Localizing 2D Ultrasound Probe from Ultrasound Image Sequences Using Deep Learning for Volume Reconstruction
| Autor: | Takafumi Aoki, Jun Ohmiya, Koichi Ito, Kanta Miura, Satoshi Kondo |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Deep learning Feature extraction Convolutional neural network Motion capture 030218 nuclear medicine & medical imaging Image (mathematics) Set (abstract data type) 03 medical and health sciences 0302 clinical medicine Position (vector) Motion estimation Computer vision Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis ISBN: 9783030603335 ASMUS/PIPPI@MICCAI |
| DOI: | 10.1007/978-3-030-60334-2_10 |
| Popis: | This paper presents an ultrasound (US) volume reconstruction method only from US image sequences using deep learning. The proposed method employs the convolutional neural network (CNN) to estimate the position of a 2D US probe only from US images. Our CNN model consists of two networks: feature extraction and motion estimation. We also introduce the consistency loss function to enforce. Through a set of experiments using US image sequence datasets with ground-truth motion measured by a motion capture system, we demonstrate that the proposed method exhibits the efficient performance on probe localization and volume reconstruction compared with the conventional method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|