Dynamic Gradient Sparsification Training for Few-Shot Fine-tuning of CT Lymph Node Segmentation Foundation Model

• URL: http://arxiv.org/abs/2503.00748v1
• Date: Sun, 02 Mar 2025 06:02:34 GMT
• Title: Dynamic Gradient Sparsification Training for Few-Shot Fine-tuning of CT Lymph Node Segmentation Foundation Model
• Authors: Zihao Luo, Zijun Gao, Wenjun Liao, Shichuan Zhang, Guotai Wang, Xiangde Luo,
• Abstract summary: lymph node (LN) segmentation is critical in radiotherapy treatment and prognosis analysis, but is limited by the need for large annotated datasets.<n>In this work, we annotated 36,106 visible LNs from 3,346 publicly available head-and-neck CT scans to establish a robust LN segmentation model (nnUNetv2)<n>We propose Dynamic Gradient Sparsification Training (D GST), a few-shot fine-tuning approach that preserves foundational knowledge while dynamically updating the most critical parameters of the LN segmentation model with few annotations.
• Score: 9.229857825454365
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Accurate lymph node (LN) segmentation is critical in radiotherapy treatment and prognosis analysis, but is limited by the need for large annotated datasets. While deep learning-based segmentation foundation models show potential in developing high-performing models with fewer samples, their medical adaptation faces LN domain-specific prior deficiencies and inefficient few-shot fine-tuning for complex clinical practices, highlighting the necessity of an LN segmentation foundation model. In this work, we annotated 36,106 visible LNs from 3,346 publicly available head-and-neck CT scans to establish a robust LN segmentation model (nnUNetv2). Building on this, we propose Dynamic Gradient Sparsification Training (DGST), a few-shot fine-tuning approach that preserves foundational knowledge while dynamically updating the most critical parameters of the LN segmentation model with few annotations. We validate it on two publicly available LN segmentation datasets: SegRap2023 and LNQ2023. The results show that DGST outperforms existing few-shot fine-tuning methods, achieving satisfactory performance with limited labeled data. We release the dataset, models and all implementations to facilitate relevant research: https://github.com/Zihaoluoh/LN-Seg-FM.

