FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound

• URL: http://arxiv.org/abs/2310.19293v1
• Date: Mon, 30 Oct 2023 06:18:47 GMT
• Title: FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound
• Authors: Chaoyu Chen, Xin Yang, Yuhao Huang, Wenlong Shi, Yan Cao, Mingyuan Luo, Xindi Hu, Lei Zhue, Lequan Yu, Kejuan Yue, Yuanji Zhang, Yi Xiong, Dong Ni, Weijun Huang
• Abstract summary: We propose a novel 3D fetal pose estimation framework (called FetusMapV2) to overcome the above challenges. First, we propose a scheme that explores the complementary network structure-unconstrained and activation-unreserved GPU memory management approaches. Second, we design a novel Pair Loss to mitigate confusion caused by symmetrical and similar anatomical structures. Third, we propose a shape priors-based self-supervised learning by selecting the relatively stable landmarks to refine the pose online.
• Score: 28.408626329596668
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fetal pose estimation in 3D ultrasound (US) involves identifying a set of associated fetal anatomical landmarks. Its primary objective is to provide comprehensive information about the fetus through landmark connections, thus benefiting various critical applications, such as biometric measurements, plane localization, and fetal movement monitoring. However, accurately estimating the 3D fetal pose in US volume has several challenges, including poor image quality, limited GPU memory for tackling high dimensional data, symmetrical or ambiguous anatomical structures, and considerable variations in fetal poses. In this study, we propose a novel 3D fetal pose estimation framework (called FetusMapV2) to overcome the above challenges. Our contribution is three-fold. First, we propose a heuristic scheme that explores the complementary network structure-unconstrained and activation-unreserved GPU memory management approaches, which can enlarge the input image resolution for better results under limited GPU memory. Second, we design a novel Pair Loss to mitigate confusion caused by symmetrical and similar anatomical structures. It separates the hidden classification task from the landmark localization task and thus progressively eases model learning. Last, we propose a shape priors-based self-supervised learning by selecting the relatively stable landmarks to refine the pose online. Extensive experiments and diverse applications on a large-scale fetal US dataset including 1000 volumes with 22 landmarks per volume demonstrate that our method outperforms other strong competitors.

Related papers

• Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videos [0.8579241568505183]
  We propose an uncertainty-aware deep learning model for automated 3D plane localization in 2D fetal brain images. Our proposed method, QAERTS, demonstrates superior pose estimation accuracy than the state-of-the-art and most of the uncertainty-based approaches.
  arXiv  Detail & Related papers  (2024-05-21T22:42:08Z)
• Ultrasound Plane Pose Regression: Assessing Generalized Pose Coordinates in the Fetal Brain [9.465965149145559]
  We aim to build a US plane localization system for 3D visualization, training, and guidance without integrating additional sensors. This work builds on our previous work, which predicts the six-dimensional (6D) pose of arbitrarily oriented US planes slicing the fetal brain. We investigate the impact of registration quality in the training and testing data and its subsequent effect on trained models.
  arXiv  Detail & Related papers  (2023-01-19T21:16:36Z)
• Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats [80.12253291709673]
  We propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model.
  arXiv  Detail & Related papers  (2022-12-29T22:22:49Z)
• Agent with Tangent-based Formulation and Anatomical Perception for Standard Plane Localization in 3D Ultrasound [56.7645826576439]
  We introduce a novel reinforcement learning framework for automatic SP localization in 3D US. First, we formulate SP localization in 3D US as a tangent-point-based problem in RL to restructure the action space. Second, we design an auxiliary task learning strategy to enhance the model's ability to recognize subtle differences crossing Non-SPs and SPs in plane search.
  arXiv  Detail & Related papers  (2022-07-01T14:53:27Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• Self Context and Shape Prior for Sensorless Freehand 3D Ultrasound Reconstruction [61.62191904755521]
  3D freehand US reconstruction is promising in addressing the problem by providing broad range and freeform scan. Existing deep learning based methods only focus on the basic cases of skill sequences. We propose a novel approach to sensorless freehand 3D US reconstruction considering the complex skill sequences.
  arXiv  Detail & Related papers  (2021-07-31T16:06:50Z)
• Map3D: Registration Based Multi-Object Tracking on 3D Serial Whole Slide Images [10.519063258650508]
  We propose a novel Multi-object Association for Pathology in 3D (Map3D) method for automatically identifying and associating large-scale cross-sections of 3D objects. Our proposed method Map3D achieved MOTA= 44.6, which is 12.1% higher than the non deep learning benchmarks.
  arXiv  Detail & Related papers  (2020-06-10T19:31:02Z)
• 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)
• Region Proposal Network with Graph Prior and IoU-Balance Loss for Landmark Detection in 3D Ultrasound [16.523977092204813]
  3D ultrasound (US) can facilitate detailed prenatal examinations for fetal growth monitoring. To analyze a 3D US volume, it is fundamental to identify anatomical landmarks accurately. We exploit an object detection framework to detect landmarks in 3D fetal facial US volumes.
  arXiv  Detail & Related papers  (2020-04-01T03:00:03Z)
• FetusMap: Fetal Pose Estimation in 3D Ultrasound [42.59502360552173]
  We propose to estimate the 3D pose of fetus in US volumes to facilitate its quantitative analyses. This is the first work about 3D pose estimation of fetus in the literature. We propose a self-supervised learning (SSL) framework to finetune the deep network to form visually plausible pose predictions.
  arXiv  Detail & Related papers  (2019-10-11T01:45:09Z)

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.