MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models

• URL: http://arxiv.org/abs/2603.11625v1
• Date: Thu, 12 Mar 2026 07:37:00 GMT
• Title: MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
• Abstract summary: We propose MedPruner, a training-free and model-agnostic hierarchical token pruning framework for efficient 3D medical image understanding.<n>We show that MedPruner enables models such as MedGemma to maintain or even exceed their original performance while retaining fewer than 5% of visual tokens.
• Score: 59.180043227905294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies. Current architectures typically suffer from massive anatomical redundancy due to the direct concatenation of consecutive 2D slices and lack the flexibility to handle heterogeneous information densities across different slices using fixed pruning ratios. To address these challenges, we propose MedPruner, a training-free and model-agnostic hierarchical token pruning framework specifically designed for efficient 3D medical image understanding. MedPruner introduces a two-stage mechanism: an Inter-slice Anchor-based Filtering module to eliminate slice-level temporal redundancy, followed by a Dynamic Information Nucleus Selection strategy that achieves adaptive token-level compression by quantifying cumulative attention weights. Extensive experiments on three 3D medical benchmarks and across three diverse medical VLMs reveal massive token redundancy in existing architectures. Notably, MedPruner enables models such as MedGemma to maintain or even exceed their original performance while retaining fewer than 5% of visual tokens, thereby drastically reducing computational overhead and validating the necessity of dynamic token selection for practical clinical deployment. Our code will be released.

Related papers

• MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models [3.8740159612186265]
  We propose MedARC, a framework for Adaptive Redundancy Compression of visual tokens in 3D medical vision-language models.<n>MedARC estimates token importance by integrating three complementary cues.<n>Experiments on CT-RATE and MR-RATE show that MedARC reduces visual-token overhead and inference time while preserving or improving diagnostic performance.
  arXiv  Detail & Related papers  (2026-07-29T07:27:09Z)
• Towards Enhancing 3D Spatial Reasoning in Medical Multimodal Large Language Models [8.949206640442354]
  We introduce a large-scale structured reasoning dataset constructed via a novel slice-wise data synthesis paradigm.<n>Inspired by the genuine diagnostic workflow of radiologists, this paradigm models visual cognition by decomposing the complex 3D reading process.<n>This strategy unlocks deep volumetric understanding and highly interpretable clinical logic without requiring computationally expensive 3D-specific pre-training.
  arXiv  Detail & Related papers  (2026-07-15T14:05:58Z)
• Adapting 2D Multi-Modal Large Language Model for 3D CT Image Analysis [52.32262701215441]
  multimodal large language models (MLLMs) have exhibited robust perceptual capacity, strong cross-modal alignment, and promising generalizability.<n>Due to the scarcity of 3D medical images, existing 3D medical MLLMs suffer from insufficiently pretrained vision encoder and inability to extract customized image features.<n>We propose a Text-Guided Hierarchical MoE framework, which can distinguish tasks under the guidance of the text prompt.
  arXiv  Detail & Related papers  (2026-04-11T14:36:05Z)
• Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification [69.87877580725768]
  Multimodal Visual Surrogate Compression (MVSC) learns to compress and adapt large 3D sMRI volumes into compact 2D features.<n>MVSC has two key components: a Volume Context that captures global cross-slice context under textual guidance, and an Adaptive Slice Fusion module that aggregates slice-level information in a text-enhanced, patch-wise manner.
  arXiv  Detail & Related papers  (2026-01-29T13:05:46Z)
• Staged Voxel-Level Deep Reinforcement Learning for 3D Medical Image Segmentation with Noisy Annotations [4.581671524490035]
  We propose an end-to-end Staged Voxel-Level Deep Reinforcement Learning framework for robust medical image segmentation under noisy annotations.<n>This framework employs a dynamic iterative update strategy to automatically mitigate the impact of erroneous labels without requiring manual intervention.
  arXiv  Detail & Related papers  (2026-01-07T12:39:54Z)
• Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging [19.44554736205812]
  We introduce BTB3D (Better Tokens for Better 3D), a causal convolutional encoder-decoder that unifies 2D and 3D training and inference.<n>A three-stage training curriculum enables (i) local reconstruction, (ii) overlapping-window tiling, and (iii) long-context decoder refinement.<n>It improves BLEU scores and increases clinical F1 by 40% over CT2Rep, CT-CHAT, and Merlin for report generation.<n>It reduces FID by 75% and halves FVD compared to GenerateCT and MedSyn for text-to-CT synthesis.
  arXiv  Detail & Related papers  (2025-10-23T15:13:13Z)
• MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation [55.37355146924576]
  MedSeqFT is a sequential fine-tuning framework for medical image analysis.<n>It adapts pre-trained models to new tasks while refining their representational capacity.<n>It consistently outperforms state-of-the-art fine-tuning strategies.
  arXiv  Detail & Related papers  (2025-09-07T15:22:53Z)
• E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation [34.865695471451886]
  We propose a 3D medical image segmentation model, named Efficient to Efficient Network (E2ENet)<n>It incorporates two parametrically and computationally efficient designs.<n>It consistently achieves a superior trade-off between accuracy and efficiency across various resource constraints.
  arXiv  Detail & Related papers  (2023-12-07T22:13:37Z)
• Spatiotemporal Modeling Encounters 3D Medical Image Analysis: Slice-Shift UNet with Multi-View Fusion [0.0]
  We propose a new 2D-based model dubbed Slice SHift UNet which encodes three-dimensional features at 2D CNN's complexity. More precisely multi-view features are collaboratively learned by performing 2D convolutions along the three planes of a volume. The effectiveness of our approach is validated in Multi-Modality Abdominal Multi-Organ axis (AMOS) and Multi-Atlas Labeling Beyond the Cranial Vault (BTCV) datasets.
  arXiv  Detail & Related papers  (2023-07-24T14:53:23Z)
• Interpretable 2D Vision Models for 3D Medical Images [47.75089895500738]
  This study proposes a simple approach of adapting 2D networks with an intermediate feature representation for processing 3D images. We show on all 3D MedMNIST datasets as benchmark and two real-world datasets consisting of several hundred high-resolution CT or MRI scans that our approach performs on par with existing methods.
  arXiv  Detail & Related papers  (2023-07-13T08:27:09Z)
• UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation [93.88170217725805]
  We propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features. Our evaluations on five benchmarks, Synapse, BTCV, ACDC, BRaTs, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2022-12-08T18:59:57Z)
• Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-fine Framework and Its Adversarial Examples [74.92488215859991]
  We propose a novel 3D-based coarse-to-fine framework to efficiently tackle these challenges. The proposed 3D-based framework outperforms their 2D counterparts by a large margin since it can leverage the rich spatial information along all three axes. We conduct experiments on three datasets, the NIH pancreas dataset, the JHMI pancreas dataset and the JHMI pathological cyst dataset.
  arXiv  Detail & Related papers  (2020-10-29T15:39:19Z)

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.