Motion Correction Using Deep Learning Neural Networks - Effects of Data Representation

被引：3

作者：

Zaydullin, Rifkat ^{[1
]}

Bharath, Anil A. ^{[1
]}

Grisan, Enrico ^{[2
]}

Christensen-Jeffries, Kirsten ^{[3
]}

Bai, Wenjia

Tang, Meng-Xing ^{[1
]}

机构：

[1] Imperial Coll London, Dept Bioengn, London, England

[2] London South Bank Univ, Sch Engn, London, England

[3] Kings Coll London, Dept Biomed Engn, London, England

来源：

2022 IEEE INTERNATIONAL ULTRASONICS SYMPOSIUM (IEEE IUS) | 2022年

基金：

英国医学研究理事会;

关键词：

deep learning; motion correction; motion estimation; ultrasound; data representation;

D O I：

10.1109/IUS54386.2022.9958903

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

An in-silico investigation of the effects of ultrasound data representation on the accuracy of the motion prediction made using deep learning neural networks was carried out. The representations studied include: linear ('envelope'), log compressed, linear with phase and log compressed with phase. A UNet model was trained to predict non-rigid deformation field using a fixed and a moving image pair as the input. The results illustrate that the choice of the representation plays an important role on the accuracy of motion estimation. Specifically, representations with phase information outperform the representations without phase. Furthermore, log-compressed data yielded predictions with higher accuracy than the linear data.

引用

页数：3

共 13 条

[1] VoxelMorph: A Learning Framework for Deformable Medical Image Registration [J].

Balakrishnan, Guha ;

Zhao, Amy ;

Sabuncu, Mert R. ;

Guttag, John ;

Dalca, Adrian, V .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2019, 38 (08) :1788-1800

[2]

Bharadwaj S., 2020, IEEE INT ULTRA SYM, DOI [DOI 10.1109/IUS46767.2020.9251739, DOI 10.1109/ius46767.2020.9251739]

[3] A Pilot Study on Convolutional Neural Networks for Motion Estimation From Ultrasound Images [J].

Evain, Ewan ;

Faraz, Khuram ;

Grenier, Thomas ;

Garcia, Damien ;

De Craene, Mathieu ;

Bernard, Olivier .

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL, 2020, 67 (12) :2565-2573

[4]

?ha, 2011, ULTRASOUND IMAGE DAT

[5] Attention-aware fully convolutional neural network with convolutional long short-term memory network for ultrasound-based motion tracking [J].

Huang, Pu ;

Yu, Gang ;

Lu, Hua ;

Liu, Danhua ;

Xing, Ligang ;

Yin, Yong ;

Kovalchuk, Nataliya ;

Xing, Lei ;

Li, Dengwang .

MEDICAL PHYSICS, 2019, 46 (05) :2275-2285

[6]

Jensen J. A., 1996, Medical & Biological Engineering & Computing, V34, P351

[7] CALCULATION OF PRESSURE FIELDS FROM ARBITRARILY SHAPED, APODIZED, AND EXCITED ULTRASOUND TRANSDUCERS [J].

JENSEN, JA ;

SVENDSEN, NB .

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL, 1992, 39 (02) :262-267

[8] Cascaded one-shot deformable convolutional neural networks: Developing a deep learning model for respiratory motion estimation in ultrasound sequences [J].

Liu, Fei ;

Liu, Dan ;

Tian, Jie ;

Xie, Xiaoyan ;

Yang, Xin ;

Wang, Kun .

MEDICAL IMAGE ANALYSIS, 2020, 65

[9]

Paszke A, 2019, ADV NEUR IN, V32

[10] U-Net: Convolutional Networks for Biomedical Image Segmentation [J].

Ronneberger, Olaf ;

Fischer, Philipp ;

Brox, Thomas .

MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION, PT III, 2015, 9351 :234-241

← 1 2 →