Artificial intelligence solution to classify pulmonary nodules on CT.

PURPOSE: The purpose of this study was to create an algorithm to detect and classify pulmonary nodules in two categories based on their volume greater than 100 mm3 or not, using machine learning and deep learning techniques. MATERIALS AND METHOD: The dataset used to train the model was provided by the organization team of the SFR (French Radiological Society) Data Challenge 2019. An asynchronous and parallel 3-stages pipeline was developed to process all the data (a data "pre-processing" stage; a "nodule detection" stage; a "classifier" stage). Lung segmentation was achieved using 3D U-NET algorithm; nodule detection was done using 3D Retina-UNET and classifier stage with a support vector machine algorithm on selected features. Performances were assessed using area under receiver operating characteristics curve (AUROC). RESULTS: The pipeline showed good performance for pathological nodule detection and patient diagnosis. With the preparation dataset, an AUROC of 0.9058 (95% confidence interval [CI]: 0.8746-0.9362) was obtained, 87% yielding accuracy (95% CI: 84.83%-91.03%) for the "nodule detection" stage, corresponding to 86% specificity (95% CI: 82%-92%) and 89% sensitivity (95% CI: 84.83%-91.03%). CONCLUSION: A fully functional pipeline using 3D U-NET, 3D Retina-UNET and classifier stage with a support vector machine algorithm was developed, resulting in high capabilities for pulmonary nodule classification.

Existence of a rotational axial component in the human humeral medullary canal.

To explain surgical findings, we studied the anatomy of the human humeral medullary canal on a series of 28 bones in 16 patients and 9 dried bones. A methodology is described to find angle of medullary canal on CT scans regarding to an epicondylar reference axis. We found a constant tri-dimensional spiral shape of the medullary canal in the distal part of the bone. The relations between this first description and the literature are discussed.

[The fourth centenary of Montaigne's death. February 28, 1533-- September 13, 1592. Mysteries of procreation]. / Pour le quatrième centenaire de la mort de Montaigne. 28 février 1533--13 septembre 1592. Les mystères de la procréation.

During millennia, the mechanisms of procreation have constituted for man an unfathomable and irritating riddle. In the sixteenth century, mystery remained still untouched upon and Montaigne complained about it. The author assigns a place to his communication within the celebrations held this year to commemorate the fourth centenary of the writer's death. In the seventeenth century, De Graaf will establish the identity of ovarian follicles and Van Leeuwenhoek will discover spermatozoons, prominent strides, but their functions will remain mysterious. In the eighteenth century, Spallanzani will demonstrate the semen's fertility, but without linking the former discoveries. In the nineteenth century only, the mechanisms of fertilization will tell their secret, when the necessity of the union of the two gametes, indispensable condition so that the egg can divide by bipartition and give birth to an embryo which will have the double heredity of origin, will be shown up.