KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation

• URL: http://arxiv.org/abs/2010.01663v2
• Date: Thu, 14 Oct 2021 20:27:36 GMT
• Title: KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation
• Authors: Jeya Maria Jose Valanarasu, Vishwanath A. Sindagi, Ilker Hacihaliloglu, Vishal M. Patel
• Abstract summary: "Traditional" encoder-decoder based approaches perform poorly in detecting smaller structures and are unable to segment boundary regions precisely. We propose KiU-Net which has two branches: (1) an overcomplete convolutional network Kite-Net which learns to capture fine details and accurate edges of the input, and (2) U-Net which learns high level features. The proposed method achieves a better performance as compared to all the recent methods with an additional benefit of fewer parameters and faster convergence.
• Score: 71.79090083883403
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most methods for medical image segmentation use U-Net or its variants as they have been successful in most of the applications. After a detailed analysis of these "traditional" encoder-decoder based approaches, we observed that they perform poorly in detecting smaller structures and are unable to segment boundary regions precisely. This issue can be attributed to the increase in receptive field size as we go deeper into the encoder. The extra focus on learning high level features causes the U-Net based approaches to learn less information about low-level features which are crucial for detecting small structures. To overcome this issue, we propose using an overcomplete convolutional architecture where we project our input image into a higher dimension such that we constrain the receptive field from increasing in the deep layers of the network. We design a new architecture for image segmentation- KiU-Net which has two branches: (1) an overcomplete convolutional network Kite-Net which learns to capture fine details and accurate edges of the input, and (2) U-Net which learns high level features. Furthermore, we also propose KiU-Net 3D which is a 3D convolutional architecture for volumetric segmentation. We perform a detailed study of KiU-Net by performing experiments on five different datasets covering various image modalities like ultrasound (US), magnetic resonance imaging (MRI), computed tomography (CT), microscopic and fundus images. The proposed method achieves a better performance as compared to all the recent methods with an additional benefit of fewer parameters and faster convergence. Additionally, we also demonstrate that the extensions of KiU-Net based on residual blocks and dense blocks result in further performance improvements. The implementation of KiU-Net can be found here: https://github.com/jeya-maria-jose/KiU-Net-pytorch

Related papers

• Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework [7.9395601503353825]
  We propose U-Next, a small but mighty framework designed for point cloud semantic segmentation. We build our U-Next by stacking multiple U-Net $L1$ codecs in a nested and densely arranged manner to minimize the semantic gap. Extensive experiments conducted on three large-scale benchmarks including S3DIS, Toronto3D, and SensatUrban demonstrate the superiority and the effectiveness of the proposed U-Next architecture.
  arXiv  Detail & Related papers  (2023-04-03T06:59:08Z)
• GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs [49.55919802779889]
  We propose a Graph Convolution based Spatial Propagation Network (GraphCSPN) as a general approach for depth completion. In this work, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning. Our method achieves the state-of-the-art performance, especially when compared in the case of using only a few propagation steps.
  arXiv  Detail & Related papers  (2022-10-19T17:56:03Z)
• EVC-Net: Multi-scale V-Net with Conditional Random Fields for Brain Extraction [3.4376560669160394]
  EVC-Net adds lower scale inputs on each encoder block. Conditional Random Fields are re-introduced here as an additional step for refining the network's output. Results show that even with limited training resources, EVC-Net achieves higher Dice Coefficient and Jaccard Index.
  arXiv  Detail & Related papers  (2022-06-06T18:21:21Z)
• R2U++: A Multiscale Recurrent Residual U-Net with Dense Skip Connections for Medical Image Segmentation [0.5735035463793008]
  We propose a new U-Net based medical image segmentation architecture R2U++. In the proposed architecture, the plain convolutional backbone is replaced by a deeper recurrent residual convolution block. The semantic gap between encoder and decoder is reduced by dense skip pathways.
  arXiv  Detail & Related papers  (2022-06-03T19:42:44Z)
• Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation [82.61182037130406]
  This work deals with medical image segmentation and in particular with accurate polyp detection and segmentation during colonoscopy examinations. Basic architecture in image segmentation consists of an encoder and a decoder. We compare some variant of the DeepLab architecture obtained by varying the decoder backbone.
  arXiv  Detail & Related papers  (2021-04-02T02:07:37Z)
• BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture [82.64881585566825]
  We present a novel Bi-directional O-shape network (BiO-Net) that reuses the building blocks in a recurrent manner without introducing any extra parameters. Our method significantly outperforms the vanilla U-Net as well as other state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-01T05:07:49Z)
• 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)
• When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks [57.0502745301132]
  We propose Micro-Dense Nets, a novel architecture with global residual learning and local micro-dense aggregations. Our micro-dense block can be integrated with neural architecture search based models to boost their performance.
  arXiv  Detail & Related papers  (2020-04-19T08:34:52Z)
• UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation [20.558512044987125]
  We propose a novel UNet 3+, which takes advantage of full-scale skip connections and deep supervisions. The proposed method is especially benefiting for organs that appear at varying scales.
  arXiv  Detail & Related papers  (2020-04-19T08:05:59Z)

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.