Acetabular posterior column screws via an anterior approach.

Screw fixation of acetabular column fractures is a well-established alternative option to plate fixation providing comparable biomechanical strength and requiring less surgical exposure. For displaced acetabular fractures involving both columns open reduction and plate fixation of one column in combination with a column-crossing screw fixation of the opposite column via a single approach is a viable treatment option. Preoperative planning of posterior column screws (PCS) via an anterior approach is mandatory to assess the eligibility of the fracture for this technique and to plan the entry point and the screw trajectory. The intraoperative application requires fluoroscopic guidance using several views. A single view showing an extraarticular screw position is adequate to rule out hip joint penetration. The fluoroscopic assessment of cortical perforation of the posterior column requires several oblique views such as lateral oblique views, obturator oblique views and axial views of the posterior column or alternatively intraoperative CT scans. The application of PCS via an anterior approach is a technically demanding procedure, that allows for a relevant reduction of approach-related morbidity, surgical time and blood loss by using a single approach.

Neuro-explicit semantic segmentation of the diffusion cloud chamber.

For decades, in diffusion cloud chambers, different types of subatomic particle tracks from radioactive sources or cosmic radiation had to be identified with the naked eye which limited the amount of data that could be processed. In order to allow these classical particle detectors to enter the digital era, we successfully developed a neuro-explicit artificial intelligence model that, given an image from the cloud chamber, automatically annotates most of the particle tracks visible in the image according to the type of particle or process that created it. To achieve this goal, we combined the attention U-Net neural network architecture with methods that model the shape of the detected particle tracks. Our experiments show that the model effectively detects particle tracks and that the neuro-explicit approach decreases the misclassification rate of rare particles by 73% compared with solely using the attention U-Net.