AI-Enhanced Detection of Clinically Relevant Structural and Functional Anomalies in MRI: Traversing the Landscape of Conventional to Explainable Approaches.

Anomaly detection in medical imaging, particularly within the realm of magnetic resonance imaging (MRI), stands as a vital area of research with far-reaching implications across various medical fields. This review meticulously examines the integration of artificial intelligence (AI) in anomaly detection for MR images, spotlighting its transformative impact on medical diagnostics. We delve into the forefront of AI applications in MRI, exploring advanced machine learning (ML) and deep learning (DL) methodologies that are pivotal in enhancing the precision of diagnostic processes. The review provides a detailed analysis of preprocessing, feature extraction, classification, and segmentation techniques, alongside a comprehensive evaluation of commonly used metrics. Further, this paper explores the latest developments in ensemble methods and explainable AI, offering insights into future directions and potential breakthroughs. This review synthesizes current insights, offering a valuable guide for researchers, clinicians, and medical imaging experts. It highlights AI's crucial role in improving the precision and speed of detecting key structural and functional irregularities in MRI. Our exploration of innovative techniques and trends furthers MRI technology development, aiming to refine diagnostics, tailor treatments, and elevate patient care outcomes. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 1.

Reconstructing the cell-cell interaction network among mouse immune cells.

Intercellular interactions and cell-cell communication are critical to regulating cell functions, especially in normal immune cells and immunotherapies. Ligand-receptor pairs mediating these cell-cell interactions can be identified using diverse experimental and computational approaches. Here, we reconstructed the intercellular interaction network between Mus musculus immune cells using publicly available receptor-ligand interaction databases and gene expression data from the immunological genome project. This reconstructed network accounts for 50,317 unique interactions between 16 cell types between 731 receptor-ligand pairs. Analysis of this network shows that cells of hematopoietic lineages use fewer communication pathways for interacting with each other, while nonhematopoietic stromal cells use the most network communications. We further observe that the WNT, BMP, and LAMININ pathways are the most significant contributors to the overall number of cell-cell interactions among the various pathways in the reconstructed communication network. This resource will enable the systematic analysis of normal and pathologic immune cell interactions, along with the study of emerging immunotherapies.

Efficacy and safety of miglustat in the treatment of GM2 gangliosidosis: A systematic review.

BACKGROUND: Since the results of previous studies regarding the safety and efficacy of miglustat in GM2 gangliosidosis (GM2g) were inconsistent, we aimed to assess miglustat therapy in GM2g patients. METHODS: This study followed the latest version of PRISMA. We included the observational or interventional studies reporting GM2g patients under miglustat therapy by searching PubMed, Web of Science, and Scopus. Data extracted included the natural history of individual patient data, as well as the safety and efficacy of miglustat in GM2g patients. The quality assessment was performed using the Joanna Briggs Institute Critical Appraisal checklist. RESULTS: A total of 1023 records were identified and reduced to 621 after removing duplicates. After screening and applying the eligibility criteria, 10 articles and 2 abstracts met the inclusion criteria. Overall, the studies represented 54 patients with GM2g under treatment with miglustat and 22 patients with GM2g in the control group. Among patients with available data, 14 and 54 have been diagnosed with Sandhoff disease and Tay-Sachs disease, respectively. Patients included in this review consisted of 23 infantile, 4 late-infantile, 18 juvenile, and 31 adult-onset GM2g. CONCLUSIONS: Although miglustat should not be considered a definite treatment for GM2g, it appears that patients, particularly those with infantile or late-infantile GM2g, could benefit from miglustat therapy to some extent. We also make some suggestions regarding future studies presenting their findings in a standard format to facilitate pooling the available data in such rare diseases for a more comprehensive conclusion.