Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis

• URL: http://arxiv.org/abs/2002.08725v1
• Date: Thu, 20 Feb 2020 13:44:29 GMT
• Title: Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis
• Authors: Maxime W. Lafarge, Erik J. Bekkers, Josien P.W. Pluim, Remco Duits, Mitko Veta
• Abstract summary: We propose a framework to encode the geometric structure of the special Euclidean motion group SE(2) in convolutional networks. We show that consistent increase of performances can be achieved when using the proposed framework.
• Score: 11.568329857588099
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rotation-invariance is a desired property of machine-learning models for medical image analysis and in particular for computational pathology applications. We propose a framework to encode the geometric structure of the special Euclidean motion group SE(2) in convolutional networks to yield translation and rotation equivariance via the introduction of SE(2)-group convolution layers. This structure enables models to learn feature representations with a discretized orientation dimension that guarantees that their outputs are invariant under a discrete set of rotations. Conventional approaches for rotation invariance rely mostly on data augmentation, but this does not guarantee the robustness of the output when the input is rotated. At that, trained conventional CNNs may require test-time rotation augmentation to reach their full capability. This study is focused on histopathology image analysis applications for which it is desirable that the arbitrary global orientation information of the imaged tissues is not captured by the machine learning models. The proposed framework is evaluated on three different histopathology image analysis tasks (mitosis detection, nuclei segmentation and tumor classification). We present a comparative analysis for each problem and show that consistent increase of performances can be achieved when using the proposed framework.

Related papers

• Advancing Medical Image Segmentation: Morphology-Driven Learning with Diffusion Transformer [4.672688418357066]
  We propose a novel Transformer Diffusion (DTS) model for robust segmentation in the presence of noise. Our model, which analyzes the morphological representation of images, shows better results than the previous models in various medical imaging modalities.
  arXiv  Detail & Related papers  (2024-08-01T07:35:54Z)
• Boosting Medical Image Segmentation Performance with Adaptive Convolution Layer [6.887244952811574]
  We propose an adaptive layer placed ahead of leading deep-learning models such as UCTransNet. Our approach enhances the network's ability to handle diverse anatomical structures and subtle image details. It consistently outperforms traditional CNNs with fixed kernel sizes with a similar number of parameters.
  arXiv  Detail & Related papers  (2024-04-17T13:18:39Z)
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration [50.62725807357586]
  This article presents a general Bayesian learning framework for multi-modal groupwise image registration. We propose a novel hierarchical variational auto-encoding architecture to realise the inference procedure of the latent variables. Experiments were conducted to validate the proposed framework, including four different datasets from cardiac, brain, and abdominal medical images.
  arXiv  Detail & Related papers  (2024-01-04T08:46:39Z)
• RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy [83.4885991036141]
  RIDE is a learning-based method for rotation-equivariant detection and invariant description. It is trained in a self-supervised manner on a large curation of endoscopic images. It sets a new state-of-the-art performance on matching and relative pose estimation tasks.
  arXiv  Detail & Related papers  (2023-09-18T08:16:30Z)
• Beyond CNNs: Exploiting Further Inherent Symmetries in Medical Image Segmentation [21.6412682130116]
  We propose a novel group equivariant segmentation framework by encoding those inherent symmetries for learning more precise representations. Based on our novel framework, extensive experiments conducted on real-world clinical data demonstrate that a Group Equivariant Res-UNet (named GER-UNet) outperforms its regular CNN-based counterpart. The newly built GER-UNet also shows potential in reducing the sample complexity and the redundancy of filters.
  arXiv  Detail & Related papers  (2022-07-29T04:28:20Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation [51.916106055115755]
  We propose a new CNN architecture that is pose and scale invariant thanks to the use of Spatial Transformer Network (STN) Our architecture is composed of three sequential modules that are estimated together during training. We test the proposed method in kidney and renal tumor segmentation on abdominal pediatric CT scanners.
  arXiv  Detail & Related papers  (2021-07-06T14:50:03Z)
• SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size [95.00667357120442]
  Changing the object location, rotation and size may affect the predictions in non-trivial ways. We perform a fine-grained analysis of robustness with respect to these factors of variation using SI-Score, a synthetic dataset.
  arXiv  Detail & Related papers  (2021-04-09T05:00:49Z)
• Orientation-Disentangled Unsupervised Representation Learning for Computational Pathology [6.468635277309852]
  We propose to extend the Variational Auto-Encoder framework by leveraging the group structure of rotation-equivariant convolutional networks. We show that the trained models efficiently disentangle the inherent orientation information of single-cell images.
  arXiv  Detail & Related papers  (2020-08-26T16:57:45Z)
• 3D Solid Spherical Bispectrum CNNs for Biomedical Texture Analysis [3.579867431007686]
  Locally Rotation Invariant (LRI) operators have shown great potential in biomedical texture analysis. We investigate the benefits of using the bispectrum over the spectrum in the design of a LRI layer embedded in a shallow Convolutional Neural Network (CNN) for 3D image analysis.
  arXiv  Detail & Related papers  (2020-04-28T09:01:13Z)
• Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation [84.7571086566595]
  We propose improvements over previous GAN-based medical image synthesis methods by jointly encoding the intrinsic relationship of geometry and shape. The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.
  arXiv  Detail & Related papers  (2020-03-31T11:50:43Z)

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.