Deep learning-based diagnosis of lung cancer using a nationwide respiratory cytology image set: improving accuracy and inter-observer variability.

Deep learning (DL)-based image analysis has recently seen widespread application in digital pathology. Recent studies utilizing DL in cytopathology have shown promising results, however, the development of DL models for respiratory specimens is limited. In this study, we designed a DL model to improve lung cancer diagnosis accuracy using cytological images from the respiratory tract.

Association of Bypass Surgery and Mortality in Moyamoya Disease.

Background: Patients with moyamoya disease (MMD) have a high risk of stroke or death. We investigated whether extracranial to intracranial bypass surgery can reduce mortality by preventing strokes in patients with MMD.

Methods And Results: This nationwide retrospective cohort study encompassed patients with MMD registered under the Rare Intractable Diseases program via the Relieved Co-Payment Policy between 2006 and 2019, using the Korean National Health Insurance Service database.

Dynamically switchable magnetic resonance imaging contrast agents.

Contrast agents can improve the sensitivity and resolution of magnetic resonance imaging (MRI) by accelerating the relaxation times of surrounding water protons. The MRI performances of contrast agents are closely related to their structural characteristics, including size, shape, surface modification, and so on. Recently, dynamically switchable MRI contrast agents that can undergo structural changes and imaging functional activations upon reaching the disease microenvironment have been developed for high performance MRI.