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. Experimental results on our own curated dataset show that modelling the problem with graphs gives the model a clear advantage over just working at pixel level. This change in perspective provides extra information that makes it possible to improve the performance. The reduction of dimensionality that comes from working with the graph also allows us to increase the field of view with low computational requirements. Code is available at https://github.com/Jerry-Master/lung-tumour-study, models are uploaded to https://huggingface.co/Jerry-Master/Hovernet-plus-Graphs, and the dataset is published on Zenodo https://zenodo.org/doi/10.5281/zenodo.8368122.

How to stratify the risk of thrombosis for esthetic plastic surgery? The proposal of a new scale.

Scales to qualify the risk of thrombosis do not include all thrombogenic factors that are generated in esthetic plastic surgery. Methods: We performed a systematic review to assess the risk of thrombosis in plastic surgery. Thrombogenic factors in esthetic surgery were analyzed by a panel of experts. We proposed a scale with 2 versions. In the first version, factors were stratified according to their impact on the possible risk of thrombosis. The second version includes the same factors but in a simplified form. We evaluated the efficacy of the proposed scale by comparing it with the Caprini score; we scored the risk in 124 cases and controls. Results: Using the Caprini score, we found that 81.45% of the patients studied and 62.5% of the cases of thrombosis were observed in the low-risk group. Only 1 case of thrombosis was reported in the high-risk group. Using the stratified version of the scale, we found that the low-risk group comprised 25% of the patients, and there were no cases of thrombosis. The high-risk group included 14.51% of patients; 10 presented thrombosis (62.5%). The proposed scale was very effective in detecting both low-risk and high-risk patients undergoing esthetic surgery procedures.

[Comparison of 2-octyl cyanoacrylate adhesive and suturing for wound closure in the canine small bowel model]. / Adhesivo tisular 2-octil cianoacrilato en el cierre de enterotomía comparado con sutura manual tradicional en dos capas. Modelo en perros.

OBJECTIVE: We undertook this study to evaluate 2-octyl cyanoacrylate (2OCA) glue and suture for wound closure in the small bowel. METHODS: This was a comparative and experimental study. Male and female domestic dogs (n = 10) underwent a 2.0-cm small bowel closure of two wounds. All of these had closure with 2OCA in the first wound. The controls (second wound in the same dog) were closed with suture. Four weeks later the wounds were observed to evaluate the repair. RESULTS: Wound closure time and macrophage count were lower with the 2OCA glue than in the suture group. CONCLUSIONS: 2OCA glue has the strength to seal a small bowel wound. The inflammatory response to the glue is less than that of the suture at 4 weeks. These properties may make it a suitable material for replacing suture in a small bowel wound.

Adhesivo tisular 2-octil cianoacrilato en el cierre de enterotomía comparado con sutura manual tradicional en dos capas: modelo en perros / Comparison of 2-octyl cyanoacrylate adhesive and suturing for wound closure in the canine small bowel model

Objetivo: Saber si el adhesivo tisular 2-octil cianoacrilato da mejores resultados en el cierre de enterotomía en comparación con la sutura manual tradicional en dos capas. Material y métodos: Estudio comparativo experimental en 10 perros. A cada uno se le realizó dos enterotomías: a una se le aplicó adhesivo tisular 2-octil cianoacrilato y a la otra, sutura en dos capas con seda y catgut crómico. Se analizaron ocho variables. Resultados: El tiempo de cierre y el número de macrófagos fueron menores con el adhesivo tisular, encontrando diferencia estadísticamente significativa. En las otras seis variables estudiadas (adherencias, dehiscencia, peritonitis, diámetro luminal del intestino, fibrosis y tipo de inflamación) no hubo diferencias. Conclusiones: En este modelo, el adhesivo tisular 2-octil cianoacrilato fue igual de seguro que la sutura tradicional en dos capas con catgut crómico y seda para cierre de una enterotomía de intestino delgado.

OBJECTIVE: We undertook this study to evaluate 2-octyl cyanoacrylate (2OCA) glue and suture for wound closure in the small bowel. METHODS: This was a comparative and experimental study. Male and female domestic dogs (n = 10) underwent a 2.0-cm small bowel closure of two wounds. All of these had closure with 2OCA in the first wound. The controls (second wound in the same dog) were closed with suture. Four weeks later the wounds were observed to evaluate the repair. RESULTS: Wound closure time and macrophage count were lower with the 2OCA glue than in the suture group. CONCLUSIONS: 2OCA glue has the strength to seal a small bowel wound. The inflammatory response to the glue is less than that of the suture at 4 weeks. These properties may make it a suitable material for replacing suture in a small bowel wound.