@article{NoyaletIlgenBuerkleinetal.2022,
  author    = {Noyalet, Laurent and Ilgen, Lukas and B{\"u}rklein, Miriam and Shehata-Dieler, Wafaa and Taeger, Johannes and Hagen, Rudolf and Neun, Tilmann and Zabler, Simon and Althoff, Daniel and Rak, Kristen},
  title     = {Vestibular aqueduct morphology and Meniere's disease - development of the vestibular aqueduct score by 3D analysis},
  series = {Frontiers in Surgery},
  volume    = {9},
  journal   = {Frontiers in Surgery},
  issn      = {2296-875X},
  doi       = {10.3389/fsurg.2022.747517},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-312893},
  year      = {2022},
  abstract  = {Improved radiological examinations with newly developed 3D models may increase understanding of Meniere's disease (MD). The morphology and course of the vestibular aqueduct (VA) in the temporal bone might be related to the severity of MD. The presented study explored, if the VA of MD and non-MD patients can be grouped relative to its angle to the semicircular canals (SCC) and length using a 3D model. Scans of temporal bone specimens (TBS) were performed using micro-CT and micro flat panel volume computed tomography (mfpVCT). Furthermore, scans were carried out in patients and TBS by computed tomography (CT). The angle between the VA and the three SCC, as well as the length of the VA were measured. From these data, a 3D model was constructed to develop the vestibular aqueduct score (VAS). Using different imaging modalities it was demonstrated that angle measurements of the VA are reliable and can be effectively used for detailed diagnostic investigation. To test the clinical relevance, the VAS was applied on MD and on non-MD patients. Length and angle values from MD patients differed from non-MD patients. In MD patients, significantly higher numbers of VAs could be assigned to a distinct group of the VAS. In addition, it was tested, whether the outcome of a treatment option for MD can be correlated to the VAS.},
  language  = {en}
}
@article{StebaniBlaimerZableretal.2023,
  author    = {Stebani, Jannik and Blaimer, Martin and Zabler, Simon and Neun, Tilmann and Pelt, Dani{\"e}l M. and Rak, Kristen},
  title     = {Towards fully automated inner ear analysis with deep-learning-based joint segmentation and landmark detection framework},
  series = {Scientific Reports},
  volume    = {13},
  journal   = {Scientific Reports},
  doi       = {10.1038/s41598-023-45466-9},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-357411},
  year      = {2023},
  abstract  = {Automated analysis of the inner ear anatomy in radiological data instead of time-consuming manual assessment is a worthwhile goal that could facilitate preoperative planning and clinical research. We propose a framework encompassing joint semantic segmentation of the inner ear and anatomical landmark detection of helicotrema, oval and round window. A fully automated pipeline with a single, dual-headed volumetric 3D U-Net was implemented, trained and evaluated using manually labeled in-house datasets from cadaveric specimen (N = 43) and clinical practice (N = 9). The model robustness was further evaluated on three independent open-source datasets (N = 23 + 7 + 17 scans) consisting of cadaveric specimen scans. For the in-house datasets, Dice scores of 0.97 and 0.94, intersection-over-union scores of 0.94 and 0.89 and average Hausdorf distances of 0.065 and 0.14 voxel units were achieved. The landmark localization task was performed automatically with an average localization error of 3.3 and 5.2 voxel units. A robust, albeit reduced performance could be attained for the catalogue of three open-source datasets. Results of the ablation studies with 43 mono-parametric variations of the basal architecture and training protocol provided task-optimal parameters for both categories. Ablation studies against single-task variants of the basal architecture showed a clear performance beneft of coupling landmark localization with segmentation and a dataset-dependent performance impact on segmentation ability.},
  language  = {en}
}