across both test sets. All segmentations were scored by radiotherapy technicians for clinical acceptability using a 4-point Likert scale.

RESULTS

The nnU-Net significantly outperformed the SynthSeg model on the internal test dataset in terms of median [range] DSC, 0.93 [0.86-0.95] vs. 0.85 [0.67-0.91], HD95, 0.9 [0.7-2.5] mm vs. 2.2 [1.7-4.8] mm, surface DSC, 0.97 [0.90-0.98] vs. 0.84 [0.70-0.89], and APL, 876 [407-1298] mm vs. 2809 [2311-3622] mm, all with p < 0.001. No significant differences in these metrics were found in the external test set. However clinical ratings favored nnU-Net segmentations on the internal and external test sets. In addition, the nnU-Net had higher clinical ratings than the GT delineation on the internal and external test set.

CONCLUSIONS

The nnU-Net model outperformed the SynthSeg model on the internal dataset in both segmentation metrics and clinician ratings. While segmentation metrics showed no significant differences between the models on the external set, clinician ratings favored nnU-Net, suggesting enhanced clinical acceptability. This suggests that nnU-Net could contribute to more time-efficient and streamlined radiotherapy planning workflows.

Assessing CT-based Volumetric Analysis via Transfer Learning with MRI and Manual Labels for Idiopathic Normal Pressure Hydrocephalus

Background

Brain computed tomography (CT) is an accessible and commonly utilized technique for assessing brain structure. In cases of idiopathic normal pressure hydrocephalus (iNPH), the presence of ventriculomegaly is often neuroradiologically evaluated by visual rating and manually measuring each image. Previously, we have developed and tested a deep-learning-model that utilizes transfer learning from magnetic resonance imaging (MRI) for CT-based intracranial tissue segmentation. Accordingly, herein we aimed to enhance the segmentation of ventricular cerebrospinal fluid (VCSF) in brain CT scans and assess the performance of automated brain CT volumetrics in iNPH patient diagnostics.

Methods

The development of the model used a two-stage approach. Initially, a 2D U-Net model was trained to predict VCSF segmentations from CT scans, using paired MR-VCSF labels from healthy controls. This model was subsequently refined by incorporating manually segmented lateral CT-VCSF labels from iNPH patients, building on the features learned from the initial U-Net model. The training dataset included 734 CT datasets from healthy controls paired with T1-weighted MRI scans from the Gothenburg H70 Birth Cohort Studies and 62 CT scans from iNPH patients at Uppsala University Hospital. To validate the model's performance across diverse patient populations, external clinical images including scans of 11 iNPH patients from the Universitatsmedizin Rostock, Germany, and 30 iNPH patients from the University of Alabama at Birmingham, United States were used. Further, we obtained three CT-based volumetric measures (CTVMs) related to iNPH.

Results

Our analyses demonstrated strong volumetric correlations (ϱ=0.91, p<0.001) between automatically and manually derived CT-VCSF measurements in iNPH patients. The CTVMs exhibited high accuracy in differentiating iNPH patients from controls in external clinical datasets with an AUC of 0.97 and in the Uppsala University Hospital datasets with an AUC of 0.99.

Discussion

CTVMs derived through deep learning, show potential for assessing and quantifying morphological features in hydrocephalus. Critically, these measures performed comparably to gold-standard neuroradiology assessments in distinguishing iNPH from healthy controls, even in the presence of intraventricular shunt catheters. Accordingly, such an approach may serve to improve the radiological evaluation of iNPH diagnosis/monitoring (i.e., treatment responses). Since CT is much more widely available than MRI, our results have considerable clinical impact.

