Browsing by Author "Harland, Niklas"

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
Data-driven identification of biomarkers for in situ monitoring of drug treatment in bladder cancer organoids
(2022) Becker, Lucas; Fischer, Felix; Fleck, Julia L.; Harland, Niklas; Herkommer, Alois; Stenzl, Arnulf; Aicher, Wilhelm K.; Schenke-Layland, Katja; Marzi, Julia
Three-dimensional (3D) organoid culture recapitulating patient-specific histopathological and molecular diversity offers great promise for precision medicine in cancer. In this study, we established label-free imaging procedures, including Raman microspectroscopy (RMS) and fluorescence lifetime imaging microscopy (FLIM), for in situ cellular analysis and metabolic monitoring of drug treatment efficacy. Primary tumor and urine specimens were utilized to generate bladder cancer organoids, which were further treated with various concentrations of pharmaceutical agents relevant for the treatment of bladder cancer (i.e., cisplatin, venetoclax). Direct cellular response upon drug treatment was monitored by RMS. Raman spectra of treated and untreated bladder cancer organoids were compared using multivariate data analysis to monitor the impact of drugs on subcellular structures such as nuclei and mitochondria based on shifts and intensity changes of specific molecular vibrations. The effects of different drugs on cell metabolism were assessed by the local autofluorophore environment of NADH and FAD, determined by multiexponential fitting of lifetime decays. Data-driven neural network and data validation analyses (k-means clustering) were performed to retrieve additional and non-biased biomarkers for the classification of drug-specific responsiveness. Together, FLIM and RMS allowed for non-invasive and molecular-sensitive monitoring of tumor-drug interactions, providing the potential to determine and optimize patient-specific treatment efficacy.