Personalized visual encoding model construction with small data
This enables efficient creation of accurate, personalized brain encoding models for new individuals in neuroscience, with applications in personalized neuroimaging and synthetic stimulus generation, though it is incremental as it builds on existing encoding models and frameworks.
The paper tackles the problem of constructing personalized visual encoding models that typically require large training datasets by proposing a personalized ensemble approach that achieves comparable accuracy with only ~300 image-response pairs instead of ~20,000, and demonstrates robustness to domain shifts and utility in generating personalized stimuli.
Encoding models that predict brain response patterns to stimuli are one way to capture this relationship between variability in bottom-up neural systems and individual's behavior or pathological state. However, they generally need a large amount of training data to achieve optimal accuracy. Here, we propose and test an alternative personalized ensemble encoding model approach to utilize existing encoding models, to create encoding models for novel individuals with relatively little stimuli-response data. We show that these personalized ensemble encoding models trained with small amounts of data for a specific individual, i.e. ~300 image-response pairs, achieve accuracy not different from models trained on ~20,000 image-response pairs for the same individual. Importantly, the personalized ensemble encoding models preserve patterns of inter-individual variability in the image-response relationship. Additionally, we show the proposed approach is robust against domain shift by validating on a prospectively collected set of image-response data in novel individuals with a different scanner and experimental setup. Finally, we use our personalized ensemble encoding model within the recently developed NeuroGen framework to generate optimal stimuli designed to maximize specific regions' activations for a specific individual. We show that the inter-individual differences in face areas responses to images of animal vs human faces observed previously is replicated using NeuroGen with the ensemble encoding model. Our approach shows the potential to use previously collected, deeply sampled data to efficiently create accurate, personalized encoding models and, subsequently, personalized optimal synthetic images for new individuals scanned under different experimental conditions.