Synthesize Mammogram from Digital Breast Tomosynthesis with Gradient Guided cGANs

Jiang, Gongfa; Lu, Yao; Wei, Jun; Xu, Yuesheng

doi:10.1007/978-3-030-32226-7_89

Cited by 13 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To train the high‐frequency network

{G^H}

, we used GGGAN 13 with perceptual loss 14,16 and multi‐frequency MSE loss as the regularization terms. In GGGAN, a discriminator network, which is denoted by D , is trained to distinguish between generated SDM image

{I_S}

and the ground truth image

{I_D}

.…”

Section: Methodsmentioning

confidence: 99%

“…The network architecture of the low-frequency network G L is shown in Figure 2. To extract 3D information in the input DBT volume, we used shared weight group convolution (SWGC) 13,14 in the encoder path of U-net.…”

Section: Network Architecturementioning

confidence: 99%

“…Deep learning has become a widely used solution for image-to-image translation. [10][11][12] Recent studies 13,14 proposed using gradient-guided generative adversarial networks (GGGAN) as the objective function for training a single deep convolutional neural network (DCNN) to directly generate an SDM image from the DBT volume. In GGGAN, a discriminator network using gradient maps as additional inputs is trained to distinguish between the generated images and ground-truth images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi‐scale cascaded networks for synthesis of mammogram to decrease intensity distortion and increase model‐based perceptual similarity

Jiang

Zhou

et al. 2022

Medical Physics

Self Cite

View full text Add to dashboard Cite

Synthetic digital mammogram (SDM) is a 2D image generated from digital breast tomosynthesis (DBT) and used as a substitute for a full-field digital mammogram (FFDM) to reduce the radiation dose for breast cancer screening. The previous deep learning-based method used FFDM images as the ground truth, and trained a single neural network to directly generate SDM images with similar appearances (e.g., intensity distribution, textures) to the FFDM images. However, the FFDM image has a different texture pattern from DBT. The difference in texture pattern might make the training of the neural network unstable and result in high-intensity distortion, which makes it hard to decrease intensity distortion and increase perceptual similarity (e.g., generate similar textures) at the same time. Clinically, radiologists want to have a 2D synthesized image that feels like an FFDM image in vision and preserves local structures such as both mass and microcalcifications (MCs) in DBT because radiologists have been trained on reading FFDM images for a long time, while local structures are important for diagnosis. In this study, we proposed to use a deep convolutional neural network to learn the transformation to generate SDM from DBT. Method: To decrease intensity distortion and increase perceptual similarity, a multi-scale cascaded network (MSCN) is proposed to generate low-frequency structures (e.g., intensity distribution) and high-frequency structures (e.g., textures) separately. The MSCN consist of two cascaded sub-networks: the first sub-network is used to predict the low-frequency part of the FFDM image; the second sub-network is used to generate a full SDM image with textures similar to the FFDM image based on the prediction of the first sub-network. The meansquared error (MSE) objective function is used to train the first sub-network, termed low-frequency network, to generate a low-frequency SDM image. The gradient-guided generative adversarial network's objective function is to train the second sub-network, termed high-frequency network, to generate a full SDM image with textures similar to the FFDM image. Results: 1646 cases with FFDM and DBT were retrospectively collected from the Hologic Selenia system for training and validation dataset, and 145 cases with masses or MC clusters were independently collected from the Hologic Selenia system for testing dataset. For comparison, the baseline network has the same architecture as the high-frequency network and directly generates a full SDM image. Compared to the baseline method, the proposed MSCN improves the peak-to-noise ratio from 25.3 to 27.9 dB and improves the Gongfa Jiang, Zilong He, and Yuanpin Zhou contributed equally to this work.

show abstract

“…To train the high‐frequency network

{G^H}

{I_S}

and the ground truth image

{I_D}

.…”

Section: Methodsmentioning

confidence: 99%

Section: Network Architecturementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐scale cascaded networks for synthesis of mammogram to decrease intensity distortion and increase model‐based perceptual similarity

