Personalized visual encoding model construction with small data

TL;DR

This paper introduces a personalized ensemble encoding model that accurately predicts individual brain responses with minimal data, enabling personalized stimulus generation and robust performance across different scanning conditions.

Contribution

The authors propose a novel ensemble encoding approach that constructs personalized brain response models using small datasets, outperforming traditional models requiring large data.

Findings

Achieves comparable accuracy with ~300 samples versus 20,000 samples in traditional models.

Maintains inter-individual variability patterns in brain responses.

Robustly generalizes across different scanners and experimental setups.

Abstract

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.