Automatic 3D Ultrasound Segmentation of Uterus Using Deep Learning

  title={Automatic 3D Ultrasound Segmentation of Uterus Using Deep Learning},
  author={Bahareh Behboodi and Hassan Rivaz and S. Lalondrelle and Emma J. Harris},
  journal={2021 IEEE International Ultrasonics Symposium (IUS)},
On-line segmentation of the uterus can aid effective image-based guidance for precise delivery of dose to the target tissue (the uterocervix) during cervix cancer radiotherapy. 3D ultrasound (US) can be used to image the uterus, however, finding the position of uterine boundary in US images is a challenging task due to large daily positional and shape changes in the uterus, large variation in bladder filling, and the limitations of 3D US images such as low resolution in the elevational… 

Figures and Tables from this paper


Two-stage ultrasound image segmentation using U-Net and test time augmentation
The proposed two-stage technique shows promising results for segmentation of breast US images and has a much smaller chance of failure.
Ultrasound segmentation using U-Net: learning from simulated data and testing on real data
  • Bahareh Behboodi, H. Rivaz
  • Computer Science, Engineering
    2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2019
This study proposes the use of simulated ultrasound (US) images for training the U-Net deep learning segmentation architecture and test on tissue-mimicking phantom data collected by an ultrasound machine, and demonstrates that the trained architecture on the simulated data is transferrable to real data.
The Stacked-Ellipse Algorithm: An Ultrasound-Based 3-D Uterine Segmentation Tool for Enabling Adaptive Radiotherapy for Uterine Cervix Cancer
The stacked-ellipse (SE) algorithm was developed to rapidly segment the uterus on 3-D ultrasound (US) for the purpose of enabling US-guided adaptive radiotherapy (RT) for uterine cervix cancer
Interfractional variation in position of the uterus during radical radiotherapy for cervical cancer.
  • S. Huh, W. Park, Youngyih Han
  • Medicine
    Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
  • 2004
Positional changes of the uterus during radiotherapy should be considered in the treatment planning of 3DCRT or IMRT, particularly in patients under 60 years or those with tumor size greater than 4 cm in diameter.
Fibroid Detection in Ultrasound Uterus Images Using Image Processing
This paper endows a method to segment uterus fibroid from ultrasound scanned images and extracts some shape-based features to detect fibroid region.
Deep classification of breast cancer in ultrasound images: more classes, better results with multi-task learning
Ultrasound (US) is a low-cost, portable, and safe tool for breast cancer screening. However, automatic classification of invasive ductal carcinoma (IDC) in US is a difficult classification task due
Objective Analysis of Neck Muscle Boundaries for Cervical Dystonia Using Ultrasound Imaging and Deep Learning
Using US, neck muscle shape alone discriminates Dystonia from healthy controls and allows online, automated visualization, and diagnostic analysis of cervical dystonia and segmentation of individual muscles for targeted injection.
Deep learning based classification of focal liver lesions with contrast-enhanced ultrasound
Deep learning is employed to classify benign and malignant focal liver lesions based on time intensity curves extracted from dynamic CEUS videos using sparse non-negative matrix factorizations.
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Ultrasound Scatterer Density Classification Using Convolutional Neural Networks and Patch Statistics
This work adapt convolutional neural network architectures for QUS and improves the network’s performance by utilizing patch statistics as additional input channels, and demonstrates the potential of CNNs in classifying scatterer density in ultrasound images.