LHU-Net: a Lean Hybrid U-Net for Cost-efficient, High-performance Volumetric Segmentation

• URL: http://arxiv.org/abs/2404.05102v3
• Date: Wed, 16 Jul 2025 12:28:25 GMT
• Title: LHU-Net: a Lean Hybrid U-Net for Cost-efficient, High-performance Volumetric Segmentation
• Authors: Yousef Sadegheih, Afshin Bozorgpour, Pratibha Kumari, Reza Azad, Dorit Merhof,
• Abstract summary: We propose LHU-Net, a Lean Hybrid U-Net for volumetric medical image segmentation.<n>LHU-Net prioritizes spatial feature extraction before refining channel features, optimizing both efficiency and accuracy.<n> evaluated on four benchmark datasets (Synapse, Left Atrial, BraTS-Decathlon, and Lung-Decathlon)
• Score: 4.168081528698768
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rise of Transformer architectures has advanced medical image segmentation, leading to hybrid models that combine Convolutional Neural Networks (CNNs) and Transformers. However, these models often suffer from excessive complexity and fail to effectively integrate spatial and channel features, crucial for precise segmentation. To address this, we propose LHU-Net, a Lean Hybrid U-Net for volumetric medical image segmentation. LHU-Net prioritizes spatial feature extraction before refining channel features, optimizing both efficiency and accuracy. Evaluated on four benchmark datasets (Synapse, Left Atrial, BraTS-Decathlon, and Lung-Decathlon), LHU-Net consistently outperforms existing models across diverse modalities (CT/MRI) and output configurations. It achieves state-of-the-art Dice scores while using four times fewer parameters and 20% fewer FLOPs than competing models, without the need for pre-training, additional data, or model ensembles. With an average of 11 million parameters, LHU-Net sets a new benchmark for computational efficiency and segmentation accuracy. Our implementation is available on GitHub: https://github.com/xmindflow/LHUNet

