ATAnke Tschirschky

Anke Tschirschky

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Anke Tschirschky has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Extending convolutional neural networks to detect differences in symmetry in videorasterstereographic back scans with the aim to improve screening for adolescent idiopathic scoliosis

    by Thurid Jochim, Paula Wilhelm, Anke Tschirschky, Arkadiusz Żurawski, Andreas Heinke, Nico Stecher, Hagen Malberg

    Purpose: A healthy posture is characterized by symmetric features like equal shoulder height, a straight spinous process line and equally-sized waist triangles. Deviations suggest spinal disorders, among them adolescent idiopathic scoliosis (AIS), a three-dimensional spinal curvature requiring timely treatment. AIS screenings are debated among the scientific community. This study proposes two symmetry-sensitive convolutional neural networks (CNNs) to identify asymmetries in videorasterstereographic back curvature images to classify AIS. Methods: A total of 1444 videorasterstereographic measurements were collected from individuals (11 ± 2.4 years), among them 355 with AIS, 306 with other spinal deformities and 783 with healthy posture. Two types of curvature images, Mean and Gauss, were compared using a VGG16 network and a two-channel CNN based on DeepSymNet. The latter analyzes left and right side of the torso image separately, then merges the results and identifies asymmetries. Results: Both models achieved accuracies between 0.768 and 0.801 during validation, the accuracy of the test set of the tuned DeepSymNet (five repeated trials) was 0.744 ± 0.014, specificity was 0.748 ± 0.025, sensitivity 0.726 ± 0.044 and PPV 0.417 ± 0.013. The equal performances show models were able to learn symmetry, making both suitable for training videorasterstereographic images. The main benefit and greatest challenge was the dataset diversity, which incorporated a variety of postural conditions, confounding AIS features. Conclusion: Adapting CNNs to include symmetry analysis could be an improvement to other known applications of deep learning in spinal deformity analysis. Refining the dataset to incorporate more mild cases could enhance the performance of DeepSymNet in particular. With these modifications, DeepSymNet as well as VGG16 are promising approaches for future AIS screenings.

  • Open Access

    Brace Effects on Spatiotemporal Gait Parameters from Pedobarography in Adolescent Idiopathic Scoliosis

    by Anke Tschirschky, Arkadiusz Żurawski, Johanna Dohndorf, Hagen Malberg, Martin Schmidt

    Adolescent idiopathic scoliosis (AIS) is a threedimensional deformation of the spine typically occuring in adolescents, mainly females. Untreated AIS can lead to the need for surgical intervention or to severe back problems later in life. The conventional treatment of AIS involves the use of custom-made braces, combined with physiotherapy. The therapeutic efficiency of the braces is determined using static X-rays. Dynamic evaluations are based on the experience of orthopedic technicians. However, evidence-based knowledge is needed to compare treatment objectively. Gait analysis offers the potential of dynamically assessing the effect of braces without radiation. To evaluate the evidence-based effect of braces using gait analysis, it is first necessary to identify differences between gait with and without brace. Therefore, in this pilot study, pedobarographic gait analyses of nine AIS patients were examined and evaluated. We comprised 199 dynamic gait parameters extracted from pedobarographic measurements covering spatiotemporal gait parameters, pressure and force distributions of foot zones. Logistic regression analysis was used to classify gait with and without brace. A significant model (p < 0.01) with two significant coefficients (p < 0.05) was revealed covering time to maximum force in relation to segment contact time for left rear and maximum pressure of left toe. Overall classification performance showed an accuracy of 88.9% to distinguish between with and without brace. Our study demonstrates that there are differences in the gait patterns of AIS patients with and without braces. Further studies, including a more extensive data set, may yield evidence-based findings on the effect of braces on dynamic gait patterns to be used in customized braces for the improved effectiveness in therapy.