Duchenne muscular dystrophy (DMD) is a progressive form of muscular dystrophy caused by mutations in the dystrophin gene. Patients with DMD are more likely to have cerebral infarction than normal populations, possibly due to low ejection fraction and cardiomyopathy, and also higher epilepsy prevalence. Careful history taking and neurological examination are needed for differentiating new symptoms from preexisting weakness in DMD. Here, we present a young male with DMD and acute ischemic stroke followed by recurrent seizures.

BACKGROUND: Cerebral air embolism is uncommon but potentially causes catastrophic events such as cardiac damage or even death. However, due to a low overall incidence, it may go undiagnosed. CASE REPORT: A 56-year-old man with a medical history of right upper lobectomy due to lung cancer showed changes in mental status after the Valsalva maneuver, followed by status epilepticus during admission. Brain and chest computed tomography showed cerebral air embolism and accidental pneumothorax in the right major fissure. After antiepileptic drug infusion and oxygen therapy, he recovered completely. CONCLUSION: Since cerebral air embolism may result in fatal outcomes, it should be suspected in patients with sudden neurological deterioration after routine medical procedures.
Brain ; Embolism, Air ; Fatal Outcome ; Humans ; Incidence ; Lung Neoplasms ; Middle Aged ; Oxygen ; Pneumothorax ; Status Epilepticus ; Thorax ; Valsalva Maneuver

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.