Tau follows principal axes of functional and structural brain organization in Alzheimer's disease

Alzheimer's disease (AD) is a brain network disorder where pathological proteins accumulate through networks and drive cognitive decline. Yet, the role of network connectivity in facilitating this accumulation remains unclear. Using in-vivo multimodal imaging, we show that the distribution of tau and reactive microglia in humans follows spatial patterns of connectivity variation, the so-called gradients of brain organization. Notably, less distinct connectivity patterns ("gradient contraction") are associated with cognitive decline in regions with greater tau, suggesting an interaction between reduced network differentiation and tau on cognition. Furthermore, by modeling tau in subject-specific gradient space, we demonstrate that tau accumulation in the frontoparietal and temporo-occipital cortices is associated with greater baseline tau within their functionally and structurally connected hubs, respectively. Our work unveils a role for both functional and structural brain organization in pathology accumulation in AD, and supports subject-specific gradient space as a promising tool to map disease progression.

Distinct brain morphometry patterns revealed by deep learning improve prediction of post-stroke aphasia severity

BACKGROUND

Emerging evidence suggests that post-stroke aphasia severity depends on the integrity of the brain beyond the lesion. While measures of lesion anatomy and brain integrity combine synergistically to explain aphasic symptoms, substantial interindividual variability remains unaccounted. One explanatory factor may be the spatial distribution of morphometry beyond the lesion (e.g., atrophy), including not just specific brain areas, but distinct three-dimensional patterns.

METHODS

Here, we test whether deep learning with Convolutional Neural Networks (CNNs) on whole brain morphometry (i.e., segmented tissue volumes) and lesion anatomy better predicts chronic stroke individuals with severe aphasia (N = 231) than classical machine learning (Support Vector Machines; SVMs), evaluating whether encoding spatial dependencies identifies uniquely predictive patterns.

RESULTS

CNNs achieve higher balanced accuracy and F1 scores, even when SVMs are nonlinear or integrate linear or nonlinear dimensionality reduction. Parity only occurs when SVMs access features learned by CNNs. Saliency maps demonstrate that CNNs leverage distributed morphometry patterns, whereas SVMs focus on the area around the lesion. Ensemble clustering of CNN saliencies reveals distinct morphometry patterns unrelated to lesion size, consistent across individuals, and which implicate unique networks associated with different cognitive processes as measured by the wider neuroimaging literature. Individualized predictions depend on both ipsilateral and contralateral features outside the lesion.

CONCLUSIONS

Three-dimensional network distributions of morphometry are directly associated with aphasia severity, underscoring the potential for CNNs to improve outcome prognostication from neuroimaging data, and highlighting the prospective benefits of interrogating spatial dependence at different scales in multivariate feature space.

Deep learning applications in vascular dementia using neuroimaging

PURPOSE OF REVIEW

Vascular dementia (VaD) is the second common cause of dementia after Alzheimer's disease, and deep learning has emerged as a critical tool in dementia research. The aim of this article is to highlight the current deep learning applications in VaD-related imaging biomarkers and diagnosis.

RECENT FINDINGS

The main deep learning technology applied in VaD using neuroimaging data is convolutional neural networks (CNN). CNN models have been widely used for lesion detection and segmentation, such as white matter hyperintensities (WMH), cerebral microbleeds (CMBs), perivascular spaces (PVS), lacunes, cortical superficial siderosis, and brain atrophy. Applications in VaD subtypes classification also showed excellent results. CNN-based deep learning models have potential for further diagnosis and prognosis of VaD.

SUMMARY

Deep learning neural networks with neuroimaging data in VaD research represent significant promise for advancing early diagnosis and treatment strategies. Ongoing research and collaboration between clinicians, data scientists, and neuroimaging experts are essential to address challenges and unlock the full potential of deep learning in VaD diagnosis and management.

Advanced brain imaging for the diagnosis of Alzheimer disease

PURPOSE OF REVIEW

The purpose is to review the latest advances of brain imaging for the diagnosis of Alzheimer disease (AD).

RECENT FINDINGS

Brain imaging techniques provide valuable and complementary information to support the diagnosis of Alzheimer disease in clinical and research settings. The recent FDA accelerated approvals of aducanumab, lecanemab and donanemab made amyloid-PET critical in helping determine the optimal window for anti-amyloid therapeutic interventions. Tau-PET, on the other hand, is considered of key importance for the tracking of disease progression and for monitoring therapeutic interventions in clinical trials. PET imaging for microglial activation, astrocyte reactivity and synaptic degeneration are still new techniques only used in the research field, and more studies are needed to validate their use in the clinical diagnosis of AD. Finally, artificial intelligence has opened new prospective in the early detection of AD using MRI modalities.

