Accelerating Cardiac Diffusion Tensor Imaging With a U-Net Based Model: Toward Single Breath-Hold.

BACKGROUND: In vivo cardiac diffusion tensor imaging (cDTI) characterizes myocardial microstructure. Despite its potential clinical impact, considerable technical challenges exist due to the inherent low signal-to-noise ratio. PURPOSE: To reduce scan time toward one breath-hold by reconstructing diffusion tensors for in vivo cDTI with a fitting-free deep learning approach. STUDY TYPE: Retrospective. POPULATION: A total of 197 healthy controls, 547 cardiac patients. FIELD STRENGTH/SEQUENCE: A 3 T, diffusion-weighted stimulated echo acquisition mode single-shot echo-planar imaging sequence. ASSESSMENT: A U-Net was trained to reconstruct the diffusion tensor elements of the reference results from reduced datasets that could be acquired in 5, 3 or 1 breath-hold(s) (BH) per slice. Fractional anisotropy (FA), mean diffusivity (MD), helix angle (HA), and sheetlet angle (E2A) were calculated and compared to the same measures when using a conventional linear-least-square (LLS) tensor fit with the same reduced datasets. A conventional LLS tensor fit with all available data (12 ± 2.0 [mean ± sd] breath-holds) was used as the reference baseline. STATISTICAL TESTS: Wilcoxon signed rank/rank sum and Kruskal-Wallis tests. Statistical significance threshold was set at P = 0.05. Intersubject measures are quoted as median [interquartile range]. RESULTS: For global mean or median results, both the LLS and U-Net methods with reduced datasets present a bias for some of the results. For both LLS and U-Net, there is a small but significant difference from the reference results except for LLS: MD 5BH (P = 0.38) and MD 3BH (P = 0.09). When considering direct pixel-wise errors the U-Net model outperformed significantly the LLS tensor fit for reduced datasets that can be acquired in three or just one breath-hold for all parameters. DATA CONCLUSION: Diffusion tensor prediction with a trained U-Net is a promising approach to minimize the number of breath-holds needed in clinical cDTI studies. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 1.

Intra-Aortic Balloon Pump Counterpulsation in the Post-Resuscitation Period is Associated with Improved Functional Outcomes in Patients Surviving an Out-of-Hospital Cardiac Arrest: Insights from a Dedicated Heart Attack Centre.

BACKGROUND: Despite advances in cardiopulmonary resuscitation, functional survival remains low after out-of-hospital cardiac arrest (OOHCA). Intra-aortic balloon pump (IABP) therapy has recently been shown to augment cerebral blood flow. Whether IABP therapy in the post-resuscitation period improves functional outcomes is unknown. METHODS: We analysed 174 consecutive patients who were successfully resuscitated from an OOHCA between 2011-2013 at Harefield Hospital, London. We analysed functional status at discharge and mortality up to one year. RESULTS: A total of 55 patients (32.1%) received IABP therapy. Comparing those receiving IABP with those not receiving IABP, there was no difference in favourable functional status at discharge (49.1% vs. 57.1%, p=0.321); and mortality at one year (45.5% vs. 35.5%, p=0.164). Multivariable analyses identified IABP therapy as a strong independent predictor for favourable functional status at discharge (OR=7.51, 95% CI: 2.15-26.14, p=0.002) and this association was maintained in propensity-score adjusted analyses (OR=9.90, 95% CI: 2.11-46.33, p=0.004) and inverse probability treatment weighted analyses (OR=10.84, 95% CI: 2.75-42.69, p<0.001). However, IABP therapy was not an independent predictor for mortality at one year (HR=0.93, 95% CI: 0.52-1.65, p=0.810) and this was confirmed in both propensity-score adjusted and inverse probability treatment weighted analyses. CONCLUSIONS: In this observational analysis of patients surviving an OOHCA, the use of IABP therapy in the post-resuscitation period was associated with improved functional outcomes. This warrants further evaluation in larger prospective studies.

Deep learning-based diffusion tensor cardiac magnetic resonance reconstruction: a comparison study.

In vivo cardiac diffusion tensor imaging (cDTI) is a promising Magnetic Resonance Imaging (MRI) technique for evaluating the microstructure of myocardial tissue in living hearts, providing insights into cardiac function and enabling the development of innovative therapeutic strategies. However, the integration of cDTI into routine clinical practice poses challenging due to the technical obstacles involved in the acquisition, such as low signal-to-noise ratio and prolonged scanning times. In this study, we investigated and implemented three different types of deep learning-based MRI reconstruction models for cDTI reconstruction. We evaluated the performance of these models based on the reconstruction quality assessment, the diffusion tensor parameter assessment as well as the computational cost assessment. Our results indicate that the models discussed in this study can be applied for clinical use at an acceleration factor (AF) of × 2 and × 4 , with the D5C5 model showing superior fidelity for reconstruction and the SwinMR model providing higher perceptual scores. There is no statistical difference from the reference for all diffusion tensor parameters at AF × 2 or most DT parameters at AF × 4 , and the quality of most diffusion tensor parameter maps is visually acceptable. SwinMR is recommended as the optimal approach for reconstruction at AF × 2 and AF × 4 . However, we believe that the models discussed in this study are not yet ready for clinical use at a higher AF. At AF × 8 , the performance of all models discussed remains limited, with only half of the diffusion tensor parameters being recovered to a level with no statistical difference from the reference. Some diffusion tensor parameter maps even provide wrong and misleading information.

A rare complication following radiofrequency ablation.

Atrial-oesophageal fistula (AOF) formation is a rare but often fatal complication post radio frequency ablation (RFA). Mortality ranges from 67% to 100%, with a rapid progression from symptom onset to death. We report a case of a healthy man in his early 40s who presented with a Glasgow Coma Scale  of 5/15, clinical evidence of sepsis and Streptococcus viridans bacteraemia, 14 days following uncomplicated RFA for atrial fibrillation. Establishing a diagnosis of AOF can be difficult, as patients may have bacteraemia, but are consequently misdiagnosed with infective endocarditis, as in this case. One should have a high-index of suspicion for AOF in patients presenting with the aforementioned constellation of symptoms following ablation. There are no established predictors of mortality, but prompt detection, emergent operative intervention and prolonged antibiotic therapy are vital for survival.

Sternal fractures and their management.

Sternal fractures are predominantly associated with deceleration injuries and blunt anterior chest trauma. Sternal trauma must be carefully evaluated by monitoring of vital parameters and it is of paramount importance that concomitant injuries are excluded. Nevertheless, routine admission of patients with isolated sternal fractures for observation is still common in today's practice, which is often unnecessary. This article aims to describe the prognosis, the recommended assessment and management of patients with sternal fractures, to help clinicians make an evidence-based judgment regarding the need for hospitalization.

Vena caval anomalies.

Anomalous vena cavae can have significant implications for procedures on the right side of the heart. We report a rare anatomical configuration in a 44-year-old female, which to the best of our knowledge, is the first report of such an association. She had a bicuspid aortic valve in conjunction with a persistent left superior vena cava (PLSVC) draining into the coronary sinus, and a left-sided inferior vena cava (IVC) draining into a left superior vena cava via the hemiazygos vein. Comprehensive assessment of these anomalies is crucial given the widespread use of invasive cardiac procedures.