Back to all papers

Generalized post-training quantization for medical image segmentation foundation model.

September 3, 2026pubmed logopapers

Authors

Huang P,Zhang A,Yin P,Chen Y,Guo H,Yang Z,Wang N,Peng B,Hu S,Peng J,Hu J,Li X,Pan S,Li X,Wu X,Prabhakaran B,Zhu H,Wang X

Affiliations (18)

  • Southwest Jiaotong University, School of Computing and Artificial Intelligence, Chengdu, 611756, Sichuan, China; University at Albany, State University of New York, College of Integrated Health Sciences, Albany, 12222, NY, USA. Electronic address: [email protected].
  • University at Albany, State University of New York, Department of Mathematics and Statistics, Albany, 12222, NY, USA. Electronic address: [email protected].
  • University at Albany, State University of New York, Department of Mathematics and Statistics, Albany, 12222, NY, USA. Electronic address: [email protected].
  • University at Albany, State University of New York, College of Integrated Health Sciences, Albany, 12222, NY, USA. Electronic address: [email protected].
  • University at Albany, State University of New York, Department of Mathematics and Statistics, Albany, 12222, NY, USA. Electronic address: [email protected].
  • University at Albany, State University of New York, Department of Mathematics and Statistics, Albany, 12222, NY, USA. Electronic address: [email protected].
  • IBM T. J. Watson Research Center, Yorktown Heights, 10598, NY, USA. Electronic address: [email protected].
  • Southwest Jiaotong University, School of Computing and Artificial Intelligence, Chengdu, 611756, Sichuan, China. Electronic address: [email protected].
  • Purdue University, School of Applied and Creative Computing, West Lafayette, 47907, IN, USA. Electronic address: [email protected].
  • Chengdu University of Information Technology, School of Computer Science, Chengdu, 610225, Sichuan, China. Electronic address: [email protected].
  • Chengdu University of Information Technology, School of Computer Science, Chengdu, 610225, Sichuan, China. Electronic address: [email protected].
  • Chengdu University of Information Technology, School of Computer Science, Chengdu, 610225, Sichuan, China. Electronic address: [email protected].
  • Rensselaer Polytechnic Institute, Troy, 12180, NY, USA. Electronic address: [email protected].
  • University at Albany, State University of New York, Department of Computer Sciences, Albany, 12222, NY, USA. Electronic address: [email protected].
  • Chengdu University of Information Technology, School of Computer Science, Chengdu, 610225, Sichuan, China. Electronic address: [email protected].
  • University at Albany, State University of New York, Department of Computer Sciences, Albany, 12222, NY, USA; University at Albany, State University of New York, AI Plus Institute, Albany, 12222, NY, USA. Electronic address: [email protected].
  • University of North Carolina at Chapel Hill, Department of Biostatistics, Chapel Hill, 27599, NC, USA. Electronic address: [email protected].
  • University at Albany, State University of New York, College of Integrated Health Sciences, Albany, 12222, NY, USA; University at Albany, State University of New York, AI Plus Institute, Albany, 12222, NY, USA. Electronic address: [email protected].

Abstract

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<sub>∞</sub>-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.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAISlice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.