SUMMARY

Brain imaging techniques using PET improve our understanding of the different AD-related pathologies and their relationship with each other along the course of disease. With more robust validation, machine learning and deep learning algorithms could be integrated with neuroimaging modalities to serve as valuable tools for clinicians to make early diagnosis and prognosis of AD.

Development and validation of a deep learning-based automatic segmentation model for assessing intracranial volume: comparison with NeuroQuant, FreeSurfer, and SynthSeg

Background and purpose

To develop and validate a deep learning-based automatic segmentation model for assessing intracranial volume (ICV) and to compare the accuracy determined by NeuroQuant (NQ), FreeSurfer (FS), and SynthSeg.

Materials and methods

This retrospective study included 60 subjects [30 Alzheimer's disease (AD), 21 mild cognitive impairment (MCI), 9 cognitively normal (CN)] from a single tertiary hospital for the training and validation group (50:10). The test group included 40 subjects (20 AD, 10 MCI, 10 CN) from the ADNI dataset. We propose a robust ICV segmentation model based on the foundational 2D UNet architecture trained with four types of input images (both single and multimodality using scaled or unscaled T1-weighted and T2-FLAIR MR images). To compare with our model, NQ, FS, and SynthSeg were also utilized in the test group. We evaluated the model performance by measuring the Dice similarity coefficient (DSC) and average volume difference.

Results

The single-modality model trained with scaled T1-weighted images showed excellent performance with a DSC of 0.989 ± 0.002 and an average volume difference of 0.46% ± 0.38%. Our multimodality model trained with both unscaled T1-weighted and T2-FLAIR images showed similar performance with a DSC of 0.988 ± 0.002 and an average volume difference of 0.47% ± 0.35%. The overall average volume difference with our model showed relatively higher accuracy than NQ (2.15% ± 1.72%), FS (3.69% ± 2.93%), and SynthSeg (1.88% ± 1.18%). Furthermore, our model outperformed the three others in each subgroup of patients with AD, MCI, and CN subjects.

Conclusion

Our deep learning-based automatic ICV segmentation model showed excellent performance for the automatic evaluation of ICV.

Accuracy of skull stripping in a single-contrast convolutional neural network model using eight-contrast magnetic resonance images

In automated analyses of brain morphometry, skull stripping or brain extraction is a critical first step because it provides accurate spatial registration and signal-intensity normalization. Therefore, it is imperative to develop an ideal skull-stripping method in the field of brain image analysis. Previous reports have shown that convolutional neural network (CNN) method is better at skull stripping than non-CNN methods. We aimed to evaluate the accuracy of skull stripping in a single-contrast CNN model using eight-contrast magnetic resonance (MR) images. A total of 12 healthy participants and 12 patients with a clinical diagnosis of unilateral Sturge-Weber syndrome were included in our study. A 3-T MR imaging system and QRAPMASTER were used for data acquisition. We obtained eight-contrast images produced by post-processing T1, T2, and proton density (PD) maps. To evaluate the accuracy of skull stripping in our CNN method, gold-standard intracranial volume (ICVG) masks were used to train the CNN model. The ICVG masks were defined by experts using manual tracing. The accuracy of the intracranial volume obtained from the single-contrast CNN model (ICVE) was evaluated using the Dice similarity coefficient [= 2(ICVE ⋂ ICVG)/(ICVE + ICVG)]. Our study showed significantly higher accuracy in the PD-weighted image (WI), phase-sensitive inversion recovery (PSIR), and PD-short tau inversion recovery (STIR) compared to the other three contrast images (T1-WI, T2-fluid-attenuated inversion recovery [FLAIR], and T1-FLAIR). In conclusion, PD-WI, PSIR, and PD-STIR should be used instead of T1-WI for skull stripping in the CNN models.

