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

• URL: http://arxiv.org/abs/2601.09191v1
• Date: Wed, 14 Jan 2026 05:44:30 GMT
• Title: From Performance to Practice: Knowledge-Distilled Segmentator for On-Premises Clinical Workflows
• Abstract summary: We present a deployment-oriented framework to translate a high-performing segmentation model into a scalable family of compact student models.<n>The proposed approach preserves architectural compatibility with existing clinical systems while enabling systematic capacity reduction.<n>Results show that knowledge distillation provides a practical and reliable pathway for converting research-grade segmentation models into maintainable, deployment-ready components.
• Score: 8.438143117044795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Latent-to-Latent Flow for Volumetric Stochastic Segmentation [42.44847226668341]
  Flow matching has emerged as a powerful framework for generative modelling.<n>We introduce a latent-to-latent flow technique for segmentation of medical volumes via encoded representations of both the image and label space.
  arXiv  Detail & Related papers  (2026-09-07T13:10:57Z)
• Uni-Light: An Ultra-Lightweight Framework via Uncertainty-Aware Knowledge Distillation for Brain Tumour Segmentation [0.13980986259786224]
  Existing brain tumour segmentation methods often suffer from heavy computational demands.<n>We propose a novel ultra-lightweight framework (Uni-Light) that achieves high-fidelity segmentation.<n>Uni-Light reduces parameters by 97.56%, floating-point operations (FLOPs) by 73.03%, and inference memory footprint by 81.58%.
  arXiv  Detail & Related papers  (2026-09-06T17:00:57Z)
• Retrieval-Augmented Interpretable Learning: Towards Task-Specific Zero-Shot Models in Healthcare [40.40611523465792]
  We introduce Retrieval-Augmented Interpretable Learning (RAIL), a meta-learning framework for zero-shot generation of task-specific interpretable models.<n>RAIL retrieves related source tasks, transfers structure through coefficient space, and generates a new predictor in the original diagnostic-feature space.
  arXiv  Detail & Related papers  (2026-07-20T03:31:36Z)
• SurgPhase: Time efficient pituitary tumor surgery phase recognition via an interactive web platform [4.1977714530157435]
  We present a comprehensive framework for phase recognition in pituitary tumor surgery (PTS) videos.<n>Our method achieves 90% accuracy on a held-out test set, outperforming current state-of-the-art approaches.<n>A central contribution of this work is the integration of a collaborative online platform designed for surgeons to upload surgical videos.
  arXiv  Detail & Related papers  (2026-03-26T00:22:20Z)
• Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Tasks [15.634158040789474]
  State-Enhanced Logical-Skill Memory (SELSM) is a training-free framework that distills simulated clinical trajectories into entity-agnostic operational rules.<n> evaluated on MedAgentBench -- the only authoritative high-fidelity virtual EHR sandbox benchmarked with real clinical data.
  arXiv  Detail & Related papers  (2026-03-06T21:42:14Z)
• AgentScore: Autoformulation of Deployable Clinical Scoring Systems [45.88028371034407]
  We introduce AgentScore, which performs semantically guided optimization in unit-weighted clinical checklists.<n>AgentScore outperforms existing score-generation methods and achieves AUC comparable to more flexible interpretable models.<n>On two additional externally validated tasks, AgentScore achieves higher discrimination than established guideline-based scores.
  arXiv  Detail & Related papers  (2026-01-29T21:11:06Z)
• Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models [45.285970665585914]
  We propose a comprehensive framework for Continual Learning.<n>We employ a multi-modal, multi-layer RAG system that provides real-time guidance for model fine-tuning.<n>We introduce a dynamic knowledge distillation framework.
  arXiv  Detail & Related papers  (2025-12-15T08:09:40Z)
• Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution [42.85462513661566]
  We present a lightweight, transparent multimodal ensemble that fuses physiological time-series measurements with unstructured clinical notes from the first 48 hours of an ICU stay.<n>A logistic regression model combines predictions from two modality-specific models: a bidirectional LSTM for vitals and a finetuned ClinicalModernBERT transformer for notes.<n>On the MIMIC-III benchmark, our late-fusion ensemble improves discrimination over the best single model while maintaining well-calibrated predictions.
