A Single-Shot Region-Adaptive Network for Myotendinous Junction Segmentation in Muscular Ultrasound Images

Zhou, Guangquan; Huo, En-Ze; Yuan, Mei; Zhou, Ping; Wang, Ruo-Li; Wang, Kai‐Ni; Chen, Yang; He, Xiaopu

doi:10.1109/tuffc.2020.2979481

Cited by 20 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a similar purpose, Zimmer et al used an auxiliary task to improve the performance and introduced a method to extract the whole placenta at late gestation using multi-view images [26], [27]. Zhou et al proposed a fully automated solution to segment the myotendinous junction region in successive ultrasound images in a single shot using a region-adaptive network (RAN), which learns about the salient information of the myotendinous junction [28]. They also introduced an approach that combined a voxel-based fully convolution network (Voxel-FCN) and a continuous max-flow post-processing module to automatically segment the carotid media-adventitia (MAB) and lumen-intima boundaries (LIB) and to generate the vessel-wall-volume (VWV) measurement from three-dimensional ultrasound images [29].…”

Section: A Related Workmentioning

confidence: 99%

Investigating Shift-Variance of Convolutional Neural Networks in Ultrasound Image Segmentation

Sharifzadeh,

Benali,

Rivaz

2021

Preprint

View full text Add to dashboard Cite

While accuracy is an evident criterion for ultrasound image segmentation, output consistency across different tests is equally crucial for tracking changes in regions of interest in applications such as monitoring the patients' response to treatment, measuring the progression or regression of the disease, reaching a diagnosis, or treatment planning. Convolutional neural networks (CNNs) have attracted rapidly growing interest in automatic ultrasound image segmentation recently. However, CNNs are not shift-equivariant, meaning that if the input translates, e.g., in the lateral direction by one pixel, the output segmentation may drastically change. To the best of our knowledge, this problem has not been studied in ultrasound image segmentation or even more broadly in ultrasound images. Herein, we investigate and quantify the shift-variance problem of CNNs in this application and further evaluate the performance of a recently published technique, called BlurPooling, for addressing the problem. In addition, we propose the Pyramidal BlurPooling method that outperforms BlurPooling in both output consistency and segmentation accuracy. Finally, we demonstrate that data augmentation is not a replacement for the proposed method. Source code is available at https://git.io/pbpunet and http://code.sonography.ai.

show abstract

Section: A Related Workmentioning

confidence: 99%

Investigating Shift-Variance of Convolutional Neural Networks in Ultrasound Image Segmentation

Sharifzadeh,

Benali,

Rivaz

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep neural networks (DNN) have significantly advanced various medical image analysis tasks, including anatomical landmark localization [25], [26], [27]. MTJ detection has also seen great promise in recent years with the availability of deeplearning models [28], [29], [30], [31]. Some DNN methods regress the MTJ positions by learning the map from the input appearance to the image coordinates [30], [31].…”

Section: Introductionmentioning

confidence: 99%

“…However, these methods require the network to learn a complicated mapping between a landmark's appearance and the corresponding image coordinates, making them usually challenging to train [27], [32]. Zhou et al [29] proposed a proposal-based DNN method to integrate an MTJ landmark regression branch into the Faster Region-based Convolutional Neural Network (Faster R-CNN) [33] architecture for adaptively segmenting the MTJ region more accurately. However, these DNN methods require a large training dataset that is expensive to annotate and acquire, especially in ultrasound videos.…”

Section: Introductionmentioning

confidence: 99%

Automatic Myotendinous Junction Identification in Ultrasound Images Based on Junction-Based Template Measurements

Zhou

Hua

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

Tracking the myotendinous junction (MTJ) motion in consecutive ultrasound images is essential to assess muscle and tendon interaction and understand the mechanics' muscle-tendon unit and its pathological conditions during motion. However, the inherent speckle noises and ambiguous boundaries deter the reliable identification of MTJ, thus restricting their usage in human motion analysis. This study advances a fully automatic displacement measurement method for MTJ using prior shape knowledge on the Y-shape MTJ, precluding the influence of irregular and complicated hyperechoic structures in muscular ultrasound images. Our proposed method first adopts the junction candidate points using a combined measure of Hessian matrix and phase congruency, followed by a hierarchical clustering technique to refine the candidates approximating the position of the MTJ. Then, based on the prior knowledge of Y-shape MTJ, we finally identify the best matching junction points according to intensity distributions and directions of their branches using multiscale Gaussian templates and a Kalman filter. We evaluated our proposed method using the ultrasound scans of the gastrocnemius from 8 young, healthy volunteers. Our results present more consistent with the manual method in the MTJ tracking method than existing optical flow tracking methods, suggesting its potential in facilitating muscle and tendon function examinations with in vivo ultrasound imaging.

