HER-Seg: Holistically Efficient Segmentation for High-Resolution Medical Images

• URL: http://arxiv.org/abs/2504.06205v2
• Date: Mon, 21 Jul 2025 15:45:54 GMT
• Title: HER-Seg: Holistically Efficient Segmentation for High-Resolution Medical Images
• Authors: Qing Xu, Zhenye Lou, Chenxin Li, Yue Li, Xiangjian He, Tesema Fiseha Berhanu, Rong Qu, Wenting Duan, Zhen Chen,
• Abstract summary: High-resolution segmentation is critical for precise disease diagnosis by extracting fine-grained morphological details.<n>Existing hierarchical encoder-decoder frameworks have demonstrated remarkable adaptability across diverse medical segmentation tasks.<n>We propose a holistically efficient framework for high-resolution medical image segmentation, called HER-Seg.
• Score: 12.452415054883256
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-resolution segmentation is critical for precise disease diagnosis by extracting fine-grained morphological details. Existing hierarchical encoder-decoder frameworks have demonstrated remarkable adaptability across diverse medical segmentation tasks. While beneficial, they usually require the huge computation and memory cost when handling large-size segmentation, which limits their applications in foundation model building and real-world clinical scenarios. To address this limitation, we propose a holistically efficient framework for high-resolution medical image segmentation, called HER-Seg. Specifically, we first devise a computation-efficient image encoder (CE-Encoder) to model long-range dependencies with linear complexity while maintaining sufficient representations. In particular, we introduce the dual-gated linear attention (DLA) mechanism to perform cascaded token filtering, selectively retaining important tokens while ignoring irrelevant ones to enhance attention computation efficiency. Then, we introduce a memory-efficient mask decoder (ME-Decoder) to eliminate the demand for the hierarchical structure by leveraging cross-scale segmentation decoding. Extensive experiments reveal that HER-Seg outperforms state-of-the-arts in high-resolution medical 2D, 3D and video segmentation tasks. In particular, our HER-Seg requires only 0.59GB training GPU memory and 9.39G inference FLOPs per 1024$\times$1024 image, demonstrating superior memory and computation efficiency. The code is available at https://github.com/xq141839/HER-Seg.

