Standard Plane Localization in Fetal Ultrasound via Domain Transferred Deep Neural Networks

By Hao Chen, Dong Ni, Jing Qin, Shengli Li, Xin Yang, Tianfu Wang, P. Heng. IEEE journal of biomedical and health informatics, 2015

348 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Pediatrics, Perinatology and Child Health

View Paper: https://www.semanticscholar.org/paper/59ca2eaaee0d3486843f324dacf26b314203dc29

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Pediatrics, Perinatology and Child Health

Daniel Rueckert

Citations in the corpus

Fine-tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally (2017, methodology): “In [5], a fine-tuned pre-trained CNN was applied for localizing standard planes in ultrasound images.”
SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound (2016, methodology): “Furthermore, data obtained using the sweep protocol are typically only 2–5 seconds long and consist of fewer than 50 frames [10].”
An Ensemble of Fine-Tuned Convolutional Neural Networks for Medical Image Classification (2017, methodology): “It has been successfully utilised in various modality or disease specific studies [29]–[31].”
Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges (2019, background): “Transfer learning can be done in three major levels: (1) full network adaption, which is to initialize the weights by a pre-trained network (rather than a random initialization) but update them all during the training [9, 77].”
Deep Learning in Medical Ultrasound Analysis: A Review (2019, background): “Both strategies achieve excellent performance in several speciﬁc tasks [77,78].”
A survey on deep learning in medical image analysis (2017, methodology): “Chen et al. (2015a), for example, employed LSTM models to incorporate temporal information of consecutive sequence in US videos for fetal standard plane detection.”
DeepPap: Deep Convolutional Networks for Cervical Cell Classification (2017, background): “such as CT [35], ultrasound [47] and X-ray [44], [48] datasets, and can subsequently reduce overfitting on small datasets while boosting performance through fine-tuning.”
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes (2018, background): “source domain efficiently transferred to another domain) for boosting the performance [23], [24].”
Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results From the MICCAI 2015 Endoscopic Vision Challenge (2017, neutral): “In addition, feature-rich hierarchies from a large scale auxiliary dataset are transferred into the model to reduce over-fitting and further boost detection performance [41].”
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? (2016, methodology): “[32] suggested the use of a fine-tuned pre-trained CNN”
Deep Convolutional Neural Networks for breast cancer screening (2018, background): “It has been very effective in the medical domain [13,14] when the amount of data is normally limited.”
Real-Time Standard Scan Plane Detection and Localisation in Fetal Ultrasound Using Fully Convolutional Neural Networks (2016, methodology): “US sweeps are acquired by moving the US probe from the cervix upwards in one continuous motion [3].”
Convolutional neural networks based transfer learning for diabetic retinopathy fundus image classification (2017, background): “In paper [11], in order to locate the fetal abdominal standard plane in ultrasound videos (US),”
CNNs for automatic glaucoma assessment using fundus images: an extensive validation (2019, background): “The study made by Chen et al. [17] demonstrated that the use of a fine-tuned pre-trained CNN for localizing standard planes in ultrasound images out-performed the state-of-the-art for the fetal abdominal standard plane (FASP).”
VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation (2016, background): “Over the last few years, deep learning especially deep convolutional neural networks (CNNs) have emerged as one of the most prominent approaches for image recognition problems in various domains including computer vision [15, 31, 18, 33] and medical image computing [25, 26, 3, 30].”
Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “And, a DNN based method was proposed to successfully identify the fetal abdominal standard plane in UlS images [146].”