show abstract

“…For better assessing the mechanics and pathological conditions of the muscle‐tendon unit in consecutive ultrasound images, Zhou et al. used a model learns salient information of myotendinous junction with a composite architecture, in which a region‐based multi‐task learning network explores the region containing myotendinous junction, while a parallel end‐to‐end U‐shape path extracts the myotendinous junction structure from the adaptively selected region for combating data imbalance and boundary ambiguity [15]. UNets have also been applied to CT image segmentation, Zhang et al.…”

Section: Introductionmentioning

confidence: 99%

“…Ge et al proposed a K-shaped Unified Network, the first end-to-end framework to simultaneously segment LV from apical four-chamber and twochamber views of echocardiography, and directly quantify LV from major-and minor-axis dimensions (1D), area (2D), and volume (3D), in sequence [14]. For better assessing the mechanics and pathological conditions of the muscle-tendon unit in consecutive ultrasound images, Zhou et al used a model learns salient information of myotendinous junction with a composite architecture, in which a region-based multi-task learning network explores the region containing myotendinous junction, while a parallel end-to-end U-shape path extracts the myotendinous junction structure from the adaptively selected region for combating data imbalance and boundary ambiguity [15]. UNets have also been applied to CT image segmentation, Zhang et al established a novel end-to-end deep convolutional neural networks model for pursuing high-accurate automatic pancreas segmentation but with low computational cost [16].…”

Section: Introductionmentioning

confidence: 99%

MFAUNet: Multiscale feature attentive U‐Net for cardiac MRI structural segmentation

Peng

Guo

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

The accurate and robust automatic segmentation of cardiac structures in magnetic resonance imaging (MRI) is significant in calculating cardiac clinical functional indices, and diagnosing heart diseases. Most U‐Net based methods use pooling, transposed convolution, and skip connection operations to integrate the multiscale features for improved segmentation in cardiac MRI. However, this architecture lacks adequate semantic connection between the channel and spatial information, and robustness in segmenting objects with significant shape variations. In this paper, a new multiscale feature attentive U‐Net for cardiac MRI structural segmentation method is proposed. An attention mechanism is adopted after concatenating the multi‐level features to aggregate different scale features and determine on which features to focus. Cascade and parallel dilated convolution is also employed in the decoder blocks and skip connection is employed to enhance the ability of sensing receptive fields for multiscale context information. Furthermore, deep supervision approach with a loss function that combines the dice and cross‐entropy losses to reduce overfitting and ensure better prediction is introduced. The proposed method was evaluated on three public cardiac datasets. The experimental results indicate that the method achieved competitive segmentation performance with the three datasets, which verifies the robustness and generalisability of the proposed network. In comparison with conventional U‐Net methods, the model leverages attention mechanism and dilated convolution block, which increases the semantic connection between the channel and the spatial information, and improves the robustness of the right ventricle segmentation performance. From the view of the Dice scores and segmentation results, the multiscale feature attentive U‐Net method is one of effective methods in segmenting cardiac MRI structures.

show abstract

A Single-Shot Region-Adaptive Network for Myotendinous Junction Segmentation in Muscular Ultrasound Images

Cited by 20 publications

References 53 publications

Investigating Shift-Variance of Convolutional Neural Networks in Ultrasound Image Segmentation

Investigating Shift-Variance of Convolutional Neural Networks in Ultrasound Image Segmentation

Automatic Myotendinous Junction Identification in Ultrasound Images Based on Junction-Based Template Measurements

MFAUNet: Multiscale feature attentive U‐Net for cardiac MRI structural segmentation

Contact Info

Product

Resources

About