Jiang

Zhou

et al. 2022

Medical Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The existing medical image to image translation (Zhang et al, 2018;Yu et al, 2019;Zhang et al, 2018;Jiang et al, 2019;Ren et al, 2021) has demonstrated considerable prospects for both research and clinical analysis. Huang et al (Huang et al, 2021) proposed an unsupervised multivariate canonical CSC 4 Net to perform cross-modal image synthesis considering both intra-modal and inter-modal heterogeneity.…”

Section: Related Workmentioning

confidence: 99%

FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss

Xie¹,

Wang²,

Huang³

et al. 2022

Preprint

View full text Add to dashboard Cite

The existence of completely aligned and paired multi-modal neuroimaging data has proved its effectiveness in the diagnosis of brain diseases. However, collecting the full set of well-aligned and paired data is impractical or even luxurious, since the practical difficulties may include high cost, long time acquisition, image corruption, and privacy issues. Previously, the misaligned unpaired neuroimaging data (termed as MUD) are generally treated as noisy label. However, such a noisy label-based method could not work very well when misaligned data occurs distortions severely, for example, different angles of rotation. In this paper, we propose a novel federated selfsupervised learning (FedMed) for brain image synthesis. An affine transform loss (ATL) was formulated to make use of severely distorted images without violating privacy legislation for the hospital. We then introduce a new data augmentation procedure for self-supervised training and fed it into three auxiliary heads, namely auxiliary rotation, auxiliary translation, and auxiliary scaling heads. The proposed method demonstrates advanced performance in both the quality of synthesized results under a severely misaligned and unpaired data setting, and better stability than other GAN-based algorithms. The proposed method also reduces the demand for deformable registration while encouraging to realize the usage of those misaligned and unpaired data. Experimental results verify the outstanding ability of our learning paradigm compared to other state-of-the-art approaches. Our code is available on the website: https://github.com/FedMed-Meta/FedMed-ATL.

show abstract

“…Although large-scale medical image datasets acquired by actual scanning are challenging to be constructed, medical images of high-quality can be synthesized, alternatively [11]- [12]. Recent studies have demonstrated that, diverse medical image modalities, including MRI images [13]- [19], PET images [20]- [22], CT / X-Ray images [23]- [25], ultrasound images [26], mammography images [27]- [28], eye (including retinal, fundus, and glaucoma) images [29]- [32], endoscopic images [33], can be successfully synthesized. Generally, machine learning techniques are widely acknowledged to provide a profound impact on medical image synthesis, and the synthesis task itself can be considered as finding a good mapping from the source image to the target image [34].…”

Section: A Review Of Recent Developments In Deep Learning-based Medical Image Synthesismentioning

confidence: 99%

Arterial Spin Labeling Image Synthesis From Structural MRI Using Improved Capsule-Based Networks

et al. 2020

View full text Add to dashboard Cite

Medical image synthesis receives much popularity in recent years, and ample medical images can be synthesized by diverse deep learning models to alleviate the problem of lack of data in many medical imaging utilizations. However, most medical image synthesis methods still incorporate the wellknown pooling operation in their convolutional neural networks-based / generative adversarial networksbased models, from which image details will be inevitably lost due to the pooling operation. In order to tackle the above problem, improved capsule-based networks, in which no pooling operation is executed and spatial details of images can be effectively preserved thanks to the equivariance characteristics of capsule models, are proposed in this paper to synthesize arterial spin labeling images, for the first time. Technically, three important issues in constructing improved capsule-based networks, including the depth of basic convolutions, the layer of capsules, and the capacity of capsules, are thoroughly investigated. Comprehensive experiments made up of region-based / voxel-based partial volume corrections and dementia diseases diagnosis based on two different datasets are conducted. The superiority of improved capsule-based networks introduced in this paper is substantiated from the statistical point of view.

show abstract

Synthesize Mammogram from Digital Breast Tomosynthesis with Gradient Guided cGANs

Cited by 13 publications

References 10 publications

Multi‐scale cascaded networks for synthesis of mammogram to decrease intensity distortion and increase model‐based perceptual similarity

Multi‐scale cascaded networks for synthesis of mammogram to decrease intensity distortion and increase model‐based perceptual similarity

FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss

Arterial Spin Labeling Image Synthesis From Structural MRI Using Improved Capsule-Based Networks

Contact Info

Product

Resources

About