Automated inversion time selection for late gadolinium-enhanced cardiac magnetic resonance imaging.

OBJECTIVES: To develop and share a deep learning method that can accurately identify optimal inversion time (TI) from multi-vendor, multi-institutional and multi-field strength inversion scout (TI scout) sequences for late gadolinium enhancement cardiac MRI. MATERIALS AND METHODS: Retrospective multicentre study conducted on 1136 1.5-T and 3-T cardiac MRI examinations from four centres and three scanner vendors. Deep learning models, comprising a convolutional neural network (CNN) that provides input to a long short-term memory (LSTM) network, were trained on TI scout pixel data from centres 1 to 3 to identify optimal TI, using ground truth annotations by two readers. Accuracy within 50 ms, mean absolute error (MAE), Lin's concordance coefficient (LCCC) and reduced major axis regression (RMAR) were used to select the best model from validation results, and applied to holdout test data. Robustness of the best-performing model was also tested on imaging data from centre 4. RESULTS: The best model (SE-ResNet18-LSTM) produced accuracy of 96.1%, MAE 22.9 ms and LCCC 0.47 compared to ground truth on the holdout test set and accuracy of 97.3%, MAE 15.2 ms and LCCC 0.64 when tested on unseen external (centre 4) data. Differences in vendor performance were observed, with greatest accuracy for the most commonly represented vendor in the training data. CONCLUSION: A deep learning model was developed that can identify optimal inversion time from TI scout images on multi-vendor data with high accuracy, including on previously unseen external data. We make this model available to the scientific community for further assessment or development. CLINICAL RELEVANCE STATEMENT: A robust automated inversion time selection tool for late gadolinium-enhanced imaging allows for reproducible and efficient cross-vendor inversion time selection. KEY POINTS: • A model comprising convolutional and recurrent neural networks was developed to extract optimal TI from TI scout images. • Model accuracy within 50 ms of ground truth on multi-vendor holdout and external data of 96.1% and 97.3% respectively was achieved. • This model could improve workflow efficiency and standardise optimal TI selection for consistent LGE imaging.

An atypical distribution of acute calcific periarthritis in the setting of trauma.

Case report of an atypical location of ACP. ACP should be considered even in small joints with characteristic imaging even with trauma involvement.

The Protective Effect of Zinc Against Liver Ischaemia Reperfusion Injury in a Rat Model of Global Ischaemia.

BACKGROUND: Ischaemia-reperfusion injury (IRI) is a major obstacle during liver transplantation and resection surgeries for cancer, with a need for effective and safe drugs to reduce IRI. Zinc preconditioning has been shown to protect against liver IRI in a partial (70%) ischaemia model. However, its efficacy against a clinically relevant Pringle manoeuvre that results in global liver ischaemia (100%) is unknown. AIMS: The aim of this study was to test the efficacy of zinc preconditioning in a rat model of global liver ischaemia. METHODS: Rats were preconditioned via subcutaneous injection of 10 mg/kg of ZnCl2, 24 h and 4 h before ischaemia. Total liver ischaemia (100%) was induced by placing a clamp across the portal triad for 30 min. Liver injury was assessed by serum alanine transaminase (ALT) and aspartate transaminase (AST) levels in blood taken before ischaemia (baseline) and at 1, 2, 4, 24, 48, 72, 96 and 120 hours after ischaemia. Animals were culled after 7 days, and the harvested livers were histologically analysed. RESULTS: On a two-way repeated-measures analysis of variance, there was a statistically significant (p = 0.025) difference in the mean ALT levels between saline- and ZnCl2-treated groups. Specifically at 24 h after ischaemia, the ALT (341 ± 99 U/L) and AST (606 ± 78 U/L) in the zinc-treated group were significantly less than the ALT (2863 ± 828 U/L) and AST (3591 ± 948 U/L) values in the saline-treated group. Zinc significantly reduced neutrophil infiltration and necrosis compared with the saline control. CONCLUSION: Zinc preconditioning reduces the overall hepatocellular damage from IRI. These results lay the foundation to assess the benefit of zinc preconditioning for clinical applications.

Arrhythmia insensitive rapid cardiac T1 mapping: comparison to modified look locker inversion recovery T1 mapping in mitral valve prolapse patients.

We compare a saturation recovery arrhythmia insensitive rapid (AIR) T1 mapping technique which is less sensitive to heart rate and requires shorter breath-holds to modified Look-Locker inversion recovery (MOLLI) T1 mapping in patients with mitral valve prolapse. 55 patients underwent AIR and MOLLI at 1.5 T. AIR and MOLLI-derived blood and myocardial T1 values and extracellular volume (ECV) were measured by two independent readers. T1 values and ECV from both techniques and inter-reader agreement were compared with Lin's concordance correlation coefficient (LCC) and reduced major axis regression. T1 values were consistently overestimated for AIR compared to MOLLI and vice versa for ECV. In the mitral valve prolapse population, mean native and post contrast myocardial T1 value for MOLLI were 1000 ± 40 ms and 411.9 ± 44.2 ms respectively and 1090.6 ± 58.7 ms and 488.2 ± 45.7 ms for AIR. Mean native and post contrast blood T1 values for MOLLI were 1566.6 ± 72.3 ms and 276.6 ± 34.1 ms respectively versus 1657.2 ± 180.9 ms and 294.9 ± 35.6 ms for AIR. AIR underestimated ECV relative to MOLLI (23.5 ± 0.4% vs 27.7 ± 0.4%). We found excellent inter-reader agreement (LCC all > 0.94, p < 0.0001) for both AIR and MOLLI techniques as well as intra-reader reliability (LCC all > 0.97, p < 0.0001). AIR can be performed in patients with mitral valve prolapse with excellent inter and intra-reader agreement, with higher T1 values compared to MOLLI, in line with other saturation recovery techniques. A consistent T1 mapping technique should be used when performing serial imaging.

Atypical Small Acinar Proliferation and High-grade Prostatic Intraepithelial Neoplasia in the Era of Multiparametric Magnetic Resonance Imaging: A Contemporary Review.

Multiparametric magnetic resonance imaging (mpMRI) has added to the armamentarium for the diagnosis and surveillance for organ-confined prostate cancer. Atypical small acinar proliferation and high-grade prostatic intraepithelial neoplasia (HGPIN) are premalignant prostatic lesions. The management of such lesions remains contentious, and the addition of mpMRI introduces further uncertainty, given its ability to pick up indolent lesions and its use in targeted biopsy. We aimed to perform a comprehensive review of current evidence regarding atypical small acinar proliferation, high-grade prostatic intraepithelial neoplasia, and mpMRI to ascertain a consensus for a current management algorithm.