RESUMO
Cerebellar infarction, a rare category of stroke, is often misdiagnosed but not given much importance in the available literature. Its presentation overlaps with symptoms of other neurologic, cardiovascular, gastrointestinal, and systemic conditions and therefore is nonspecific. Early diagnosis and management of cerebellar strokes are of utmost importance as the lack of a proper diagnosis may increase overall morbidity and mortality. Lack of awareness of the warning signs and symptoms, non-specificity of symptoms, absence of neurological deficits, and imaging discrepancies are some of the factors contributing to misdiagnosis and delayed treatment. If symptomatology is considered, it is found that symptoms of posterior circulation stroke were more frequently misdiagnosed compared to anterior circulation. Nausea and vomiting increased the chance further. Some other rare presentations include gastrointestinal symptoms, isolated vertigo, and symptoms of inner ear disease. Overdependence on radiological investigations often masks the significance of clinical examination. Ischemic stroke may appear normal in the initial 48 hours in the computed tomography scan of the brain or bony artefacts may hide the lesion. Permanent disabling deficits can follow a cerebellar stroke and the complications, which include hydrocephalus, brain stem compression, and gait abnormalities, necessitate prompt identification and management. In this review article, we aim at analysing various case reports of cerebellar infarction, the most common presentations that were under-evaluated, and their outcomes, thereby highlighting the importance of proper diagnosis and reporting of cerebellar infarction in the future. A thorough knowledge of the association between various clinical presentations of cerebellar stroke and its misdiagnosis helps clinicians to be more vigilant about the disease.
RESUMO
Artificial intelligence (AI) simulates intelligent behavior as well as critical thinking comparable to a human being and can be used to analyze and interpret complex medical data. The application of AI in imaging diagnostics reduces the burden of radiologists and increases the sensitivity of lung cancer screening so that the morbidity and mortality associated with lung cancer can be decreased. In this article, we have tried to evaluate the role of artificial intelligence in lung cancer screening, as well as the future potential and efficiency of AI in the classification of nodules. The relevant studies between 2010-2020 were selected from the PubMed database after excluding animal studies and were analyzed for the contribution of AI. Techniques such as deep learning and machine learning allow automatic characterization and classification of nodules with high precision and promise an advanced lung cancer screening method in the future. Even though several combination models with high performance have been proposed, an effectively validated model for routine use still needs to be improvised. Combining the performance of artificial intelligence with a radiologist's expertise offers a successful outcome with higher accuracy. Thus, we can conclude that higher sensitivity, specificity, and accuracy of lung cancer screening and classification of nodules is possible through the integration of artificial intelligence and radiology. The validation of models and further research is to be carried out to determine the feasibility of this integration.