Dataset Information

The impact of transfer learning on 3D deep learning convolutional neural network segmentation of the hippocampus in mild cognitive impairment and Alzheimer disease subjects.

ABSTRACT: Research on segmentation of the hippocampus in magnetic resonance images through deep learning convolutional neural networks (CNNs) shows promising results, suggesting that these methods can identify small structural abnormalities of the hippocampus, which are among the earliest and most frequent brain changes associated with Alzheimer disease (AD). However, CNNs typically achieve the highest accuracy on datasets acquired from the same domain as the training dataset. Transfer learning allows domain adaptation through further training on a limited dataset. In this study, we applied transfer learning on a network called spatial warping network segmentation (SWANS), developed and trained in a previous study. We used MR images of patients with clinical diagnoses of mild cognitive impairment (MCI) and AD, segmented by two different raters. By using transfer learning techniques, we developed four new models, using different training methods. Testing was performed using 26% of the original dataset, which was excluded from training as a hold-out test set. In addition, 10% of the overall training dataset was used as a hold-out validation set. Results showed that all the new models achieved better hippocampal segmentation quality than the baseline SWANS model (p_s < .001), with high similarity to the manual segmentations (mean dice [best model] = 0.878 ± 0.003). The best model was chosen based on visual assessment and volume percentage error (VPE). The increased precision in estimating hippocampal volumes allows the detection of small hippocampal abnormalities already present in the MCI phase (SD = [3.9 ± 0.6]%), which may be crucial for early diagnosis.

SUBMITTER: Balboni E

PROVIDER: S-EPMC9248306 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background and purposeManually drawn VOI-based analysis shows a decrease in magnetization transfer ratio in the hippocampus of patients with Alzheimer disease. We investigated with whole-brain voxelwise analysis the regional changes of the magnetization transfer ratio in patients with mild Alzheimer disease and patients with amnestic mild cognitive impairment.Materials and methodsTwenty patients with mild Alzheimer disease, 27 patients with amnestic mild cognitive impairment, and 30 healthy elderly control subjects were examined with high-resolution T1WI and 3-mm-thick magnetization transfer images. Whole-brain voxelwise analysis of magnetization transfer ratio maps was performed by use of Statistical Parametric Mapping 8 software and was supplemented by the analysis of the magnetization transfer ratio in FreeSurfer parcellation-derived VOIs.ResultsVoxelwise analysis showed 2 clusters of significantly decreased magnetization transfer ratio in the left hippocampus and amygdala and in the left posterior mesial temporal cortex (fusiform gyrus) of patients with Alzheimer disease as compared with control subjects but no difference between patients with amnestic mild cognitive impairment and either patients with Alzheimer disease or control subjects. VOI analysis showed that the magnetization transfer ratio in the hippocampus and amygdala was significantly lower (bilaterally) in patients with Alzheimer disease when compared with control subjects (ANOVA with Bonferroni correction, at P < .05). Mean magnetization transfer ratio values in the hippocampus and amygdala in patients with amnestic mild cognitive impairment were between those of healthy control subjects and those of patients with mild Alzheimer disease. Support vector machine-based classification demonstrated improved classification performance after inclusion of magnetization transfer ratio-related features, especially between patients with Alzheimer disease versus healthy subjects.ConclusionsBilateral but asymmetric decrease of magnetization transfer ratio reflecting microstructural changes of the residual GM is present not only in the hippocampus but also in the amygdala in patients with mild Alzheimer disease.

Project description:BackgroundDetection of mild cognitive impairment (MCI) is essential to screen high risk of Alzheimer's disease (AD). However, subtle changes during MCI make it challenging to classify in machine learning. The previous pathological analysis pointed out that the hippocampus is the critical hub for the white matter (WM) network of MCI. Damage to the white matter pathways around the hippocampus is the main cause of memory decline in MCI. Therefore, it is vital to biologically extract features from the WM network driven by hippocampus-related regions to improve classification performance.MethodsOur study proposes a method for feature extraction of the whole-brain WM network. First, 42 MCI and 54 normal control (NC) subjects were recruited using diffusion tensor imaging (DTI), resting-state functional magnetic resonance imaging (rs-fMRI), and T1-weighted (T1w) imaging. Second, mean diffusivity (MD) and fractional anisotropy (FA) were calculated from DTI, and the whole-brain WM networks were obtained. Third, regions of interest (ROIs) with significant functional connectivity to the hippocampus were selected for feature extraction, and the hippocampus (HIP)-related WM networks were obtained. Furthermore, the rank sum test with Bonferroni correction was used to retain significantly different connectivity between MCI and NC, and significant HIP-related WM networks were obtained. Finally, the classification performances of these three WM networks were compared to select the optimal feature and classifier.Results(1) For the features, the whole-brain WM network, HIP-related WM network, and significant HIP-related WM network are significantly improved in turn. Also, the accuracy of MD networks as features is better than FA. (2) For the classification algorithm, the support vector machine (SVM) classifier with radial basis function, taking the significant HIP-related WM network in MD as a feature, has the optimal classification performance (accuracy = 89.4%, AUC = 0.954). (3) For the pathologic mechanism, the hippocampus and thalamus are crucial hubs of the WM network for MCI.ConclusionFeature extraction from the WM network driven by hippocampus-related regions provides an effective method for the early diagnosis of AD.

Dataset Information

The impact of transfer learning on 3D deep learning convolutional neural network segmentation of the hippocampus in mild cognitive impairment and Alzheimer disease subjects.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets