The increased availability of labeled X-ray image archives (e.g. ChestX-ray14 dataset) has triggered a growing interest in deep learning techniques. To provide better insight into the different approaches, and their applications to chest X-ray classification, we investigate a powerful network architecture in detail: the ResNet-50. Building on prior work in this domain, we consider transfer learning with and without fine-tuning as well as the training of a dedicated X-ray network from scratch. To leverage the high spatial resolution of X-ray data, we also include an extended ResNet-50 architecture, and a network integrating non-image data (patient age, gender and acquisition type) in the classification process. In a concluding experiment, we also investigate multiple ResNet depths (i.e. ResNet-38 and ResNet-101). In a systematic evaluation, using 5-fold re-sampling and a multi-label loss function, we compare the performance of the different approaches for pathology classification by ROC statistics and analyze differences between the classifiers using rank correlation. Overall, we observe a considerable spread in the achieved performance and conclude that the X-ray-specific ResNet-38, integrating non-image data yields the best overall results. Furthermore, class activation maps are used to understand the classification process, and a detailed analysis of the impact of non-image features is provided.

Determining the brain perfusion is an important task for diagnosis of vascular diseases such as occlusions and intracerebral haemorrhage. Even after successful diagnosis, there is a high risk of restenosis or rebleeding such that patients need intense attention in the days after treatment. Within this work, we present a diagnostic tomographic imager that allows access to brain perfusion quantitatively in short intervals. The device is based on the magnetic particle imaging technology and is designed for human scale. It is highly sensitive and allows the detection of an iron concentration of 263 pmol Fe ml −1 , which is one of the lowest iron concentrations imaged by MPI so far. The imager is self-shielded and can be used in unshielded environments such as intensive care units. In combination with the low technical requirements this opens up a variety of medical applications and would allow monitoring of stroke on intensive care units.