Search

Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstruction, and focuses on various DL approaches and architectures designed to improve image quality, accelerate scans, and address data-related challenges. It explores end-to-end neural networks, pre-trained and generative models, and self-supervised methods, and highlights their contributions to overcoming traditional MRI limitations. It also discusses the role of DL in optimizing acquisition protocols, enhancing robustness against distribution shifts, and tackling biases. Drawing on the extensive literature and practical insights, it outlines current successes, limitations, and future directions for leveraging DL in MRI reconstruction, while emphasizing the potential of DL to significantly impact clinical imaging practices. [ABSTRACT FROM AUTHOR]

Side experiments are performed on radiomics models to improve their reproducibility. We measure the impact of myocardial masks, radiomic side experiments and data augmentation for information transfer (DAFIT) approach to differentiate patients with and without pulmonary hypertension (PH) using cardiac MRI (CMRI) derived radiomics. Feature extraction was performed from the left ventricle (LV) and right ventricle (RV) myocardial masks using CMRI in 82 patients (42 PH and 40 controls). Various side study experiments were evaluated: Original data without and with intraclass correlation (ICC) feature-filtering and DAFIT approach (without and with ICC feature-filtering). Multiple machine learning and feature selection strategies were evaluated. Primary analysis included all PH patients with subgroup analysis including PH patients with preserved LVEF (≥ 50%). For both primary and subgroup analysis, DAFIT approach without feature-filtering was the highest performer (AUC 0.957–0.958). ICC approaches showed poor performance compared to DAFIT approach. The performance of combined LV and RV masks was superior to individual masks alone. There was variation in top performing models across all approaches (AUC 0.862–0.958). DAFIT approach with features from combined LV and RV masks provide superior performance with poor performance of feature filtering approaches. Model performance varies based upon the feature selection and model combination. [ABSTRACT FROM AUTHOR]

Clustering is a challenging problem in unsupervised learning. In lieu of a gold standard, stability has become a valuable surrogate to performance and robustness. In this work, we propose a non-parametric bootstrapping approach to estimating the stability of a clustering method, which also captures stability of the individual clusters and observations. This flexible framework enables different types of comparisons between clusterings and can be used in connection with two possible bootstrap approaches for stability. The first approach, scheme 1, can be used to assess confidence (stability) around clustering from the original dataset based on bootstrap replications. A second approach, scheme 2, searches over the bootstrap clusterings for an optimally stable partitioning of the data. The two schemes accommodate different model assumptions that can be motivated by an investigator's trust (or lack thereof) in the original data and additional computational considerations. We propose a hierarchical visualization extrapolated from the stability profiles that give insights into the separation of groups, and projected visualizations for the inspection of the stability of individual operations. Our approaches show good performance in simulation and on real data. These approaches can be implemented using the R package bootcluster that is available on the Comprehensive R Archive Network (CRAN). [ABSTRACT FROM AUTHOR]

Purpose: Telehealth allows patients to maintain contact with healthcare providers without necessitating travel, and is becoming increasingly utilized. The purpose of this study is to describe the components of telehealth palliative care interventions for patients with advanced cancer before the COVID-19 pandemic; identify any intervention components associated with improvements in outcomes; and evaluate reporting of interventions. Methods: This scoping review was registered on the Open Science Framework. We searched 5 medical databases from inception to June 19, 2020. Inclusion criteria were: age ≥ 18, advanced cancer, asynchronous or synchronous telehealth intervention, and specialized palliative care interventions in any setting. We assessed the quality of intervention reporting using the Template for Intervention Description and Replication (TIDieR) checklist. Results: Twenty-three studies met the inclusion criteria: 15 (65%) quantitative (7 randomized controlled trials, 5 feasibility trials, 3 retrospective chart reviews); 4 (17%) mixed methods, and 4 (17%) qualitative. Most quantitative and mixed methods studies were conducted in North America (12/19, 63%), reported on hybrid (in-person and telehealth) interventions (9/19, 47%), and were delivered by nurses (12/19, 63%) in the home setting (14/19, 74%). In most studies that reported improvements in patient- or caregiver-reported outcomes, the content was psychoeducational and resulted in improvements for psychological symptoms. No study provided complete reporting on all 12 TIDieR checklist items. Conclusion: Telehealth studies are needed that reflect palliative care's mission to provide multidisciplinary team-based care that improves quality of life in diverse settings, and that provide detailed reporting of interventions. [ABSTRACT FROM AUTHOR]