From performance to practice: knowledge-distilled segmentator for on-premises clinical workflows.
Authors
Affiliations (8)
Affiliations (8)
- McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX USA.
- M31 AI, Toronto, ON Canada.
- AI Collaborative Centre, University Health Network, Toronto, ON Canada.
- Princess Margaret Cancer Centre, University Health Network, Toronto, ON Canada.
- Peter Munk Cardiac Centre, University Health Network, Toronto, ON Canada.
- Department of Laboratory Medicine and Pathobiology and Department of Computer Science, University of Toronto, Toronto, ON Canada.
- Vector Institute, Toronto, ON Canada.
- Center for Precision Health, McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX USA.
Abstract
Deploying medical image segmentation models in routine clinical workflows is often constrained by on-premises infrastructure, where computational resources are fixed and cloud-based inference may be restricted by governance and security policies. While high-capacity models achieve strong segmentation accuracy, their computational demands hinder practical deployment and long-term maintainability in hospital environments. We present a deployment-oriented framework that leverages knowledge distillation to translate a high-performing segmentation model into a scalable family of compact student models without modifying the inference pipeline. The framework is primarily evaluated on nnU-Net, with additional validation across transformer and heterogeneous teacher-student architectures. The proposed approach preserves architectural compatibility with existing clinical systems while enabling systematic capacity reduction. We evaluate framework on a multi-site brain MRI dataset comprising 1104 3D volumes, with independent testing on 101 curated cases, and is further examined on abdominal CT to assess cross-modality generalizability. Under aggressive parameter reduction (94%), the distilled student model preserves nearly all of the teacher's segmentation accuracy (98.7%), while achieving substantial efficiency gains, including up to a 67% reduction in CPU inference latency without additional deployment overhead. These results demonstrate that knowledge distillation provides a practical and reliable pathway for converting research-grade segmentation models into maintainable, deployment-ready components for on-premises clinical workflows in real-world health systems.