知镜 Cognispect · 医学文献与研究工作台

Generalized post-training quantization for medical image segmentation foundation model

Huang P, Zhang A, Yin P, et al.
Med Image Anal · 2026-09-03 · PMID 42705143

文献摘要

Medical image segmentation foundation models (MedFMs) perform strongly across diverse imaging modalities, but their large size and computational demands hinder deployment in resource-limited clinical settings. Lightweight fine-tuning is impractical given the high training cost of MedFMs, and the efficiency benefits of integer inference remain underused. Post-training quantization (PTQ) is a promising alternative, yet existing PTQ methods fail on MedFMs because their heterogeneous weight distributions lead to severe accuracy degradation at low bit-widths. To address this challenge, we propose GPTQ-MedFM, a generalized post-training quantization framework tailored for medical foundation models. GPTQ-MedFM standardizes complex weight distributions under an ℓ ∞ -constrained normalization to produce quantization-friendly matrices, and then applies an efficient coordinate-descent solver to obtain high-fidelity low-bit representations. The method adds no extra computation or memory overhead at inference, enabling seamless deployment on medical edge devices. By explicitly modeling and mitigating quantization-induced errors, GPTQ-MedFM achieves state-of-the-art low-bit compression across six medical foundation models and nine imaging modalities - spanning nearly the full range of clinical imaging scenarios - and remains robust even with a single calibration sample. Its broad generalization and minimal calibration cost make GPTQ-MedFM a practical pathway for real-time AI-assisted diagnostics in resource-limited healthcare settings.

在知镜精读原文来源DOI 原文

知镜提供医学文献检索、阅读笔记、人体图谱、统计绘图与研究复现工具。