From Performance to Practice: Knowledge-Distilled Segmentator for On-Premises Clinical Workflows

TL;DR

This paper introduces a knowledge distillation framework that creates compact, efficient segmentation models suitable for on-premises clinical workflows, maintaining high accuracy while significantly reducing computational demands.

Contribution

The study presents a deployment-oriented knowledge distillation method that produces scalable, architecture-compatible segmentation models with minimal accuracy loss, tailored for hospital environments.

Findings

Achieves 94% parameter reduction with 98.7% of teacher accuracy

Reduces CPU inference latency by up to 67%

Demonstrates cross-modality generalizability on MRI and CT datasets

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 proposed approach preserves architectural compatibility with existing clinical systems while enabling systematic capacity reduction. The framework is evaluated on a multi-site brain MRI dataset comprising 1,104 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.