Amyloid-PET of the white matter: Relationship to free water, fiber integrity, and cognition in patients with dementia and small vessel disease

White matter (WM) injury is frequently observed along with dementia. Positron emission tomography with amyloid-ligands (Aβ-PET) recently gained interest for detecting WM injury. Yet, little is understood about the origin of the altered Aβ-PET signal in WM regions. Here, we investigated the relative contributions of diffusion MRI-based microstructural alterations, including free water and tissue-specific properties, to Aβ-PET in WM and to cognition. We included a unique cohort of 115 participants covering the spectrum of low-to-severe white matter hyperintensity (WMH) burden and cognitively normal to dementia. We applied a bi-tensor diffusion-MRI model that differentiates between (i) the extracellular WM compartment (represented via free water), and (ii) the fiber-specific compartment (via free water-adjusted fractional anisotropy [FA]). We observed that, in regions of WMH, a decrease in Aβ-PET related most closely to higher free water and higher WMH volume. In contrast, in normal-appearing WM, an increase in Aβ-PET related more closely to higher cortical Aβ (together with lower free water-adjusted FA). In relation to cognitive impairment, we observed a closer relationship with higher free water than with either free water-adjusted FA or WM PET. Our findings support free water and Aβ-PET as markers of WM abnormalities in patients with mixed dementia, and contribute to a better understanding of processes giving rise to the WM PET signal.

AI-based medical e-diagnosis for fast and automatic ventricular volume measurement in patients with normal pressure hydrocephalus

Based on CT and MRI images acquired from normal pressure hydrocephalus (NPH) patients, using machine learning methods, we aim to establish a multimodal and high-performance automatic ventricle segmentation method to achieve an efficient and accurate automatic measurement of the ventricular volume. First, we extract the brain CT and MRI images of 143 definite NPH patients. Second, we manually label the ventricular volume (VV) and intracranial volume (ICV). Then, we use the machine learning method to extract features and establish automatic ventricle segmentation model. Finally, we verify the reliability of the model and achieved automatic measurement of VV and ICV. In CT images, the Dice similarity coefficient (DSC), intraclass correlation coefficient (ICC), Pearson correlation, and Bland-Altman analysis of the automatic and manual segmentation result of the VV were 0.95, 0.99, 0.99, and 4.2 ± 2.6, respectively. The results of ICV were 0.96, 0.99, 0.99, and 6.0 ± 3.8, respectively. The whole process takes 3.4 ± 0.3 s. In MRI images, the DSC, ICC, Pearson correlation, and Bland-Altman analysis of the automatic and manual segmentation result of the VV were 0.94, 0.99, 0.99, and 2.0 ± 0.6, respectively. The results of ICV were 0.93, 0.99, 0.99, and 7.9 ± 3.8, respectively. The whole process took 1.9 ± 0.1 s. We have established a multimodal and high-performance automatic ventricle segmentation method to achieve efficient and accurate automatic measurement of the ventricular volume of NPH patients. This can help clinicians quickly and accurately understand the situation of NPH patient's ventricles.

Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation

White matter hyperintensities (WMHs) are frequently observed on structural neuroimaging of elderly populations and are associated with cognitive decline and increased risk of dementia. Many existing WMH segmentation algorithms produce suboptimal results in populations with vascular lesions or brain atrophy, or require parameter tuning and are computationally expensive. Additionally, most algorithms do not generate a confidence estimate of segmentation quality, limiting their interpretation. MRI‐based segmentation methods are often sensitive to acquisition protocols, scanners, noise‐level, and image contrast, failing to generalize to other populations and out‐of‐distribution datasets. Given these concerns, we propose a novel Bayesian 3D convolutional neural network with a U‐Net architecture that automatically segments WMH, provides uncertainty estimates of the segmentation output for quality control, and is robust to changes in acquisition protocols. We also provide a second model to differentiate deep and periventricular WMH. Four hundred thirty‐two subjects were recruited to train the CNNs from four multisite imaging studies. A separate test set of 158 subjects was used for evaluation, including an unseen multisite study. We compared our model to two established state‐of‐the‐art techniques (BIANCA and DeepMedic), highlighting its accuracy and efficiency. Our Bayesian 3D U‐Net achieved the highest Dice similarity coefficient of 0.89 ± 0.08 and the lowest modified Hausdorff distance of 2.98 ± 4.40 mm. We further validated our models highlighting their robustness on “clinical adversarial cases” simulating data with low signal‐to‐noise ratio, low resolution, and different contrast (stemming from MRI sequences with different parameters). Our pipeline and models are available at: https://hypermapp3r.readthedocs.io.

