Brain aging represents an intrinsic biological phenomenon marked by discernible morphological changes within the human brain Fjell and Walhovd (2010). In the analysis of brain aging using medical imaging, structural magnetic resonance imaging (sMRI) plays a crucial role as they provide detailed insights into age-related variations and assist in accurate assessments of these alterations. Advances in sMRI-based age transformation have especially allowed researchers and clinicians to visualize and quantify patient-specific intricate brain maturation and degeneration patterns, facilitating medical diagnosis advancements. These capabilities can be pivotal for longitudinal studies to track cognitive or health state progressions over time Cole, Ritchie, Bastin, Hernández, Muñoz Maniega, Royle, Corley, Pattie, Harris, Zhang et al. (2018); Huizinga, Poot, Vernooij, Roshchupkin, Bron, Ikram, Rueckert, Niessen, Klein, Initiative et al. (2018), whereas brain age transformation with preserving patient traits remains a formidable challenge. Because most methods even change characteristics unrelated to aging during the transformation process, the crux lies in modeling the aging process without distorting personal identities intrinsic to each subject Xia, Chartsias, Wang, Tsaftaris, Initiative et al. (2021). When the aging model fails to preserve personal properties regarding identity, it may lead to misinterpretations of age-related changes, potentially compromising the accuracy and reliability of diagnostic decisions. Previous brain age transformation studies Huizinga et al. (2018); Zhang, Shi, Wu, Wang, Yap and Shen (2016); Zhao, Adeli, Honnorat, Leng and Pohl (2019); Lorenzi, Pennec, Frisoni, Ayache, Initiative et al. (2015); Sivera, Delingette, Lorenzi, Pennec, Ayache, Initiative et al. (2019) have often relied on prototype-based strategies that compare averaged brain patterns across different age groups. While these approaches aid in understanding generalized characteristics shared among age groups, they tend to neglect the unique traits of individual subjects. Recently, with the emergence of generative models using longitudinal data Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville and Bengio (2014); Makhzani, Shlens, Jaitly, Goodfellow and Frey (2015), researchers have gained the ability to create more accurate and realistic simulations of brain aging by virtue of the advantages of its data, which comprised MRI scans of the same subject at multiple time points Rachmadi, del C. Valdés-Hernández, Makin,

Alzheimer's disease (AD) is a devastating neurodegenerative condition that precedes progressive and irreversible dementia; thus, predicting its progression over time is vital for clinical diagnosis and treatment. Numerous studies have implemented structural magnetic resonance imaging (MRI) to model AD progression, focusing on three integral aspects: (i) temporal variability, (ii) incomplete observations, and (iii) temporal geometric characteristics. However, deep learning-based approaches regarding data variability and sparsity have yet to consider inherent geometrical properties sufficiently. The ordinary differential equation-based geometric modeling method (ODE-RGRU) has recently emerged as a promising strategy for modeling time-series data by intertwining a recurrent neural network and an ODE in Riemannian space. Despite its achievements, ODE-RGRU encounters limitations when extrapolating positive definite symmetric metrics from incomplete samples, leading to feature reverse occurrences that are particularly problematic, especially within the clinical facet. Therefore, this study proposes a novel geometric learning approach that models longitudinal MRI biomarkers and cognitive scores by combining three modules: topological space shift, ODE-RGRU, and trajectory estimation. We have also developed a training algorithm that integrates manifold mapping with monotonicity constraints to reflect measurement transition irreversibility. We verify our proposed method's efficacy by predicting clinical labels and cognitive scores over time in regular and irregular settings. Furthermore, we thoroughly analyze our proposed framework through an ablation study.

Deep learning (DL) for predicting Alzheimer's disease (AD) has provided timely intervention in disease progression yet still demands attentive interpretability to explain how their DL models make definitive decisions. Recently, counterfactual reasoning has gained increasing attention in medical research because of its ability to provide a refined visual explanatory map. However, such visual explanatory maps based on visual inspection alone are insufficient unless we intuitively demonstrate their medical or neuroscientific validity via quantitative features. In this study, we synthesize the counterfactual-labeled structural MRIs using our proposed framework and transform it into a gray matter density map to measure its volumetric changes over the parcellated region of interest (ROI). We also devised a lightweight linear classifier to boost the effectiveness of constructed ROIs, promoted quantitative interpretation, and achieved comparable predictive performance to DL methods. Throughout this, our framework produces an ``AD-relatedness index'' for each ROI and offers an intuitive understanding of brain status for an individual patient and across patient groups with respect to AD progression.

Deep learning models based on resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used to diagnose brain diseases, particularly autism spectrum disorder (ASD). Existing studies have leveraged the functional connectivity (FC) of rs-fMRI, achieving notable classification performance. However, they have significant limitations, including the lack of adequate information while using linear low-order FC as inputs to the model, not considering individual characteristics (i.e., different symptoms or varying stages of severity) among patients with ASD, and the non-explainability of the decision process. To cover these limitations, we propose a novel explainability-guided region of interest (ROI) selection (EAG-RS) framework that identifies non-linear high-order functional associations among brain regions by leveraging an explainable artificial intelligence technique and selects class-discriminative regions for brain disease identification. The proposed framework includes three steps: (i) inter-regional relation learning to estimate non-linear relations through random seed-based network masking, (ii) explainable connection-wise relevance score estimation to explore high-order relations between functional connections, and (iii) non-linear high-order FC-based diagnosis-informative ROI selection and classifier learning to identify ASD. We validated the effectiveness of our proposed method by conducting experiments using the Autism Brain Imaging Database Exchange (ABIDE) dataset, demonstrating that the proposed method outperforms other comparative methods in terms of various evaluation metrics. Furthermore, we qualitatively analyzed the selected ROIs and identified ASD subtypes linked to previous neuroscientific studies.

Although recent advances in deep learning accelerated an improvement in a weakly supervised object localization (WSOL) task, there are still challenges to identify the entire body of an object, rather than only discriminative parts. In this paper, we propose a novel residual fine-grained attention (RFGA) module that autonomously excites the less activated regions of an object by utilizing information distributed over channels and locations within feature maps in combination with a residual operation. To be specific, we devise a series of mechanisms of triple-view attention representation, attention expansion, and feature calibration. Unlike other attention-based WSOL methods that learn a coarse attention map, having the same values across elements in feature maps, our proposed RFGA learns fine-grained values in an attention map by assigning different attention values for each of the elements. We validated the superiority of our proposed RFGA module by comparing it with the recent methods in the literature over three datasets. Further, we analyzed the effect of each mechanism in our RFGA and visualized attention maps to get insights.