Efficient Quantization-Aware Training on Segment Anything Model in Medical Images and Its Deployment

TL;DR

This paper presents a quantization-aware training method for the MedSAM model to improve inference speed and efficiency in medical image segmentation, balancing accuracy with computational resource demands.

Contribution

We propose a novel quantization-aware training pipeline for MedSAM, enabling efficient deployment on limited hardware with minimal accuracy loss.

Findings

Significantly increased processing speed

Reduced disk storage requirements

Maintained acceptable segmentation accuracy

Abstract

Medical image segmentation is a critical component of clinical practice, and the state-of-the-art MedSAM model has significantly advanced this field. Nevertheless, critiques highlight that MedSAM demands substantial computational resources during inference. To address this issue, the CVPR 2024 MedSAM on Laptop Challenge was established to find an optimal balance between accuracy and processing speed. In this paper, we introduce a quantization-aware training pipeline designed to efficiently quantize the Segment Anything Model for medical images and deploy it using the OpenVINO inference engine. This pipeline optimizes both training time and disk storage. Our experimental results confirm that this approach considerably enhances processing speed over the baseline, while still achieving an acceptable accuracy level. The training script, inference script, and quantized model are publicly accessible at https://github.com/AVC2-UESTC/QMedSAM.