Related papers

• InceptionMamba: Efficient Multi-Stage Feature Enhancement with Selective State Space Model for Microscopic Medical Image Segmentation [15.666926528144202]
  We propose an efficient framework for the segmentation task, named InceptionMamba, which encodes multi-stage rich features.<n>We exploit semantic cues to capture both low-frequency and high-frequency regions to enrich the multi-stage features.<n>Our model achieves state-of-the-art performance on two challenging microscopic segmentation datasets.
  arXiv  Detail & Related papers  (2025-06-13T20:25:12Z)
• MRGen: Segmentation Data Engine For Underrepresented MRI Modalities [59.61465292965639]
  Training medical image segmentation models for rare yet clinically significant imaging modalities is challenging due to the scarcity of annotated data.<n>This paper investigates leveraging generative models to synthesize training data, to train segmentation models for underrepresented modalities.
  arXiv  Detail & Related papers  (2024-12-04T16:34:22Z)
• MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation [0.8437187555622164]
  This study explores enhancing Vision Transformers (ViTs) for medical image segmentation by integrating pre-trained LLM transformer blocks. Our approach, which incorporates a frozen LLM transformer block into the encoder of a ViT-based model, leads to substantial improvements in segmentation performance. The enhanced model shows significant performance gains, including an average Dice score increase from 0.74 to 0.79 and improvements in accuracy, precision, and the Jaccard Index.
  arXiv  Detail & Related papers  (2024-10-03T14:50:33Z)
• Prompting Segment Anything Model with Domain-Adaptive Prototype for Generalizable Medical Image Segmentation [49.5901368256326]
  We propose a novel Domain-Adaptive Prompt framework for fine-tuning the Segment Anything Model (termed as DAPSAM) in segmenting medical images. Our DAPSAM achieves state-of-the-art performance on two medical image segmentation tasks with different modalities.
  arXiv  Detail & Related papers  (2024-09-19T07:28:33Z)
• MedSAGa: Few-shot Memory Efficient Medical Image Segmentation using Gradient Low-Rank Projection in SAM [0.0]
  We present the Segment Anything Model with Galore MedSAGa to achieve memory-efficient, few-shot medical image segmentation. We report on MedSAGa's memory efficiency and parameter segmentation performance across multiple medical image segmentation datasets. The combination of substantially lower memory requirements and comparable to SOTA results in few-shot learning positions MedSAGa as an optimal solution for deployment in resource-constrained settings.
  arXiv  Detail & Related papers  (2024-07-21T03:34:49Z)
• EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation [6.4399181389092]
  We introduce EMCAD, a new efficient multi-scale convolutional attention decoder. By employing group and depth-wise convolution, EMCAD is very efficient and scales well. Our evaluations reveal that EMCAD achieves state-of-the-art (SOTA) performance with 79.4% and 80.3% reduction in #Params and #FLOPs, respectively.
  arXiv  Detail & Related papers  (2024-05-11T02:23:24Z)
• Light-weight Retinal Layer Segmentation with Global Reasoning [14.558920359236572]
  We propose LightReSeg for retinal layer segmentation which can be applied to OCT images. Our approach achieves a better segmentation performance compared to the current state-of-the-art method TransUnet.
  arXiv  Detail & Related papers  (2024-04-25T05:42:41Z)
• Generative Medical Segmentation [5.4613210257624605]
  Generative Medical (GMS) is a novel approach leveraging a generative model to perform image segmentation. GMS employs a robust pre-trained vision foundation model to extract latent representations for images and corresponding ground truth masks. The design of GMS leads to fewer trainable parameters in the model which reduces the risk of overfitting and enhances its capability.
  arXiv  Detail & Related papers  (2024-03-27T02:16:04Z)
• BRAU-Net++: U-Shaped Hybrid CNN-Transformer Network for Medical Image Segmentation [11.986549780782724]
  We propose a hybrid yet effective CNN-Transformer network, named BRAU-Net++, for an accurate medical image segmentation task. Specifically, BRAU-Net++ uses bi-level routing attention as the core building block to design our u-shaped encoder-decoder structure. Our proposed approach surpasses other state-of-the-art methods including its baseline: BRAU-Net.
  arXiv  Detail & Related papers  (2024-01-01T10:49:09Z)
• Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
  Medical image segmentation plays a crucial role in computer-aided diagnosis. We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
  arXiv  Detail & Related papers  (2023-12-26T12:56:31Z)
• I-MedSAM: Implicit Medical Image Segmentation with Segment Anything [24.04558900909617]
  We propose I-MedSAM, which leverages the benefits of both continuous representations and SAM to obtain better cross-domain ability and accurate boundary delineation. Our proposed method with only 1.6M trainable parameters outperforms existing methods including discrete and implicit methods.
  arXiv  Detail & Related papers  (2023-11-28T00:43:52Z)
• MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation [58.53672866662472]
  We introduce a modality-agnostic SAM adaptation framework, named as MA-SAM. Our method roots in the parameter-efficient fine-tuning strategy to update only a small portion of weight increments. By injecting a series of 3D adapters into the transformer blocks of the image encoder, our method enables the pre-trained 2D backbone to extract third-dimensional information from input data.
  arXiv  Detail & Related papers  (2023-09-16T02:41:53Z)
• Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentation [84.58210297703714]
  We propose a self-supervised correction learning paradigm for semi-supervised biomedical image segmentation. We design a dual-task network, including a shared encoder and two independent decoders for segmentation and lesion region inpainting. Experiments on three medical image segmentation datasets for different tasks demonstrate the outstanding performance of our method.
  arXiv  Detail & Related papers  (2023-01-12T08:19:46Z)
• 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)
• Efficient Multi-Organ Segmentation Using SpatialConfiguration-Net with Low GPU Memory Requirements [8.967700713755281]
  In this work, we employ a multi-organ segmentation model based on the SpatialConfiguration-Net (SCN) We modified the architecture of the segmentation model to reduce its memory footprint without drastically impacting the quality of the predictions. Lastly, we implemented a minimal inference script for which we optimized both, execution time and required GPU memory.
  arXiv  Detail & Related papers  (2021-11-26T17:47:10Z)
• Small Lesion Segmentation in Brain MRIs with Subpixel Embedding [105.1223735549524]
  We present a method to segment MRI scans of the human brain into ischemic stroke lesion and normal tissues. We propose a neural network architecture in the form of a standard encoder-decoder where predictions are guided by a spatial expansion embedding network.
  arXiv  Detail & Related papers  (2021-09-18T00:21:17Z)
• Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions [58.71117402626524]
  We present a novel double-branch encoder architecture for medical image segmentation. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels. The experiments validate the effectiveness of our model on four datasets.
  arXiv  Detail & Related papers  (2021-07-24T02:58:32Z)
• Medical Transformer: Gated Axial-Attention for Medical Image Segmentation [73.98974074534497]
  We study the feasibility of using Transformer-based network architectures for medical image segmentation tasks. We propose a Gated Axial-Attention model which extends the existing architectures by introducing an additional control mechanism in the self-attention module. To train the model effectively on medical images, we propose a Local-Global training strategy (LoGo) which further improves the performance.
  arXiv  Detail & Related papers  (2021-02-21T18:35:14Z)
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation [78.01570371790669]
  Medical image segmentation is an essential prerequisite for developing healthcare systems. On various medical image segmentation tasks, the u-shaped architecture, also known as U-Net, has become the de-facto standard. We propose TransUNet, which merits both Transformers and U-Net, as a strong alternative for medical image segmentation.
  arXiv  Detail & Related papers  (2021-02-08T16:10:50Z)
• Modeling the Probabilistic Distribution of Unlabeled Data forOne-shot Medical Image Segmentation [40.41161371507547]
  We develop a data augmentation method for one-shot brain magnetic resonance imaging (MRI) image segmentation. Our method exploits only one labeled MRI image (named atlas) and a few unlabeled images. Our method outperforms the state-of-the-art one-shot medical segmentation methods.
  arXiv  Detail & Related papers  (2021-02-03T12:28:04Z)

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.