  arXiv  Detail & Related papers  (2025-11-19T20:11:49Z)
• Cancer-Net PCa-MultiSeg: Multimodal Enhancement of Prostate Cancer Lesion Segmentation Using Synthetic Correlated Diffusion Imaging [55.62977326180104]
  Current deep learning approaches for prostate cancer lesion segmentation achieve limited performance.<n>We investigate synthetic correlated diffusion imaging (CDI$s$) as an enhancement to standard diffusion-based protocols.<n>Our results establish validated integration pathways for CDI$s$ as a practical drop-in enhancement for PCa lesion segmentation tasks.
  arXiv  Detail & Related papers  (2025-11-11T04:16:12Z)
• Task-Adaptive Low-Dose CT Reconstruction [0.0]
  Deep learning-based computed tomography reconstruction methods already achieve high performance on standard image quality metrics.<n>Yet, they frequently fail to preserve the critical anatomical details needed for diagnostic tasks.<n>We propose a novel task-adaptive reconstruction framework that incorporates a frozen pre-trained task network as a regularization term in the reconstruction loss function.
  arXiv  Detail & Related papers  (2025-11-10T13:30:59Z)
• Colorectal Cancer Histopathological Grading using Multi-Scale Federated Learning [0.0]
  We propose a scalable, privacy-preserving federated learning framework for colorectal cancer grading.<n>Our framework achieves an overall accuracy of 83.5%, outperforming a comparable centralized model.<n>The proposed modular pipeline establishes a foundational step toward deployable, privacy-aware clinical AI for digital pathology.
  arXiv  Detail & Related papers  (2025-11-05T18:18:09Z)
• A Deep Learning Framework for Real-Time Image Processing in Medical Diagnostics: Enhancing Accuracy and Speed in Clinical Applications [0.0]
  This paper introduces a deep learning framework for real-time medical image analysis.<n>The proposed system integrates advanced neural network architectures with real-time optimization strategies.<n>It can substantially accelerate diagnostic, reduce clinician workload, and support AI integration in time-critical healthcare environments.
  arXiv  Detail & Related papers  (2025-10-18T18:26:09Z)
• Efficient Epistemic Uncertainty Estimation in Cerebrovascular Segmentation [1.3980986259786223]
  We introduce an efficient ensemble model combining the advantages of Bayesian Approximation and Deep Ensembles.<n>Areas of high model uncertainty and erroneous predictions are aligned which demonstrates the effectiveness and reliability of the approach.
  arXiv  Detail & Related papers  (2025-03-28T09:39:37Z)
• InfLocNet: Enhanced Lung Infection Localization and Disease Detection from Chest X-Ray Images Using Lightweight Deep Learning [0.5242869847419834]
  This paper presents a novel, lightweight deep learning based segmentation-classification network. It is designed to enhance the detection and localization of lung infections using chest X-ray images. Our model achieves remarkable results with an Intersection over Union (IoU) of 93.59% and a Dice Similarity Coefficient (DSC) of 97.61% in lung area segmentation.
  arXiv  Detail & Related papers  (2024-08-12T19:19:23Z)
• U-PASS: an Uncertainty-guided deep learning Pipeline for Automated Sleep Staging [61.6346401960268]
  We propose a machine learning pipeline called U-PASS tailored for clinical applications that incorporates uncertainty estimation at every stage of the process. We apply our uncertainty-guided deep learning pipeline to the challenging problem of sleep staging and demonstrate that it systematically improves performance at every stage.
  arXiv  Detail & Related papers  (2023-06-07T08:27:36Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)
• Self-Training with Improved Regularization for Sample-Efficient Chest X-Ray Classification [80.00316465793702]
  We present a deep learning framework that enables robust modeling in challenging scenarios. Our results show that using 85% lesser labeled data, we can build predictive models that match the performance of classifiers trained in a large-scale data setting.
  arXiv  Detail & Related papers  (2020-05-03T02:36:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.