High-quality segmentation of low quality cardiac MR images using k-space artefact correction

Ilkay Oksuz, James Clough, Wenjia Bai, Bram Ruijsink, Esther Puyol-Antón, Gastao Cruz, Claudia Prieto, Andrew P. King, Julia A. Schnabel
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:380-389, 2019.

Abstract

Deep learning methods have shown great success in segmenting the anatomical and pathological structures in medical images. This success is closely bounded with the quality of the images in the dataset that are being segmented. A commonly overlooked issue in the medical image analysis community is the vast amount of clinical images that have severe image artefacts. In this paper, we discuss the implications of image artefacts on cardiac MR segmentation and compare a variety of approaches for motion artefact correction with our proposed method Automap-GAN. Our method is based on the recently developed Automap reconstruction method, which directly reconstructs high quality MR images from k-space using deep learning. We propose to use a loss function that combines mean square error with structural similarity index to robustly segment poor-quality images. We train the reconstruction network to automatically correct for motion-related artefacts using synthetically corrupted CMR k-space data and uncorrected reconstructed images. In the experiments, we apply the proposed method to correct for motion artefacts on a large dataset of 1,400 subjects to improve image quality. The improvement of image quality is quantitatively assessed using segmentation accuracy as a metric. The segmentation is improved from 0.63 to 0.72 dice overlap after artefact correction. We quantitatively compare our method with a variety of techniques for recovering image quality to showcase the influence on segmentation. In addition, we qualitatively evaluate the proposed technique using k-space data containing real motion artefacts.

Cite this Paper


BibTeX
@InProceedings{pmlr-v102-oksuz19a, title = {High-quality segmentation of low quality cardiac MR images using k-space artefact correction}, author = {Oksuz, Ilkay and Clough, James and Bai, Wenjia and Ruijsink, Bram and Puyol-Ant{\'o}n, Esther and Cruz, Gastao and Prieto, Claudia and King, Andrew P. and Schnabel, Julia A.}, booktitle = {Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning}, pages = {380--389}, year = {2019}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, volume = {102}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v102/oksuz19a/oksuz19a.pdf}, url = { http://proceedings.mlr.press/v102/oksuz19a.html }, abstract = {Deep learning methods have shown great success in segmenting the anatomical and pathological structures in medical images. This success is closely bounded with the quality of the images in the dataset that are being segmented. A commonly overlooked issue in the medical image analysis community is the vast amount of clinical images that have severe image artefacts. In this paper, we discuss the implications of image artefacts on cardiac MR segmentation and compare a variety of approaches for motion artefact correction with our proposed method Automap-GAN. Our method is based on the recently developed Automap reconstruction method, which directly reconstructs high quality MR images from k-space using deep learning. We propose to use a loss function that combines mean square error with structural similarity index to robustly segment poor-quality images. We train the reconstruction network to automatically correct for motion-related artefacts using synthetically corrupted CMR k-space data and uncorrected reconstructed images. In the experiments, we apply the proposed method to correct for motion artefacts on a large dataset of 1,400 subjects to improve image quality. The improvement of image quality is quantitatively assessed using segmentation accuracy as a metric. The segmentation is improved from 0.63 to 0.72 dice overlap after artefact correction. We quantitatively compare our method with a variety of techniques for recovering image quality to showcase the influence on segmentation. In addition, we qualitatively evaluate the proposed technique using k-space data containing real motion artefacts.} }
Endnote
%0 Conference Paper %T High-quality segmentation of low quality cardiac MR images using k-space artefact correction %A Ilkay Oksuz %A James Clough %A Wenjia Bai %A Bram Ruijsink %A Esther Puyol-Antón %A Gastao Cruz %A Claudia Prieto %A Andrew P. King %A Julia A. Schnabel %B Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2019 %E M. Jorge Cardoso %E Aasa Feragen %E Ben Glocker %E Ender Konukoglu %E Ipek Oguz %E Gozde Unal %E Tom Vercauteren %F pmlr-v102-oksuz19a %I PMLR %P 380--389 %U http://proceedings.mlr.press/v102/oksuz19a.html %V 102 %X Deep learning methods have shown great success in segmenting the anatomical and pathological structures in medical images. This success is closely bounded with the quality of the images in the dataset that are being segmented. A commonly overlooked issue in the medical image analysis community is the vast amount of clinical images that have severe image artefacts. In this paper, we discuss the implications of image artefacts on cardiac MR segmentation and compare a variety of approaches for motion artefact correction with our proposed method Automap-GAN. Our method is based on the recently developed Automap reconstruction method, which directly reconstructs high quality MR images from k-space using deep learning. We propose to use a loss function that combines mean square error with structural similarity index to robustly segment poor-quality images. We train the reconstruction network to automatically correct for motion-related artefacts using synthetically corrupted CMR k-space data and uncorrected reconstructed images. In the experiments, we apply the proposed method to correct for motion artefacts on a large dataset of 1,400 subjects to improve image quality. The improvement of image quality is quantitatively assessed using segmentation accuracy as a metric. The segmentation is improved from 0.63 to 0.72 dice overlap after artefact correction. We quantitatively compare our method with a variety of techniques for recovering image quality to showcase the influence on segmentation. In addition, we qualitatively evaluate the proposed technique using k-space data containing real motion artefacts.
APA
Oksuz, I., Clough, J., Bai, W., Ruijsink, B., Puyol-Antón, E., Cruz, G., Prieto, C., King, A.P. & Schnabel, J.A.. (2019). High-quality segmentation of low quality cardiac MR images using k-space artefact correction. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 102:380-389 Available from http://proceedings.mlr.press/v102/oksuz19a.html .

Related Material