Application of Evans Index in Normal Pressure Hydrocephalus Patients: A Mini Review

With an ever-growing aging population, the prevalence of normal pressure hydrocephalus (NPH) is increasing. Clinical symptoms of NPH include cognitive impairment, gait disturbance, and urinary incontinence. Surgery can improve symptoms, which leads to the disease's alternative name: treatable dementia. The Evans index (EI), defined as the ratio of the maximal width of the frontal horns to the maximum inner skull diameter, is the most commonly used index to indirectly assess the condition of the ventricles in NPH patients. EI measurement is simple, fast, and does not require any special software; in clinical practice, an EI >0.3 is the criterion for ventricular enlargement. However, EI's measurement methods, threshold setting, correlation with ventricle volume, and even its clinical value has been questioned. Based on the EI, the z-EI and anteroposterior diameter of the lateral ventricle index were derived and are discussed in this review.

Differential Cognitive Decline in Alzheimer's Disease Is Predicted by Changes in Ventricular Size but Moderated by Apolipoprotein E and Pulse Pressure

BACKGROUND

Differential cognitive trajectories in Alzheimer's disease (AD) may be predicted by biomarkers from multiple domains.

OBJECTIVE

In a longitudinal sample of AD and AD-related dementias patients (n = 312), we tested whether 1) change in brain morphometry (ventricular enlargement) predicts differential cognitive trajectories, 2) further risk is contributed by genetic (Apolipoprotein E [APOE] ɛ4+) and vascular (pulse pressure [PP]) factors separately, and 3) the genetic + vascular risk moderates this pattern.

METHODS

We applied a dynamic computational approach (parallel process models) to test both concurrent and change-related associations between predictor (ventricular size) and cognition (executive function [EF]/attention). We then tested these associations as stratified by APOE (ɛ4-/ɛ4+), PP (low/high), and APOE+ PP (low/intermediate/high) risk.

RESULTS

First, concurrently, higher ventricular size predicted lower EF/attention performance and, longitudinally, increasing ventricular size predicted steeper EF/attention decline. Second, concurrently, higher ventricular size predicted lower EF/attention performance selectively in APOEɛ4+ carriers, and longitudinally, increasing ventricular size predicted steeper EF/attention decline selectively in the low PP group. Third, ventricular size and EF/attention associations were absent in the high APOE+ PP risk group both concurrently and longitudinally.

CONCLUSION

As AD progresses, a threshold effect may be present in which ventricular enlargement in the context of exacerbated APOE+ PP risk does not produce further cognitive decline.

Brain atrophy trajectories predict differential functional performance in Alzheimer's disease: Moderations with apolipoprotein E and sex

INTRODUCTION

We examine whether distinct brain atrophy patterns (using brain parenchymal fraction [BPF]) differentially predict functional performance and decline in Alzheimer's disease (AD), and are independently moderated by (1) a key AD genetic risk marker (apolipoprotein E [APOE]), (2) sex, and (3) high-risk group (women APOE ɛ4 carriers).

METHODS

We used a 2-year longitudinal sample of AD patients (baseline N = 170; mean age = 71.3 [9.1] years) from the Sunnybrook Dementia Study. We applied latent class analysis, latent growth modeling, and path analysis. We aimed to replicate our findings (N = 184) in the Alzheimer's Disease Neuroimaging Initiative.

RESULTS

We observed that high brain atrophy class predicted lower functional performance and steeper decline. This association was moderated by APOE, sex, and high-risk group. Baseline findings as moderated by APOE and high-risk group were replicated.

DISCUSSION

Women APOE ɛ4 carriers may selectively be at a greater risk of functional impairment with higher brain atrophy.