Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge.

The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field.

Breathing Maneuvers as a Vasoactive Stimulus for Detecting Inducible Myocardial Ischemia - An Experimental Cardiovascular Magnetic Resonance Study.

BACKGROUND: Breathing maneuvers can elicit a similar vascular response as vasodilatory agents like adenosine; yet, their potential diagnostic utility in the presence of coronary artery stenosis is unknown. The objective of the study is to investigate if breathing maneuvers can non-invasively detect inducible ischemia in an experimental animal model when the myocardium is imaged with oxygenation-sensitive cardiovascular magnetic resonance (OS-CMR). METHODS AND FINDINGS: In 11 anesthetised swine with experimentally induced significant stenosis (fractional flow reserve <0.75) of the left anterior descending coronary artery (LAD) and 9 control animals, OS-CMR at 3T was performed during two different breathing maneuvers, a long breath-hold; and a combined maneuver of 60s of hyperventilation followed by a long breath-hold. The resulting change of myocardial oxygenation was compared to the invasive measurements of coronary blood flow, blood gases, and oxygen extraction. In control animals, all breathing maneuvers could significantly alter coronary blood flow as hyperventilation decreased coronary blood flow by 34±23%. A long breath-hold alone led to an increase of 97±88%, while the increase was 346±327% (p<0.001), when the long breath-hold was performed after hyperventilation. In stenosis animals, the coronary blood flow response was attenuated after both hyperventilation and the following breath-hold. This was matched by the observed oxygenation response as breath-holds following hyperventilation consistently yielded a significant difference in the signal of the MRI images between the perfusion territory of the stenosis LAD and remote myocardium. There was no difference between the coronary territories during the other breathing maneuvers or in the control group at any point. CONCLUSION: In an experimental animal model, the response to a combined breathing maneuver of hyperventilation with subsequent breath-holding is blunted in myocardium subject to significant coronary artery stenosis. This maneuver may allow for detecting severe coronary artery stenosis and have a significant clinical potential as a non-pharmacological method for diagnostic testing in patients with suspected coronary artery disease.

Hyperoxia Exacerbates Myocardial Ischemia in the Presence of Acute Coronary Artery Stenosis in Swine.

BACKGROUND: Current guidelines limit the use of high oxygen tension after return of spontaneous circulation after cardiac arrest, focusing on neurological outcome and mortality. Little is known about the impact of hyperoxia on the ischemic heart. Oxygen is frequently administered and is generally expected to be beneficial. This study seeks to assess the effects of hyperoxia on myocardia oxygenation in the presence of severe coronary artery stenosis in swine. METHODS AND RESULTS: In 22 healthy pigs, we surgically attached a magnetic resonance compatible flow probe to the left anterior descending coronary artery (LAD). In 11 pigs, a hydraulic occluder was inflated distal to the flow probe. After increasing PaO2 to >300 mm Hg, LAD flow decreased in all animals. In 8 stenosed animals with a mean fractional flow reserve of 0.64±0.02, hyperoxia resulted in a significant decrease of myocardial signal intensity in oxygenation-sensitive cardiovascular magnetic resonance images of the midapical segments of the LAD territory. This was not seen in remote myocardium or in the other 8 healthy animals. The decreased signal intensity was accompanied by a decrease in circumferential strain in the same segments. Furthermore, ejection fraction, cardiac output, and oxygen extraction ratio declined in these animals. Changing PaCO2 levels did not have a significant effect on any of the parameters; however, hypercapnia seemed to nonsignificantly attenuate the hyperoxia-induced changes. CONCLUSIONS: Ventilation-induced hyperoxia may decrease myocardial oxygenation and lead to ischemia in myocardium subject to severe coronary artery stenosis.