Multi-Atlas Segmentation and Spatial Alignment of the Human Embryo in First Trimester 3D Ultrasound

• URL: http://arxiv.org/abs/2202.06599v3
• Date: Mon, 28 Aug 2023 08:27:30 GMT
• Title: Multi-Atlas Segmentation and Spatial Alignment of the Human Embryo in First Trimester 3D Ultrasound
• Authors: W.A.P. Bastiaansen, M. Rousian, R.P.M. Steegers-Theunissen, W.J. Niessen, A.H.J. Koning, S. Klein
• Abstract summary: We propose a framework for automatic segmentation and spatial alignment of the embryo using deep learning with minimal supervision. Our framework learns to register the embryo to an atlas, which consists of the US images acquired at a range of gestational age. We evaluated different fusion strategies to incorporate multiple atlases.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Segmentation and spatial alignment of ultrasound (US) imaging data acquired in the in first trimester are crucial for monitoring human embryonic growth and development throughout this crucial period of life. Current approaches are either manual or semi-automatic and are therefore very time-consuming and prone to errors. To automate these tasks, we propose a multi-atlas framework for automatic segmentation and spatial alignment of the embryo using deep learning with minimal supervision. Our framework learns to register the embryo to an atlas, which consists of the US images acquired at a range of gestational age (GA), segmented and spatially aligned to a predefined standard orientation. From this, we can derive the segmentation of the embryo and put the embryo in standard orientation. US images acquired at 8+0 till 12+6 weeks GA were used and eight subjects were selected as atlas. We evaluated different fusion strategies to incorporate multiple atlases: 1) training the framework using atlas images from a single subject, 2) training the framework with data of all available atlases and 3) ensembling of the frameworks trained per subject. To evaluate the performance, we calculated the Dice score over the test set. We found that training the framework using all available atlases outperformed ensembling and gave similar results compared to the best of all frameworks trained on a single subject. Furthermore, we found that selecting images from the four atlases closest in GA out of all available atlases, regardless of the individual quality, gave the best results with a median Dice score of 0.72. We conclude that our framework can accurately segment and spatially align the embryo in first trimester 3D US images and is robust for the variation in quality that existed in the available atlases.

Related papers

• Robust Alignment of the Human Embryo in 3D Ultrasound using PCA and an Ensemble of Heuristic, Atlas-based and Learning-based Classifiers Evaluated on the Rotterdam Periconceptional Cohort [0.22485007639406515]
  Standardized alignment of the embryo in 3D ultrasound images aids prenatal growth monitoring.<n>We propose an automated method for standardizing this alignment.<n>We tested our method on 2166 images longitudinally acquired 3D ultrasound scans from 1043 pregnancies.
  arXiv  Detail & Related papers  (2025-11-05T12:30:11Z)
• AtlasSeg: Atlas Prior Guided Dual-U-Net for Cortical Segmentation in Fetal Brain MRI [26.806048154974707]
  Existing segmentation networks can only implicitly learn age-related features. We introduce AtlasSeg, a dual-U-shape convolution network that explicitly integrates GA-specific information as guidance.
  arXiv  Detail & Related papers  (2024-11-05T07:16:32Z)
• Multi-organ Self-supervised Contrastive Learning for Breast Lesion Segmentation [0.0]
  This paper employs multi-organ datasets for pre-training models tailored to specific organ-related target tasks. Our target task is breast tumour segmentation in ultrasound images. Results show that conventional contrastive learning pre-training improves performance compared to supervised baseline approaches.
  arXiv  Detail & Related papers  (2024-02-21T20:29:21Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels [54.58539616385138]
  We introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owN Anatomy (MONA) First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features. Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features.
  arXiv  Detail & Related papers  (2022-09-27T15:50:31Z)
• Placenta Segmentation in Ultrasound Imaging: Addressing Sources of Uncertainty and Limited Field-of-View [12.271784950642344]
  We propose a multi-task learning approach that combines the classification of placental location and semantic placenta segmentation in a single convolutional neural network. Our approach can deliver whole placenta segmentation using a multi-view US acquisition pipeline consisting of three stages: multi-probe image acquisition, image fusion and image segmentation.
  arXiv  Detail & Related papers  (2022-06-29T16:18:55Z)
• Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning with Pairwise Alignment [18.338563869053065]
  This work explores using a convolutional neural network (CNN) to jointly predict the atlas and a stationary velocity field (SVF) parameterization for diffeomorphic image registration. Our results show that the proposed framework achieves better performance than other state-of-the-art image registration algorithms.
  arXiv  Detail & Related papers  (2022-02-07T23:52:21Z)
• Automatic 3D Ultrasound Segmentation of Uterus Using Deep Learning [4.2698418800007865]
  3D ultrasound (US) can be used to image the uterus, but finding the position of uterine boundary in US images is a challenging task. We developed 2D UNet-based networks that are trained based on two scenarios.
  arXiv  Detail & Related papers  (2021-09-20T03:13:57Z)
• Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound [56.631021151764955]
  Standard plane recognition plays an important role in prenatal ultrasound (US) screening. We build a novel multi-label learning scheme to identify multiple standard planes and corresponding anatomical structures simultaneously.
  arXiv  Detail & Related papers  (2021-08-11T06:39:26Z)
• Developmental Stage Classification of EmbryosUsing Two-Stream Neural Network with Linear-Chain Conditional Random Field [74.53314729742966]
  We propose a two-stream model for developmental stage classification. Unlike previous methods, our two-stream model accepts both temporal and image information. We demonstrate our algorithm on two time-lapse embryo video datasets.
  arXiv  Detail & Related papers  (2021-07-13T19:56:01Z)
• Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification [63.44396343014749]
  We propose a new margin-based surrogate loss function for the AUC score. It is more robust than the commonly used. square loss while enjoying the same advantage in terms of large-scale optimization. To the best of our knowledge, this is the first work that makes DAM succeed on large-scale medical image datasets.
  arXiv  Detail & Related papers  (2020-12-06T03:41:51Z)
• Towards segmentation and spatial alignment of the human embryonic brain using deep learning for atlas-based registration [3.8874909016794463]
  We propose an unsupervised deep learning method for atlas based registration to achieve segmentation and spatial alignment of the embryonic brain in a single framework. We trained this network end-to-end and validated it against a ground truth on synthetic datasets designed to resemble the challenges present in 3D first trimester ultrasound.
  arXiv  Detail & Related papers  (2020-05-13T15:23:44Z)
• Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes [52.53375964591765]
  We propose the first fully-automated solution to segment the whole fetal head in US volumes. The segmentation task is firstly formulated as an end-to-end volumetric mapping under an encoder-decoder deep architecture. We then combine the segmentor with a proposed hybrid attention scheme (HAS) to select discriminative features and suppress the non-informative volumetric features.
  arXiv  Detail & Related papers  (2020-04-28T14:43:05Z)

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.