Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data

Ma, Chunwei; Ji, Zhanghexuan; Gao, Mingchen

doi:10.48550/arxiv.1909.09716

Cited by 4 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The last columns in Table 1 and 2 show the runtime comparisons among different methods using a single GTX 1080 Ti. We used the same hyperparameter settings in [9] for Gatys et al [8] and followed the original settings in STROTSS [10]. The online style transfer methods above require much time to iteratively reconstruct a fluctuating stylized result, which goes against the clinical requirements.…”

Section: Resultsmentioning

confidence: 99%

“…To meet clinical US scanning requirements, following aspects should be considered: (a) The method should enable universal transfer between any stylecontent image pairs. (b) Transfer results should be stable rather than fluctuant [9,10]. (c) Image structure details should be highly preserved.…”

Section: Universal and High Quality Style Transfermentioning

confidence: 99%

“…Different from previous online style transfer methods which may distort image details [9], the proposed WaveCT has two main advantages. First, WaveCT replaces vanilla max-pooling/unpooling layers with the Haar wavelet pooling/unpooling layers, which can exactly reconstruct the stylized image with minimal structure loss.…”

Section: Universal and High Quality Style Transfermentioning

confidence: 99%

“…This is not suitable for the open scenario with unpredictable image appearance shift. By revisiting the style transfer [8], Ma et al built an online scheme to remove appearance shift in the cardiovascular magnetic resonance (MR) image segmentation [9]. However, their style transfer method is unstable and may destroy image details.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Remove Appearance Shift for Ultrasound Image Segmentation via Fast and Universal Style Transfer

Liu¹,

Yang²,

Gao³

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) suffer from the performance degradation when image appearance shift occurs, especially in ultrasound (US) image segmentation. In this paper, we propose a novel and intuitive framework to remove the appearance shift, and hence improve the generalization ability of DNNs. Our work has three highlights. First, we follow the spirit of universal style transfer to remove appearance shifts, which was not explored before for US images. Without sacrificing image structure details, it enables the arbitrary style-content transfer. Second, accelerated with Adaptive Instance Normalization block, our framework achieved real-time speed required in the clinical US scanning. Third, an efficient and effective style image selection strategy is proposed to ensure the target-style US image and testing content US image properly match each other. Experiments on two large US datasets demonstrate that our methods are superior to state-of-the-art methods on making DNNs robust against various appearance shifts.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Universal and High Quality Style Transfermentioning

confidence: 99%

Section: Universal and High Quality Style Transfermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Remove Appearance Shift for Ultrasound Image Segmentation via Fast and Universal Style Transfer

Liu¹,

Yang²,

Gao³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Other areas where these NST decoders might be tested are data augmentation of medical data (see [13,14]) and material translation [15]; basically, any domain where we can…”

Section: Discussionmentioning

confidence: 99%

Deep Layer Aggregation Architectures for Photorealistic Universal Style Transfer

Dediu

Vasile

Bîră

2023

Sensors

View full text Add to dashboard Cite

This paper introduces a deep learning approach to photorealistic universal style transfer that extends the PhotoNet network architecture by adding extra feature-aggregation modules. Given a pair of images representing the content and the reference of style, we augment the state-of-the-art solution mentioned above with deeper aggregation, to better fuse content and style information across the decoding layers. As opposed to the more flexible implementation of PhotoNet (i.e., PhotoNAS), which targets the minimization of inference time, our method aims to achieve better image reconstruction and a more pleasant stylization. We propose several deep layer aggregation architectures to be used as wrappers over PhotoNet, to enhance the stylization and quality of the output image.

show abstract

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation

Tajbakhsh¹,

Jeyaseelan²,

Li³

et al. 2019

Preprint

113

View full text Add to dashboard Cite

Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data

Cited by 4 publications

References 10 publications

Remove Appearance Shift for Ultrasound Image Segmentation via Fast and Universal Style Transfer

Remove Appearance Shift for Ultrasound Image Segmentation via Fast and Universal Style Transfer

Deep Layer Aggregation Architectures for Photorealistic Universal Style Transfer

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation

Contact Info

Product

Resources

About