Hippocampus segmentation on MRI (magnetic resonance imaging) plays a vital role in detecting, diagnosing, tracking, and monitoring neurodegenerative diseases, particularly Alzheimer’s disease. While larger datasets often provide an advantage in deep learning-based segmentation, smaller datasets pose unique challenges due to limited data variability and an increased risk of overfitting. This study addresses these challenges by developing a computationally efficient and accurate 3D U-Net model tailored for hippocampus segmentation. The proposed approach employs a preprocessing pipeline combining 3D Contrast Limited Adaptive Histogram Equalization (CLAHE) and Selective Coefficient-Enhanced 3D Wavelet Transform (SCE-3DWT), which enhances contrast and reduces noise for improved feature extraction. The experimental evaluation was conducted using the EADC-ADNI HarP dataset, comprising 135 hippocampal MRI scans with an input image size of 64×64×96. The model achieved a Dice coefficient of 0.8838 and a Jaccard Index of 0.7920, surpassing recent state-of-the-art methods. Comparative analysis highlights reduced Over-Segmentation Ratio (OSR = FP/(FP+TP), 0.0594) and Under-Segmentation Ratio (USR = FN/(FN+TP), 0.0569, reflecting its robustness and generalization. The lightweight architecture, designed with a maximum filter size of 512, operates efficiently without relying on transfer learning, making it accessible for broader applications. Future work will focus on integrating post processing techniques, leveraging larger and more diverse datasets, and exploring higher-resolution volumetric data to further improve segmentation accuracy and clinical utility. This study contributes to the advancement of medical image analysis, offering a resource-efficient framework for precise hippocampus segmentation, with potential implications for improved Alzheimer’s disease management.

Accurate hippocampal segmentation in 3D MRI is essential for neurodegenerative disease research and diagnosis. Preprocessing pipelines can strongly influence segmentation accuracy, yet their impact across datasets and in transfer learning scenarios remains underexplored. This study systematically compares a No Preprocessing (NP) pipeline and a Full Preprocessing (FP) pipeline for hippocampal segmentation on the EADC-ADNI HarP clinical dataset and the multi-site MSD dataset using a 3D U-Net with residual connections and dropout regularization. Evaluations employed standard overlap metrics, Hausdorff Distance (HD), and Wilcoxon signed-rank tests, complemented by qualitative analysis. Results show that NP consistently outperformed FP in Dice, Jaccard, and F1 metrics on HarP (e.g., Dice 0.8876 vs. 0.8753, p < 0.05), while FP achieved superior HD, indicating better boundary precision. Similar trends emerged in transfer learning from MSD to HarP, with NP improving overlap measures and FP maintaining lower HD. To test whether the findings generalize across architectures, experiments on Harp Dataset were also repeated with a 3D V-Net backbone, which reproduced the same trend. Comparative analysis with recent studies confirmed the competitiveness of the proposed approach despite lower input resolution and reduced model complexity. These findings highlight that preprocessing choice should be tailored to dataset characteristics and the target evaluation metric. The results provide practical guidance for selecting segmentation workflows in clinical and multi-center neuroimaging applications.

Background/Objectives: Existing Alzheimer’s disease (AD) prediction studies often treat APOE ε4 as a binary carrier variable and emphasize classification rather than time-to-event progression. This study evaluated whether APOE ε4 allele dose predicts clinical conversion from mild cognitive impairment (MCI) to AD dementia/probable AD in a longitudinal survival framework adjusted for hippocampal volume and baseline cognition. Methods: We analyzed 1115 Alzheimer’s Disease Neuroimaging Initiative (ADNI) participants with baseline MCI, APOE genotype data, and at least one follow-up visit, grouped by APOE ε4 allele count (0, 1, or 2). Kaplan–Meier curves, Bonferroni-corrected log-rank tests, nested Cox models, interaction testing, and twelve sensitivity and robustness analyses were performed. Results: During 3.73 ± 3.38 years of mean follow-up, 399 participants (35.8%) clinically converted. Median conversion-free survival was 18.47 years for non-carriers, 4.32 years for heterozygotes, and 3.41 years for homozygotes, although the non-carrier median occurred late in follow-up. In the fully adjusted Cox model, APOE ε4 dose remained associated with conversion hazard (HR = 1.580, 95% CI 1.362–1.834, p < 0.0001). Intracranial Volume (ICV)-adjusted hippocampal volume was protective (HR = 0.620, 95% CI 0.566–0.680, p < 0.0001), and the model achieved a Concordance Index (C-index) of 0.805. The APOE ε4 × hippocampal volume interaction was not significant (likelihood ratio test p = 0.098). Sensitivity analyses supported robustness, although the APOE ε4 association was attenuated in the exploratory amyloid-positive CSF subgroup. Conclusions: These findings support APOE ε4 allele dose as a statistical marker of clinical progression risk in ADNI, not as evidence of biomarker-confirmed AD progression or distinct mechanisms.