0000000000485476
AUTHOR
Sebastian Brodehl
showing 3 related works from this author
Studying the evolution of neural activation patterns during training of feed-forward ReLU networks
2021
The ability of deep neural networks to form powerful emergent representations of complex statistical patterns in data is as remarkable as imperfectly understood. For deep ReLU networks, these are encoded in the mixed discrete–continuous structure of linear weight matrices and non-linear binary activations. Our article develops a new technique for instrumenting such networks to efficiently record activation statistics, such as information content (entropy) and similarity of patterns, in real-world training runs. We then study the evolution of activation patterns during training for networks of different architecture using different training and initialization strategies. As a result, we see …
Predicting survival after transarterial chemoembolization for hepatocellular carcinoma using a neural network: A Pilot Study.
2019
BACKGROUND AND AIMS Deciding when to repeat and when to stop transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) can be difficult even for experienced investigators. Our aim was to develop a survival prediction model for such patients undergoing TACE using novel machine learning algorithms and to compare it to conventional prediction scores, ART, ABCR and SNACOR. METHODS For this retrospective analysis, 282 patients who underwent TACE for HCC at our tertiary referral centre between January 2005 and December 2017 were included in the final analysis. We built an artificial neural network (ANN) including all parameters used by the aforementioned risk scores a…
Workflow-centred open-source fully automated lung volumetry in chest CT
2019
Aim To develop a robust open-source method for fully automated extraction of total lung capacity (TLC) from computed tomography (CT) images and to demonstrate its integration into the clinical workflow. Materials and methods Using only open-source software, an algorithm was developed based on a region-growing method that does not require manual interaction. Lung volumes calculated from reconstructions with different kernels (TLCCT) were assessed. To validate the algorithm calculations, the results were correlated to TLC measured by pulmonary function testing (TLCPFT) in a subgroup of patients for which this information was available within 3 days of the CT examination. Results A total of 28…