Creating Digital Rescue Sheets.

Rescue sheets enable rescue personnel to timely extricate trapped victims of road traffic accidents and increase their chance of survival. However, in the year 2024, these rescue sheets are still paper based DIN A4 documents. The digital transformation of the rescue process through new reporting technologies, such as eCall or the International Standard Accident Number (ISAN) facilitates digital rescue sheets, providing benefits for availability and functionality. This work addresses design considerations raised by previous research to suggest a process for the creation of digital rescue sheets. Our process transforms high-resolution models provided by car manufacturers and vendors into small files by shape abstraction of the components. The system maps the body of the car to generic representative models of defined car body types reducing the number of models that need to be stored. We develop a hierarchical tree data structure with three levels that allows appending new components of the increasingly complex cars. Our data format for transmission of the rescue sheet sends all relevant data for visualization while still retaining a small file size to account for a poor internet connection. In the future, we aim to evaluate our approach involving car manufacturers and other stakeholders.

Task design for crowdsourced glioma cell annotation in microscopy images.

Crowdsourcing has been used in computational pathology to generate cell and cell nuclei annotations for machine learning. Herein, we broaden its scope to the previously unsolved challenging task of glioma cell detection. This requires multiplexed immunofluorescence microscopy due to diffuse invasiveness and exceptional similarity between glioma cells and reactive astrocytes. In four pilot experiments, we iteratively developed a task design enabling high-quality annotations by crowdworkers on Amazon Mechanical Turk. We applied majority or weighted vote and validated them against ground truth in the final setting. On the base of a YOLO convolutional neural network architecture, we used these consensus labels for training with different image representations regarding colors, intensities, and immmunohistochemical marker combinations. A crowd of 712 workers defined aggregated point annotations in 235 images with an average [Formula: see text] score of 0.627 for majority vote. The networks resulted in acceptable [Formula: see text] scores up to 0.69 for YOLOv8 on average and indicated first evidence for transferability to images lacking tumor markers, especially in IDH-wildtype glioblastoma. Our work confirms feasibility of crowdsourcing to generate labels suitable for training of machine learning tools in the challenging and clinically relevant use case of glioma microenvironment.

Towards Prediction of Injuries in Traffic Accidents.

For people involved in road traffic accidents, the time necessary to respond is crucial and it is hard to discern, which persons in which cars most urgently need help. To plan the rescue operation before arriving at the scene, digital information regarding the severity of the accident is vital. Our framework aims to transmit available data from the in-car sensors and to simulate the forces enacted on occupants using injury models. To avoid data security and privacy issues, we install low-cost hardware in the car for aggregation and preprocessing. Our framework can be retrofitted to existing cars and therefore could extend the benefits to a wide range of people.