Related papers

• NAN: A Training-Free Solution to Coefficient Estimation in Model Merging [61.36020737229637]
  We show that the optimal merging weights should scale with the amount of task-specific information encoded in each model.<n>We propose NAN, a simple yet effective method that estimates model merging coefficients via the inverse of parameter norm.<n>NAN is training-free, plug-and-play, and applicable to a wide range of merging strategies.
  arXiv  Detail & Related papers  (2025-05-22T02:46:08Z)
• AI-Assisted Colonoscopy: Polyp Detection and Segmentation using Foundation Models [0.10037949839020764]
  In colonoscopy, 80% of the missed polyps could be detected with the help of Deep Learning models. In the search for algorithms capable of addressing this challenge, foundation models emerge as promising candidates. Their zero-shot or few-shot learning capabilities, facilitate generalization to new data or tasks without extensive fine-tuning. A comprehensive evaluation of foundation models for polyp segmentation was conducted, assessing both detection and delimitation.
  arXiv  Detail & Related papers  (2025-03-31T14:20:53Z)
• Low-Rank Continual Pyramid Vision Transformer: Incrementally Segment Whole-Body Organs in CT with Light-Weighted Adaptation [10.746776960260297]
  We propose a new continual whole-body organ segmentation model with light-weighted low-rank adaptation (LoRA) We first train and freeze a pyramid vision transformer (PVT) base segmentation model on the initial task, then continually add light-weighted trainable LoRA parameters to the frozen model for each new learning task. Our proposed model continually segments new organs without catastrophic forgetting and meanwhile maintaining a low parameter increasing rate.
  arXiv  Detail & Related papers  (2024-10-07T02:00:13Z)
• Leveraging Task-Specific Knowledge from LLM for Semi-Supervised 3D Medical Image Segmentation [9.778201925906913]
  We introduce LLM-SegNet, which exploits a large language model (LLM) to integrate task-specific knowledge into our co-training framework. Experiments on publicly available Left Atrium, Pancreas-CT, and Brats-19 datasets demonstrate the superior performance of LLM-SegNet compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-07-06T14:23:16Z)
• Few-Shot Learning for Annotation-Efficient Nucleus Instance Segmentation [50.407071700154674]
  We propose to formulate annotation-efficient nucleus instance segmentation from the perspective of few-shot learning (FSL) Our work was motivated by that, with the prosperity of computational pathology, an increasing number of fully-annotated datasets are publicly accessible. Extensive experiments on a couple of publicly accessible datasets demonstrate that SGFSIS can outperform other annotation-efficient learning baselines.
  arXiv  Detail & Related papers  (2024-02-26T03:49:18Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)
• Uncertainty-Aware Semi-Supervised Learning for Prostate MRI Zonal Segmentation [0.9176056742068814]
  We propose a novel semi-supervised learning (SSL) approach that requires only a relatively small number of annotations. Our method uses a pseudo-labeling technique that employs recent deep learning uncertainty estimation models. Our proposed model outperformed the semi-supervised model in experiments with the ProstateX dataset and an external test set.
  arXiv  Detail & Related papers  (2023-05-10T08:50:04Z)
• Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation [20.94974284175104]
  Few-Shot Efficient Fine-Tuning (FSEFT) is a novel and realistic scenario for adapting medical image segmentation foundation models. Our comprehensive transfer learning experiments confirm the suitability of foundation models in medical image segmentation and unveil the limitations of popular fine-tuning strategies in few-shot scenarios.
  arXiv  Detail & Related papers  (2023-03-29T22:50:05Z)
• SegPrompt: Using Segmentation Map as a Better Prompt to Finetune Deep Models for Kidney Stone Classification [62.403510793388705]
  Deep learning has produced encouraging results for kidney stone classification using endoscope images. The shortage of annotated training data poses a severe problem in improving the performance and generalization ability of the trained model. We propose SegPrompt to alleviate the data shortage problems by exploiting segmentation maps from two aspects.
  arXiv  Detail & Related papers  (2023-03-15T01:30:48Z)
• A Kernel-Based View of Language Model Fine-Tuning [94.75146965041131]
  We investigate whether the Neural Tangent Kernel (NTK) describes fine-tuning of pre-trained LMs. We show that formulating the downstream task as a masked word prediction problem through prompting often induces kernel-based dynamics during fine-tuning.
  arXiv  Detail & Related papers  (2022-10-11T17:34:32Z)
• Towards Robust Partially Supervised Multi-Structure Medical Image Segmentation on Small-Scale Data [123.03252888189546]
  We propose Vicinal Labels Under Uncertainty (VLUU) to bridge the methodological gaps in partially supervised learning (PSL) under data scarcity. Motivated by multi-task learning and vicinal risk minimization, VLUU transforms the partially supervised problem into a fully supervised problem by generating vicinal labels. Our research suggests a new research direction in label-efficient deep learning with partial supervision.
  arXiv  Detail & Related papers  (2020-11-28T16:31:00Z)
• Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition [22.90127409366107]
  We propose an efficient but strong baseline based on Graph Convolutional Network (GCN) Inspired by the success of the ResNet architecture in Convolutional Neural Network (CNN), a ResGCN module is introduced in GCN. A PartAtt block is proposed to discover the most essential body parts over a whole action sequence.
  arXiv  Detail & Related papers  (2020-10-20T02:56:58Z)
• The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation [93.17367076148348]
  We investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset. We unveil that a major cause is the inaccurate classification of object proposals. We propose a simple calibration framework to more effectively alleviate classification head bias with a bi-level class balanced sampling approach.
  arXiv  Detail & Related papers  (2020-07-23T12:49:07Z)

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.