4D Semantic Cardiac Magnetic Resonance Image Synthesis on XCAT Anatomical Model

Abbasi-Sureshjani, Samaneh; Amirrajab, Sina; Lorenz, Cristian; Weese, Juergen; Pluim, Josien P. W.; Breeuwer, Marcel

doi:10.48550/arxiv.2002.07089

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combining the controllable anatomical model with the imaging features has gained more attention in recent years. Abbasi-Sureshjani et al in [26] and Amirrajab et al in [25] propose to integrate the anatomical information of the XCAT phantoms [5] with modality-specific appearance of real data to synthesize data for creating a virtual database of realistic CMR images with ground truth labels. Although the anatomical variability can be created using the heart model, new image appearances can not be generated.…”

Section: Hybrid Image Generationmentioning

confidence: 99%

A Framework for Simulating Cardiac MR Images With Varying Anatomy and Contrast

Amirrajab

Khalil

Lorenz

et al. 2023

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

One of the limiting factors for the development and adoption of novel deep-learning (DL) based medical image analysis methods is the scarcity of labeled medical images. Medical image simulation and synthesis can provide solutions by generating ample training data with corresponding ground truth labels. Despite recent advances, generated images demonstrate limited realism and diversity. In this work, we develop a flexible framework for simulating cardiac magnetic resonance (MR) images with variable anatomical and imaging characteristics for the purpose of creating a diversified virtual population.We advance previous works on both cardiac MR image simulation and anatomical modeling to increase the realism in terms of both image appearance and underlying anatomy. To diversify the generated images, we define parameters: 1) to alter the anatomy, 2) to assign MR tissue properties to various tissue types, and 3) to manipulate the image contrast via acquisition parameters. The proposed framework is optimized to generate a substantial number of cardiac MR images with ground truth labels suitable for downstream supervised tasks. A database of virtual subjects is simulated and its usefulness for aiding a DL segmentation method is evaluated. Our experiments show that training completely with simulated images can perform comparable with a model trained with real images for heart cavity segmentation in mid-ventricular slices. Moreover, such data can be used in addition to classical augmentation for boosting the performance when training data is limited, particularly by increasing the contrast and anatomical variation, leading to better regularization and generalization. The database is publicly available at https://osf.io/ bkzhm/ and the simulation code will be available at https: //github.com/sinaamirrajab/CMRI_Simulation .

show abstract

Section: Hybrid Image Generationmentioning

confidence: 99%

A Framework for Simulating Cardiac MR Images With Varying Anatomy and Contrast

Amirrajab

Khalil

Lorenz

et al. 2023

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…Most of the recent results and approaches adopt DL models to perform domain translation, with GANs being widely used since they can generate high quality samples, with a high level of realism [10], across several medical imaging modalities such as MRI [11] - [12], CT [13], and Ultrasound, namely echocardiography [14] - [15], with a fast sampling time. In a GAN, the generator tries to synthesize a sample that matches the target domain, which has an inherent data distribution function.…”

Section: A State Of the Artmentioning

confidence: 99%

A Domain Translation Framework With an Adversarial Denoising Diffusion Model to Generate Synthetic Datasets of Echocardiography Images

et al. 2023

View full text Add to dashboard Cite

Currently, medical image domain translation operations show a high demand from researchers and clinicians. Amongst other capabilities, this task allows the generation of new medical images with sufficiently high image quality, making them clinically relevant. Deep Learning (DL) architectures, most specifically deep generative models, are widely used to generate and translate images from one domain to another. The proposed framework relies on an adversarial Denoising Diffusion Model (DDM) to synthesize echocardiography images and perform domain translation. Contrary to Generative Adversarial Networks (GANs), DDMs are able to generate high quality image samples with a large diversity. If a DDM is combined with a GAN, this ability to generate new data is completed at an even faster sampling time. In this work we trained an adversarial DDM combined with a GAN to learn the reverse denoising process, relying on a guide image, making sure relevant anatomical structures of each echocardiography image were kept and represented on the generated image samples. For several domain translation operations, the results verified that such generative model was able to synthesize high quality image samples: MSE: 11.50 ± 3.69, PSNR (dB): 30.48 ± 0.09, SSIM: 0.47 ± 0.03. The proposed method showed high generalization ability, introducing a framework to create echocardiography images suitable to be used for clinical research purposes.

show abstract

“…They concluded that common GAN training problems such as mode collapse occur. Abbasi-Sureshjani et al [24] developed a method to generate 3D labeled Cardiac MR images relying on CT anatomical models to obtain labels for the synthesized images, using a SPADE GAN [25]. More recently, Cirillo et al [26] adapted the original Pix2pix model to generate 3D brain tumor segmentations.…”

Section: A State Of the Artmentioning

confidence: 99%

A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images Using a GAN

et al. 2022

View full text Add to dashboard Cite

Due to privacy issues and limited amount of publicly available labeled datasets in the domain of medical imaging, we propose an image generation pipeline to synthesize 3D echocardiographic images with corresponding ground truth labels, to alleviate the need for data collection and for laborious and errorprone human labeling of images for subsequent Deep Learning (DL) tasks. The proposed method utilizes detailed anatomical segmentations of the heart as ground truth label sources. This initial dataset is combined with a second dataset made up of real 3D echocardiographic images to train a Generative Adversarial Network (GAN) to synthesize realistic 3D cardiovascular ultrasound images paired with ground truth labels. To generate the synthetic 3D dataset, the trained GAN uses high resolution anatomical models from Computed Tomography (CT) as input. A qualitative analysis of the synthesized images showed that the main structures of the heart are well delineated and closely follow the labels obtained from the anatomical models. To assess the usability of these synthetic images for DL tasks, segmentation algorithms were trained to delineate the left ventricle, left atrium, and myocardium. A quantitative analysis of the 3D segmentations given by the models trained with the synthetic images indicated the potential use of this GAN approach to generate 3D synthetic data, use the data to train DL models for different clinical tasks, and therefore tackle the problem of scarcity of 3D labeled echocardiography datasets.

show abstract

4D Semantic Cardiac Magnetic Resonance Image Synthesis on XCAT Anatomical Model

Cited by 5 publications

References 0 publications

A Framework for Simulating Cardiac MR Images With Varying Anatomy and Contrast

A Framework for Simulating Cardiac MR Images With Varying Anatomy and Contrast

A Domain Translation Framework With an Adversarial Denoising Diffusion Model to Generate Synthetic Datasets of Echocardiography Images

A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images Using a GAN

Contact Info

Product

Resources

About