Advancing Brain Imaging Analysis Step-by-step via Progressive Self-paced Learning

TL;DR

This paper introduces the Progressive Self-Paced Distillation framework to improve brain imaging analysis by dynamically adjusting curriculum learning, effectively addressing dataset limitations and enhancing model robustness and generalization.

Contribution

The paper proposes a novel PSPD framework that employs adaptive curriculum pacing and distillation, leveraging past models to guide current learning in brain imaging analysis.

Findings

PSPD improves model accuracy on ADNI dataset.

Enhanced generalization and robustness demonstrated across CNNs.

Framework effectively mitigates overfitting with small datasets.

Abstract

Recent advancements in deep learning have shifted the development of brain imaging analysis. However, several challenges remain, such as heterogeneity, individual variations, and the contradiction between the high dimensionality and small size of brain imaging datasets. These issues complicate the learning process, preventing models from capturing intrinsic, meaningful patterns and potentially leading to suboptimal performance due to biases and overfitting. Curriculum learning (CL) presents a promising solution by organizing training examples from simple to complex, mimicking the human learning process, and potentially fostering the development of more robust and accurate models. Despite its potential, the inherent limitations posed by small initial training datasets present significant challenges, including overfitting and poor generalization. In this paper, we introduce the Progressive Self-Paced Distillation (PSPD) framework, employing an adaptive and progressive pacing and distillation mechanism. This allows for dynamic curriculum adjustments based on the states of both past and present models. The past model serves as a teacher, guiding the current model with gradually refined curriculum knowledge and helping prevent the loss of previously acquired knowledge. We validate PSPD's efficacy and adaptability across various convolutional neural networks using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, underscoring its superiority in enhancing model performance and generalization capabilities. The source code for this approach will be released at https://github.com/Hrychen7/PSPD.