@article{ToepferCorovicFetteetal.2015,
  author    = {Toepfer, Martin and Corovic, Hamo and Fette, Georg and Kl{\"u}gl, Peter and St{\"o}rk, Stefan and Puppe, Frank},
  title     = {Fine-grained information extraction from German transthoracic echocardiography reports},
  series = {BMC Medical Informatics and Decision Making},
  volume    = {15},
  journal   = {BMC Medical Informatics and Decision Making},
  number    = {91},
  doi       = {doi:10.1186/s12911-015-0215-x},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-125509},
  year      = {2015},
  abstract  = {Background Information extraction techniques that get structured representations out of unstructured data make a large amount of clinically relevant information about patients accessible for semantic applications. These methods typically rely on standardized terminologies that guide this process. Many languages and clinical domains, however, lack appropriate resources and tools, as well as evaluations of their applications, especially if detailed conceptualizations of the domain are required. For instance, German transthoracic echocardiography reports have not been targeted sufficiently before, despite of their importance for clinical trials. This work therefore aimed at development and evaluation of an information extraction component with a fine-grained terminology that enables to recognize almost all relevant information stated in German transthoracic echocardiography reports at the University Hospital of W{\"u}rzburg. Methods A domain expert validated and iteratively refined an automatically inferred base terminology. The terminology was used by an ontology-driven information extraction system that outputs attribute value pairs. The final component has been mapped to the central elements of a standardized terminology, and it has been evaluated according to documents with different layouts. Results The final system achieved state-of-the-art precision (micro average.996) and recall (micro average.961) on 100 test documents that represent more than 90 \% of all reports. In particular, principal aspects as defined in a standardized external terminology were recognized with f 1=.989 (micro average) and f 1=.963 (macro average). As a result of keyword matching and restraint concept extraction, the system obtained high precision also on unstructured or exceptionally short documents, and documents with uncommon layout. Conclusions The developed terminology and the proposed information extraction system allow to extract fine-grained information from German semi-structured transthoracic echocardiography reports with very high precision and high recall on the majority of documents at the University Hospital of W{\"u}rzburg. Extracted results populate a clinical data warehouse which supports clinical research.},
  language  = {en}
}
@article{WickHarteltPuppe2019,
  author    = {Wick, Christoph and Hartelt, Alexander and Puppe, Frank},
  title     = {Staff, symbol and melody detection of Medieval manuscripts written in square notation using deep Fully Convolutional Networks},
  series = {Applied Sciences},
  volume    = {9},
  journal   = {Applied Sciences},
  number    = {13},
  issn      = {2076-3417},
  doi       = {10.3390/app9132646},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-197248},
  year      = {2019},
  abstract  = {Even today, the automatic digitisation of scanned documents in general, but especially the automatic optical music recognition (OMR) of historical manuscripts, still remains an enormous challenge, since both handwritten musical symbols and text have to be identified. This paper focuses on the Medieval so-called square notation developed in the 11th-12th century, which is already composed of staff lines, staves, clefs, accidentals, and neumes that are roughly spoken connected single notes. The aim is to develop an algorithm that captures both the neumes, and in particular its melody, which can be used to reconstruct the original writing. Our pipeline is similar to the standard OMR approach and comprises a novel staff line and symbol detection algorithm based on deep Fully Convolutional Networks (FCN), which perform pixel-based predictions for either staff lines or symbols and their respective types. Then, the staff line detection combines the extracted lines to staves and yields an F\(_1\) -score of over 99\% for both detecting lines and complete staves. For the music symbol detection, we choose a novel approach that skips the step to identify neumes and instead directly predicts note components (NCs) and their respective affiliation to a neume. Furthermore, the algorithm detects clefs and accidentals. Our algorithm predicts the symbol sequence of a staff with a diplomatic symbol accuracy rate (dSAR) of about 87\%, which includes symbol type and location. If only the NCs without their respective connection to a neume, all clefs and accidentals are of interest, the algorithm reaches an harmonic symbol accuracy rate (hSAR) of approximately 90\%. In general, the algorithm recognises a symbol in the manuscript with an F\(_1\) -score of over 96\%.},
  language  = {en}
}