by Stephens, Maialen, Estepar, Raúl San José, Ruiz-Cabello, Jesús, Arganda-Carreras, Ignacio, Macía, Iván and López-Linares, Karen
Abstract:
Pulmonary Hypertension (PH) is a cardiovascular disease where the pulmonary arterial pressure and resistance increases, causing functional and morphological changes in structures like the Pulmonary Artery (PA). Magnetic Resonance (MR) is a noninvasive image modality whose importance is raising as it allows a complete functional evaluation of the affected structures, as well as complex blood flow pattern analysis. However, anatomical information is more accurately estimated from Computed Tomography (CT), where structures are better defined. Thus, both image modalities are required for a complete PH evaluation and generating CT images from MR seems to be a good alternative to reduce patient radiation, time and expense for a complete characterization of PH only from MR images. Previous approaches have shown CycleGANs to successfully complete image-to-image translation tasks with different medical image modalities, yet, lung MR-CT translation for PA characterization has barely been exploited using CycleGANs. Hence, in this work we propose generating synthetic CT Angiography (CTA) images from pulmonary MR images training a CycleGAN with unpaired data, to further evaluate the ability of the synthetic CT images to provide structural PA information. We demonstrate to generate synthetic CTA images that correctly resemble real CTA images by automatically segmenting the PA with a 2D CNN trained with real CTA scans. We also prove to preserve PA structural information comparing the ground truth PA annotations of the real CTA images and the predicted PA segmentations of the reconstructed CTA scans.
Reference:
MRI to CTA Translation for Pulmonary Artery Evaluation Using CycleGANs Trained with Unpaired Data (Stephens, Maialen, Estepar, Raúl San José, Ruiz-Cabello, Jesús, Arganda-Carreras, Ignacio, Macía, Iván and López-Linares, Karen), In Thoracic Image Analysis (Petersen, Jens, San José Estépar, Raúl, Schmidt-Richberg, Alexander, Gerard, Sarah, Lassen-Schmidt, Bianca, Jacobs, Colin, Beichel, Reinhard, Mori, Kensaku, eds.), Springer International Publishing, 2020.
Bibtex Entry:
@inproceedings{stephens_mri_2020,
	address = {Cham},
	series = {Lecture {Notes} in {Computer} {Science}},
	title = {{MRI} to {CTA} {Translation} for {Pulmonary} {Artery} {Evaluation} {Using} {CycleGANs} {Trained} with {Unpaired} {Data}},
	isbn = {978-3-030-62469-9},
	doi = {10.1007/978-3-030-62469-9_11},
	abstract = {Pulmonary Hypertension (PH) is a cardiovascular disease where the pulmonary arterial pressure and resistance increases, causing functional and morphological changes in structures like the Pulmonary Artery (PA). Magnetic Resonance (MR) is a noninvasive image modality whose importance is raising as it allows a complete functional evaluation of the affected structures, as well as complex blood flow pattern analysis. However, anatomical information is more accurately estimated from Computed Tomography (CT), where structures are better defined. Thus, both image modalities are required for a complete PH evaluation and generating CT images from MR seems to be a good alternative to reduce patient radiation, time and expense for a complete characterization of PH only from MR images. Previous approaches have shown CycleGANs to successfully complete image-to-image translation tasks with different medical image modalities, yet, lung MR-CT translation for PA characterization has barely been exploited using CycleGANs. Hence, in this work we propose generating synthetic CT Angiography (CTA) images from pulmonary MR images training a CycleGAN with unpaired data, to further evaluate the ability of the synthetic CT images to provide structural PA information. We demonstrate to generate synthetic CTA images that correctly resemble real CTA images by automatically segmenting the PA with a 2D CNN trained with real CTA scans. We also prove to preserve PA structural information comparing the ground truth PA annotations of the real CTA images and the predicted PA segmentations of the reconstructed CTA scans.},
	language = {en},
	booktitle = {Thoracic {Image} {Analysis}},
	publisher = {Springer International Publishing},
	author = {Stephens, Maialen and Estepar, Raúl San José and Ruiz-Cabello, Jesús and Arganda-Carreras, Ignacio and Macía, Iván and López-Linares, Karen},
	editor = {Petersen, Jens and San José Estépar, Raúl and Schmidt-Richberg, Alexander and Gerard, Sarah and Lassen-Schmidt, Bianca and Jacobs, Colin and Beichel, Reinhard and Mori, Kensaku},
	year = {2020},
	keywords = {Convolutional neural network, CT synthesis, CycleGAN, Pulmonary hypertension, Segmentation},
	pages = {118--129}
}