Combining graph neural networks and computer vision methods for cell nuclei classification in lung tissue.

The detection of tumoural cells from whole slide images is an essential task in medical diagnosis and research. In this article, we propose and analyse a novel approach that combines computer vision-based models with graph neural networks to improve the accuracy of automated tumoural cell detection in lung tissue. Our proposal leverages the inherent structure and relationships between cells in the tissue.

Glyoxal acid-free (GAF) histological fixative is a suitable alternative to formalin: results from an open-label comparative non-inferiority study.

Formalin, an aqueous solution of formaldehyde, has been the gold standard for fixation of histological samples for over a century. Despite its considerable advantages, growing evidence points to objective toxicity, particularly highlighting its carcinogenicity and mutagenic effects. In 2016, the European Union proposed a ban, but a temporary permission was granted in consideration of its fundamental role in the medical-diagnostic field.

Typical and atypical carcinoid tumors of the lung: a clinicopathological correlation of 783 cases with emphasis on histological features.

We present 783 surgical resections of typical and atypical carcinoid tumors of the lung identified in the pathology files of 20 different pathology departments. All cases were critically reviewed for clinical and pathological features and further correlated with clinical outcomes. Long-term follow-up was obtained in all the patients and statistically analyzed to determine significance of the different parameters evaluated.

Pulmonary Adenofibromas: A Clinicopathologic Correlation of 13 Cases.

Thirteen cases of primary pulmonary adenofibromas are presented. The patients are 8 women and 5 men between the ages of 41 and 73 years (average: 57 y). The patients presented with nonspecific symptomatology or their tumor was identified during routine chest films.