Parameter Efficient Fine Tuning for Multi-scanner PET to PET Reconstruction

TL;DR

This paper introduces PETITE, a parameter-efficient fine-tuning method for multi-scanner PET image reconstruction, achieving comparable performance to full fine-tuning while using less than 1% of the parameters, thus reducing data and resource requirements.

Contribution

The study is the first to systematically evaluate diverse PEFT techniques in medical imaging reconstruction, specifically for multi-scanner PET, and proposes the novel Mix-PEFT approach for improved performance.

Findings

PETITE achieves full fine-tuning performance with less than 1% parameters.

Mix-PEFT methods improve cross-scanner PET reconstruction.

Multi-scanner datasets validate the effectiveness of PEFT in PET imaging.

Abstract

Reducing scan time in Positron Emission Tomography (PET) imaging while maintaining high-quality images is crucial for minimizing patient discomfort and radiation exposure. Due to the limited size of datasets and distribution discrepancy across scanners in medical imaging, fine-tuning in a parameter-efficient and effective manner is on the rise. Motivated by the potential of Parameter-Efficient Fine-Tuning (PEFT), we aim to address these issues by effectively leveraging PEFT to improve limited data and GPU resource issues in multi-scanner setups. In this paper, we introduce PETITE, Parameter-Efficient Fine-Tuning for MultI-scanner PET to PET REconstruction that uses fewer than 1% of the parameters. To the best of our knowledge, this study is the first to systematically explore the efficacy of diverse PEFT techniques in medical imaging reconstruction tasks via prevalent encoder-decoder-type deep models. This investigation, in particular, brings intriguing insights into PETITE as we show further improvements by treating encoder and decoder separately and mixing different PEFT methods, namely, Mix-PEFT. Using multi-scanner PET datasets comprised of five different scanners, we extensively test the cross-scanner PET scan time reduction performances (i.e., a model pre-trained on one scanner is fine-tuned on a different scanner) of 21 feasible Mix-PEFT combinations to derive optimal PETITE. We show that training with less than 1% parameters using PETITE performs on par with full fine-tuning (i.e., 100% parameter)