D-Net: Dynamic Large Kernel with Dynamic Feature Fusion for Volumetric Medical Image Segmentation

• URL: http://arxiv.org/abs/2403.10674v2
• Date: Thu, 17 Oct 2024 00:51:28 GMT
• Title: D-Net: Dynamic Large Kernel with Dynamic Feature Fusion for Volumetric Medical Image Segmentation
• Authors: Jin Yang, Peijie Qiu, Yichi Zhang, Daniel S. Marcus, Aristeidis Sotiras,
• Abstract summary: We propose Dynamic Large Kernel (DLK) and Dynamic Feature Fusion (DFF) modules. D-Net is able to effectively utilize a multi-scale large receptive field and adaptively harness global contextual information.
• Score: 7.894630378784007
• License:
• Abstract: Hierarchical transformers have achieved significant success in medical image segmentation due to their large receptive field and capabilities of effectively leveraging global long-range contextual information. Convolutional neural networks (CNNs) can also deliver a large receptive field by using large kernels, enabling them to achieve competitive performance with fewer model parameters. However, CNNs incorporated with large convolutional kernels remain constrained in adaptively capturing multi-scale features from organs with large variations in shape and size due to the employment of fixed-sized kernels. Additionally, they are unable to utilize global contextual information efficiently. To address these limitations, we propose Dynamic Large Kernel (DLK) and Dynamic Feature Fusion (DFF) modules. The DLK module employs multiple large kernels with varying kernel sizes and dilation rates to capture multi-scale features. Subsequently, a dynamic selection mechanism is utilized to adaptively highlight the most important spatial features based on global information. Additionally, the DFF module is proposed to adaptively fuse multi-scale local feature maps based on their global information. We integrate DLK and DFF in a hierarchical transformer architecture to develop a novel architecture, termed D-Net. D-Net is able to effectively utilize a multi-scale large receptive field and adaptively harness global contextual information. Extensive experimental results demonstrate that D-Net outperforms other state-of-the-art models in the two volumetric segmentation tasks, including abdominal multi-organ segmentation and multi-modality brain tumor segmentation. Our code is available at https://github.com/sotiraslab/DLK.

Related papers

• DMC-Net: Lightweight Dynamic Multi-Scale and Multi-Resolution Convolution Network for Pancreas Segmentation in CT Images [1.9422777572345737]
  Convolutional neural networks (CNNs) have shown great effectiveness in medical image segmentation. CNNs may be limited in modeling large inter-subject variations in organ shapes and sizes and exploiting global long-range contextual information. We develop Dynamic Multi-Resolution Convolution (DMRC) and Dynamic Multi-Scale Convolution (DMSC) modules.
  arXiv  Detail & Related papers  (2024-10-03T01:19:21Z)
• Multiscale Encoder and Omni-Dimensional Dynamic Convolution Enrichment in nnU-Net for Brain Tumor Segmentation [9.39565041325745]
  This study introduces a novel segmentation algorithm utilizing a modified nnU-Net architecture. We enhance conventional convolution layers by incorporating omni-dimensional dynamic convolution layers, resulting in improved feature representation. Our model's efficacy is demonstrated on diverse datasets from the BraTS-2023 challenge.
  arXiv  Detail & Related papers  (2024-09-20T05:25:46Z)
• A Multimodal Feature Distillation with CNN-Transformer Network for Brain Tumor Segmentation with Incomplete Modalities [15.841483814265592]
  We propose a Multimodal feature distillation with Convolutional Neural Network (CNN)-Transformer hybrid network (MCTSeg) for accurate brain tumor segmentation with missing modalities. Our ablation study demonstrates the importance of the proposed modules with CNN-Transformer networks and the convolutional blocks in Transformer for improving the performance of brain tumor segmentation with missing modalities.
  arXiv  Detail & Related papers  (2024-04-22T09:33:44Z)
• Lesion-aware Dynamic Kernel for Polyp Segmentation [49.63274623103663]
  We propose a lesion-aware dynamic network (LDNet) for polyp segmentation. It is a traditional u-shape encoder-decoder structure incorporated with a dynamic kernel generation and updating scheme. This simple but effective scheme endows our model with powerful segmentation performance and generalization capability.
  arXiv  Detail & Related papers  (2023-01-12T09:53:57Z)
• Adaptive Dynamic Filtering Network for Image Denoising [8.61083713580388]
  In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. We propose to employ dynamic convolution to improve the learning of high-frequency and multi-scale features. We build an efficient denoising network with the proposed DCB and MDCB, named ADFNet.
  arXiv  Detail & Related papers  (2022-11-22T06:54:27Z)
• Learning from partially labeled data for multi-organ and tumor segmentation [102.55303521877933]
  We propose a Transformer based dynamic on-demand network (TransDoDNet) that learns to segment organs and tumors on multiple datasets. A dynamic head enables the network to accomplish multiple segmentation tasks flexibly. We create a large-scale partially labeled Multi-Organ and Tumor benchmark, termed MOTS, and demonstrate the superior performance of our TransDoDNet over other competitors.
  arXiv  Detail & Related papers  (2022-11-13T13:03:09Z)
• Salient Object Detection via Dynamic Scale Routing [62.26677215668959]
  This paper introduces the "dynamic" scale routing (as a brand-new idea) in this paper. It will result in a generic plug-in that could directly fit the existing feature backbone. We provide a self-adaptive bidirectional decoder design to accommodate the DPConv-based encoder best.
  arXiv  Detail & Related papers  (2022-10-25T08:01:27Z)
• Global Filter Networks for Image Classification [90.81352483076323]
  We present a conceptually simple yet computationally efficient architecture that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness.
  arXiv  Detail & Related papers  (2021-07-01T17:58:16Z)
• DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets [102.55303521877933]
  We propose a dynamic on-demand network (DoDNet) that learns to segment multiple organs and tumors on partially labelled datasets. DoDNet consists of a shared encoder-decoder architecture, a task encoding module, a controller for generating dynamic convolution filters, and a single but dynamic segmentation head.
  arXiv  Detail & Related papers  (2020-11-20T04:56:39Z)
• Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification [47.423272376757204]
  The Receptive Field (RF) size has been one of the most important factors for One Dimensional Convolutional Neural Networks (1D-CNNs) on time series classification tasks. We propose an Omni-Scale block (OS-block) for 1D-CNNs, where the kernel sizes are decided by a simple and universal rule. Experiment result shows that models with the OS-block can achieve a similar performance as models with the searched optimal RF size.
  arXiv  Detail & Related papers  (2020-02-24T03:33:58Z)

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.