Jain Chirag Shantilal supervised by Prof. Bapiraju Surampudi received his  Master of Science –  Dual Degree in Lateral Electronics and Communication Engineering  (LED). Here’s a summary of his research work on Function from Structure: Predicting Functional States Of Brain From Axonal Connections Using Diffusion Wavelets: 

 Understanding the complex relationship between brain Structural Connectivity (SC) and Functional Connectivity (FC) remains a central challenge in computational neuroscience. A popular class of approaches models this relationship by simulating diffusion processes on the structural connectome to approximate functional patterns. While prior works have explored such models using fixed or multi-scale Graph Diffusion Kernels, they typically lack spatial specificity, as they do not associate diffusion parameters with individual brain Regions of Interest (RoIs). This limits the biological interpretability and precision of the models.

 In this work, we introduce a novel framework based on Graph Diffusion Wavelets, which enable learning region-specific diffusion scales to more accurately capture the mapping from SC to FC. By leveraging the multi-scale and localized nature of diffusion wavelets, our method uncovers how spatial communication varies across brain regions. Evaluated on the Human Connectome Project (HCP) dataset, our model achieves a high average Pearson correlation coefficient of 0.833 between predicted and empirical FC, outperforming several existing state-of-the-art methods.

 Importantly, the proposed architecture is linear and computationally efficient, and it reveals that the distribution of diffusion scales follows a power-law, indicative of scale-free dynamics. This is consistent with known organizational principles of the brain. Notably, we find that the bilateral frontal pole exhibits the largest diffusion scales, suggesting its integrative role within large-scale Resting-State Networks (RSNs). These findings align with previous literature on the frontal pole’s role in high-level cognitive functions. Overall, our results highlight the potential of graph diffusion wavelets as both a predictive and interpretable tool for studying brain structure-function coupling. The thesis also includes application of spectral graph theoretic method to relate the structural features like curvature to physiological traits like age and sex. Finally, the thesis is concluded by summarizing and proposing research directions.

July 2025