Related papers

• Simple is what you need for efficient and accurate medical image segmentation [7.2109224546543675]
  This paper presents SimpleUNet, a scalable ultra-lightweight medical image segmentation model.<n>With a record-breaking 16 KB parameter configuration, SimpleUNet outperforms LBUNet and other lightweight benchmarks.<n>The 0.67 MB variant achieves superior efficiency (8.60 GFLOPs) and accuracy, attaining a mean DSC/IoU of 85.76%/75.60% on multi-center breast lesion datasets.
  arXiv  Detail & Related papers  (2025-06-16T12:31:48Z)
• Efficient FPGA-accelerated Convolutional Neural Networks for Cloud Detection on CubeSats [0.5420492913071214]
  We present the implementation of four FPGA-accelerated convolutional neural network (CNN) models for onboard cloud detection in resource-constrained CubeSat missions. This study explores both pixel-wise (Pixel-Net and Patch-Net) and image-wise (U-Net and Scene-Net) models to benchmark trade-offs in accuracy, latency, and model complexity. All models retained high accuracy post-FPGA integration, with a cumulative maximum accuracy drop of only 0.6% after quantization and pruning.
  arXiv  Detail & Related papers  (2025-04-04T19:32:47Z)
• GLoG-CSUnet: Enhancing Vision Transformers with Adaptable Radiomic Features for Medical Image Segmentation [2.294915015129229]
  Vision Transformers (ViTs) have shown promise in medical image semantic segmentation (MISS) We introduce Gabor and Laplacian of Gaussian Convolutional Swin Network (GLoG-CSUnet) GLoG-CSUnet is a novel architecture enhancing Transformer-based models by incorporating learnable radiomic features.
  arXiv  Detail & Related papers  (2025-01-06T06:07:40Z)
• S3TU-Net: Structured Convolution and Superpixel Transformer for Lung Nodule Segmentation [5.2752693301728355]
  We propose a segmentation model, S3TU-Net, which integrates multi-dimensional spatial connectors and a superpixel-based visual transformer. S3TU-Net is built on a multi-view CNN-Transformer hybrid architecture, incorporating superpixel algorithms, structured weighting, and spatial shifting techniques. Experimental results on the LIDC-IDRI dataset demonstrate that S3TU-Net achieves a DSC, precision, and IoU of 89.04%, 90.73%, and 90.70%, respectively.
  arXiv  Detail & Related papers  (2024-11-19T15:00:18Z)
• TransUKAN:Computing-Efficient Hybrid KAN-Transformer for Enhanced Medical Image Segmentation [5.280523424712006]
  U-Net is currently the most widely used architecture for medical image segmentation. We have improved the KAN to reduce memory usage and computational load. This approach enhances the model's capability to capture nonlinear relationships.
  arXiv  Detail & Related papers  (2024-09-23T02:52:49Z)
• Handling Geometric Domain Shifts in Semantic Segmentation of Surgical RGB and Hyperspectral Images [67.66644395272075]
  We present first analysis of state-of-the-art semantic segmentation models when faced with geometric out-of-distribution data. We propose an augmentation technique called "Organ Transplantation" to enhance generalizability. Our augmentation technique improves SOA model performance by up to 67 % for RGB data and 90 % for HSI data, achieving performance at the level of in-distribution performance on real OOD test data.
  arXiv  Detail & Related papers  (2024-08-27T19:13:15Z)
• MPruner: Optimizing Neural Network Size with CKA-Based Mutual Information Pruning [7.262751938473306]
  Pruning is a well-established technique that reduces the size of neural networks while mathematically guaranteeing accuracy preservation. We develop a new pruning algorithm, MPruner, that leverages mutual information through vector similarity. MPruner achieved up to a 50% reduction in parameters and memory usage for CNN and transformer-based models, with minimal to no loss in accuracy.
  arXiv  Detail & Related papers  (2024-08-24T05:54:47Z)
• A lightweight residual network for unsupervised deformable image registration [2.7309692684728617]
  We propose a residual U-Net with embedded parallel dilated-convolutional blocks to enhance the receptive field. The proposed method is evaluated on inter-patient and atlas-based datasets.
  arXiv  Detail & Related papers  (2024-06-14T07:20:49Z)
• CFDP: Common Frequency Domain Pruning [0.3021678014343889]
  We introduce a novel end-to-end pipeline for model pruning via the frequency domain. We have achieved state-of-the-art results on CIFAR-10 with GoogLeNet reaching an accuracy of 95.25%, that is, +0.2% from the original model. In addition to notable performances, models produced via CFDP exhibit robustness to a variety of configurations.
  arXiv  Detail & Related papers  (2023-06-07T04:49:26Z)
• 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)
• EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications [68.35683849098105]
  We introduce split depth-wise transpose attention (SDTA) encoder that splits input tensors into multiple channel groups. Our EdgeNeXt model with 1.3M parameters achieves 71.2% top-1 accuracy on ImageNet-1K. Our EdgeNeXt model with 5.6M parameters achieves 79.4% top-1 accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-06-21T17:59:56Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers [105.74546828182834]
  We show a hardware-efficient dynamic inference regime, named dynamic weight slicing, which adaptively slice a part of network parameters for inputs with diverse difficulty levels. We present dynamic slimmable network (DS-Net) and dynamic slice-able network (DS-Net++) by input-dependently adjusting filter numbers of CNNs and multiple dimensions in both CNNs and transformers.
  arXiv  Detail & Related papers  (2021-09-21T09:57:21Z)
• HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification [5.094623170336122]
  Spiking Neural Networks (SNNs) are trained with quantization-aware gradient descent to optimize weights, membrane leak, and firing thresholds. During both training and inference, the analog pixel values of a HSI are directly applied to the input layer of the SNN without the need to convert to a spike-train. We evaluate our proposal using three HSI datasets on a 3-D and a 3-D/2-D hybrid convolutional architecture.
  arXiv  Detail & Related papers  (2021-07-26T06:17:10Z)
• ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models [56.21470608621633]
  We propose a time estimation framework to decouple the architectural search from the target hardware. The proposed methodology extracts a set of models from micro- kernel and multi-layer benchmarks and generates a stacked model for mapping and network execution time estimation. We compare estimation accuracy and fidelity of the generated mixed models, statistical models with the roofline model, and a refined roofline model for evaluation.
  arXiv  Detail & Related papers  (2021-05-07T11:39:05Z)
• Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions [11.769185588579488]
  We present state-of-the-art performance with lower memory consumption and latency, along with characteristics suited to accelerator implementation. Our proposal uses memory proportional to the number of vertices in the graph, in contrast to competing methods which require memory proportional to the number of edges. We propose aggregator fusion, a technique to enable GNNs to significantly boost their representational power, with only a small increase in latency of 19% over standard sparse matrix multiplication.
  arXiv  Detail & Related papers  (2021-04-03T20:54:36Z)
• KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations [59.65174244047216]
  We propose an over-complete architecture (Ki-Net) which involves projecting the data onto higher dimensions. This network, when augmented with U-Net, results in significant improvements in the case of segmenting small anatomical landmarks. We evaluate the proposed method on the task of brain anatomy segmentation from 2D Ultrasound of preterm neonates.
  arXiv  Detail & Related papers  (2020-06-08T18:59:24Z)
• Highly Efficient Salient Object Detection with 100K Parameters [137.74898755102387]
  We propose a flexible convolutional module, namely generalized OctConv (gOctConv), to efficiently utilize both in-stage and cross-stages multi-scale features. We build an extremely light-weighted model, namely CSNet, which achieves comparable performance with about 0.2% (100k) of large models on popular object detection benchmarks.
  arXiv  Detail & Related papers  (2020-03-12T07:00:46Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

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.