Browsing by Author "Veil, Carina"

Now showing 1 - 2 of 2

Open Access
Cystoscopic depth estimation using gated adversarial domain adaptation
(2023) Somers, Peter; Holdenried-Krafft, Simon; Zahn, Johannes; Schüle, Johannes; Veil, Carina; Harland, Niklas; Walz, Simon; Stenzl, Arnulf; Sawodny, Oliver; Tarín, Cristina; Lensch, Hendrik P. A.
Monocular depth estimation from camera images is very important for surrounding scene evaluation in many technical fields from automotive to medicine. However, traditional triangulation methods using stereo cameras or multiple views with the assumption of a rigid environment are not applicable for endoscopic domains. Particularly in cystoscopies it is not possible to produce ground truth depth information to directly train machine learning algorithms for using a monocular image directly for depth prediction. This work considers first creating a synthetic cystoscopic environment for initial encoding of depth information from synthetically rendered images. Next, the task of predicting pixel-wise depth values for real images is constrained to a domain adaption between the synthetic and real image domains. This adaptation is done through added gated residual blocks in order to simplify the network task and maintain training stability during adversarial training. Training is done on an internally collected cystoscopy dataset from human patients. The results after training demonstrate the ability to predict reasonable depth estimations from actual cystoscopic videos and added stability from using gated residual blocks is shown to prevent mode collapse during adversarial training.
Open Access
Mathematical modeling and simulation of thyroid homeostasis : implications for the Allan-Herndon-Dudley syndrome
(2022) Wolff, Tobias M.; Veil, Carina; Dietrich, Johannes W.; Müller, Matthias A.
Introduction: A mathematical model of the pituitary-thyroid feedback loop is extended to deepen the understanding of the Allan-Herndon-Dudley syndrome (AHDS). The AHDS is characterized by unusual thyroid hormone concentrations and a mutation in the SLC16A2 gene encoding for the monocarboxylate transporter 8 (MCT8). This mutation leads to a loss of thyroid hormone transport activity. One hypothesis to explain the unusual hormone concentrations of AHDS patients is that due to the loss of thyroid hormone transport activity, thyroxine (T4) is partially retained in thyroid cells. This hypothesis is investigated by extending a mathematical model of the pituitary-thyroid feedback loop to include a model of the net effects of membrane transporters such that the thyroid hormone transport activity can be considered. A nonlinear modeling approach based on the Michaelis-Menten kinetics and its linear approximation are employed to consider the membrane transporters. The unknown parameters are estimated through a constrained parameter optimization. In dynamic simulations, damaged membrane transporters result in a retention of T4 in thyroid cells and ultimately in the unusual hormone concentrations of AHDS patients. The Michaelis-Menten modeling approach and its linear approximation lead to similar results. The results support the hypothesis that a partial retention of T4 in thyroid cells represents one mechanism responsible for the unusual hormone concentrations of AHDS patients. Moreover, our results suggest that the retention of T4 in thyroid cells could be the main reason for the unusual hormone concentrations of AHDS patients.