IdenBAT: Disentangled Representation Learning for Identity-Preserved Brain Age Transformation

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,