Localizing 2D Ultrasound Probe from Ultrasound Image Sequences Using Deep Learning for Volume Reconstruction

Miura, Kanta; Ito, Koichi; Aoki, Takafumi; Ohmiya, Jun; Kondo, Satoshi

doi:10.1007/978-3-030-60334-2_10

Cited by 14 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The encoder's chief purpose is to estimate the position per pixel and then concatenate the acquired feature map with a relevant part in the decoder. In subsequent studies, FlowNet has been used to register and fuse images [46][47][48]. However, as the network in a DNN deepens, gradient and information tend to vanish from output to input, and vice versa.…”

Section: Applied Methodsmentioning

confidence: 99%

Speckle noise reduction on aligned consecutive ultrasound frames via deep neural network

Mikaeili,

Bilge,

Kılıçaslan

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Despite the benefits of ultrasound imaging systems for medical diagnosis and treatment, ultrasound images are prone to low resolution and contrast due to ultrasound’s inherent attributes, as well as affected by speckle noise that directly influences their quality. In retrospective studies, diverse filters have been applied to minimize the effects of speckle noise and enhance the quality of ultrasound images. In this article, we propose a method of enhancing ultrasound images inspired by synthetic aperture imaging, which provides high-resolution images by adding low-resolution images and measuring the probe’s movement. Our proposed method does not involve synthetic aperture imaging but compensates for the motion effect in the temporal dimension, aligns consecutive images, and stacks aligned images to suppress speckle noise and consequently enhance the resolution of ultrasound images. We exploited deep neural network models to estimate motion parameters between consecutive ultrasound images. In a new database of ultrasound images, we also collected the images’ position-related information implicitly measured in inertial measurement units, which was exploited as a ground truth for motion parameters between consecutive images. Compared with other image-enhancing techniques involving conventional filters and deep neural network modalities, our method demonstrated superiority in enhancing the quality of ultrasound images. We also found that estimating motion parameters directly influenced the success of the image-stacking process. As in ablation studies in deep neural networks, we additionally investigated the effect of dropping some images in the temporal dimension, which revealed that contextual differences and excessive rates of movement in successive ultrasound images weakens the image-stacking process and thus the potential enhancement of ultrasound images.

show abstract

Section: Applied Methodsmentioning

confidence: 99%

Speckle noise reduction on aligned consecutive ultrasound frames via deep neural network

Mikaeili,

Bilge,

Kılıçaslan

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…One study [14] proposed a dual-branch balanced feature extraction network to make the model equally sensitive to both the frame and volume information. For volume reconstruction problems [27], [28], the addition of very local spatial context is often used through the addition of the previous slice as input. It contributes to the relative localization between successive slices.…”

Section: B 2d/3d Deep Registration Strategies For Real-time Navigatio...mentioning

confidence: 99%

“…Net (with T prior = T t−1 ) 11.72 ± 6 28. 5.06 ±5.70 8.87 ± 5.82 5.01 ± 7.82 5.80 ± 7.00 7.30 ± 7.25 7.28 ± 8.50 Without network (only T prior ) 7.70 ± 6.24 9.65 ± 6.11 6.35 ± 6.88 5.91 ± 6.77 9.39 ± 7.65 7.63 ± 7.67 Scenario Im+PT SpT-Net (with T prior = T t−1 ) 11.72 ± 6.28 2.68 ± 1.49 2.81 ± 2.00 5.28 ± 6.30 3.97 ± 2.03 3.15 ± 2.17 5.91 ± 7.19 Without network (only T prior * T P T ) 3.11 ± 2.67 3.15 ± 2.94 5.23 ± 6.32 4.28 ± 2.93 3.53 ± 3.10 5.84 ± 7.22…”

mentioning

confidence: 99%

2D/3D Deep Registration Along Trajectories With Spatiotemporal Context: Application to Prostate Biopsy Navigation

Dupuy

Beitone

Troccaz

et al. 2023

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

“…FlowNet and densely connected networks were used in [11,21]. In [12], ResNet and FlowNetS were integrated for a better localization and optical flow estimation, and consistency loss derived from stereo vision was added. Forward consistency loss was then proposed in [14].…”

Section: Introductionmentioning

confidence: 99%

Trackerless freehand ultrasound with sequence modelling and auxiliary transformation over past and future frames

Li¹,

Shen²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Three-dimensional (3D) freehand ultrasound (US) reconstruction without a tracker can be advantageous over its two-dimensional or tracked counterparts in many clinical applications. In this paper, we propose to estimate 3D spatial transformation between US frames from both past and future 2D images, using feed-forward and recurrent neural networks (RNNs). With the temporally available frames, a further multitask learning algorithm is proposed to utilise a large number of auxiliary transformation-predicting tasks between them. Using more than 40,000 US frames acquired from 228 scans on 38 forearms of 19 volunteers in a volunteer study, the hold-out test performance is quantified by frame prediction accuracy, volume reconstruction overlap, accumulated tracking error and final drift, based on ground-truth from an optical tracker. The results show the importance of modelling the temporal-spatially correlated input frames as well as output transformations, with further improvement owing to additional past and/or future frames. The best performing model was associated with predicting transformation between moderately-spaced frames, with an interval of less than ten frames at 20 frames per second (fps). Little benefit was observed by adding frames more than one second away from the predicted transformation, with or without LSTM-based RNNs. Interestingly, with the proposed approach, explicit within-sequence loss that encourages consistency in composing transformations or minimises accumulated error may no longer be required. The implementation code and volunteer data 1 will be made publicly available ensuring reproducibility and further research.

show abstract

Localizing 2D Ultrasound Probe from Ultrasound Image Sequences Using Deep Learning for Volume Reconstruction

Cited by 14 publications

References 18 publications

Speckle noise reduction on aligned consecutive ultrasound frames via deep neural network

Speckle noise reduction on aligned consecutive ultrasound frames via deep neural network

2D/3D Deep Registration Along Trajectories With Spatiotemporal Context: Application to Prostate Biopsy Navigation

Trackerless freehand ultrasound with sequence modelling and auxiliary transformation over past and future frames

Contact Info

Product

Resources

About