@phdthesis{Krenzer2023,
  author    = {Krenzer, Adrian},
  title     = {Machine learning to support physicians in endoscopic examinations with a focus on automatic polyp detection in images and videos},
  doi       = {10.25972/OPUS-31911},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-319119},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2023},
  abstract  = {Deep learning enables enormous progress in many computer vision-related tasks. Artificial Intel- ligence (AI) steadily yields new state-of-the-art results in the field of detection and classification. Thereby AI performance equals or exceeds human performance. Those achievements impacted many domains, including medical applications. One particular field of medical applications is gastroenterology. In gastroenterology, machine learning algorithms are used to assist examiners during interventions. One of the most critical concerns for gastroenterologists is the development of Colorectal Cancer (CRC), which is one of the leading causes of cancer-related deaths worldwide. Detecting polyps in screening colonoscopies is the essential procedure to prevent CRC. Thereby, the gastroenterologist uses an endoscope to screen the whole colon to find polyps during a colonoscopy. Polyps are mucosal growths that can vary in severity. This thesis supports gastroenterologists in their examinations with automated detection and clas- sification systems for polyps. The main contribution is a real-time polyp detection system. This system is ready to be installed in any gastroenterology practice worldwide using open-source soft- ware. The system achieves state-of-the-art detection results and is currently evaluated in a clinical trial in four different centers in Germany. The thesis presents two additional key contributions: One is a polyp detection system with ex- tended vision tested in an animal trial. Polyps often hide behind folds or in uninvestigated areas. Therefore, the polyp detection system with extended vision uses an endoscope assisted by two additional cameras to see behind those folds. If a polyp is detected, the endoscopist receives a vi- sual signal. While the detection system handles the additional two camera inputs, the endoscopist focuses on the main camera as usual. The second one are two polyp classification models, one for the classification based on shape (Paris) and the other on surface and texture (NBI International Colorectal Endoscopic (NICE) classification). Both classifications help the endoscopist with the treatment of and the decisions about the detected polyp. The key algorithms of the thesis achieve state-of-the-art performance. Outstandingly, the polyp detection system tested on a highly demanding video data set shows an F1 score of 90.25 \% while working in real-time. The results exceed all real-time systems in the literature. Furthermore, the first preliminary results of the clinical trial of the polyp detection system suggest a high Adenoma Detection Rate (ADR). In the preliminary study, all polyps were detected by the polyp detection system, and the system achieved a high usability score of 96.3 (max 100). The Paris classification model achieved an F1 score of 89.35 \% which is state-of-the-art. The NICE classification model achieved an F1 score of 81.13 \%. Furthermore, a large data set for polyp detection and classification was created during this thesis. Therefore a fast and robust annotation system called Fast Colonoscopy Annotation Tool (FastCAT) was developed. The system simplifies the annotation process for gastroenterologists. Thereby the i gastroenterologists only annotate key parts of the endoscopic video. Afterward, those video parts are pre-labeled by a polyp detection AI to speed up the process. After the AI has pre-labeled the frames, non-experts correct and finish the annotation. This annotation process is fast and ensures high quality. FastCAT reduces the overall workload of the gastroenterologist on average by a factor of 20 compared to an open-source state-of-art annotation tool.},
  subject      = {Deep Learning},
  language  = {en}
}
@phdthesis{Houshiar2017,
  author    = {Houshiar, Hamidreza},
  title     = {Documentation and mapping with 3D point cloud processing},
  isbn      = {978-3-945459-14-0},
  doi       = {10.25972/OPUS-14449},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-144493},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2017},
  abstract  = {3D point clouds are a de facto standard for 3D documentation and modelling. The advances in laser scanning technology broadens the usability and access to 3D measurement systems. 3D point clouds are used in many disciplines such as robotics, 3D modelling, archeology and surveying. Scanners are able to acquire up to a million of points per second to represent the environment with a dense point cloud. This represents the captured environment with a very high degree of detail. The combination of laser scanning technology with photography adds color information to the point clouds. Thus the environment is represented more realistically. Full 3D models of environments, without any occlusion, require multiple scans. Merging point clouds is a challenging process. This thesis presents methods for point cloud registration based on the panorama images generated from the scans. Image representation of point clouds introduces 2D image processing methods to 3D point clouds. Several projection methods for the generation of panorama maps of point clouds are presented in this thesis. Additionally, methods for point cloud reduction and compression based on the panorama maps are proposed. Due to the large amounts of data generated from the 3D measurement systems these methods are necessary to improve the point cloud processing, transmission and archiving. This thesis introduces point cloud processing methods as a novel framework for the digitisation of archeological excavations. The framework replaces the conventional documentation methods for excavation sites. It employs point clouds for the generation of the digital documentation of an excavation with the help of an archeologist on-site. The 3D point cloud is used not only for data representation but also for analysis and knowledge generation. Finally, this thesis presents an autonomous indoor mobile mapping system. The mapping system focuses on the sensor placement planning method. Capturing a complete environment requires several scans. The sensor placement planning method solves for the minimum required scans to digitise large environments. Combining this method with a navigation system on a mobile robot platform enables it to acquire data fully autonomously. This thesis introduces a novel hole detection method for point clouds to detect obscured parts of a captured environment. The sensor placement planning method selects the next scan position with the most coverage of the obscured environment. This reduces the required number of scans. The navigation system on the robot platform consist of path planning, path following and obstacle avoidance. This guarantees the safe navigation of the mobile robot platform between the scan positions. The sensor placement planning method is designed as a stand alone process that could be used with a mobile robot platform for autonomous mapping of an environment or as an assistant tool for the surveyor on scanning projects.},
  subject      = {3D Punktwolke},
  language  = {en}
}
@phdthesis{Sun2014,
  author    = {Sun, Kaipeng},
  title     = {Six Degrees of Freedom Object Pose Estimation with Fusion Data from a Time-of-flight Camera and a Color Camera},
  isbn      = {978-3-923959-97-6},
  doi       = {10.25972/OPUS-10508},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-105089},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2014},
  abstract  = {Object six Degrees of Freedom (6DOF) pose estimation is a fundamental problem in many practical robotic applications, where the target or an obstacle with a simple or complex shape can move fast in cluttered environments. In this thesis, a 6DOF pose estimation algorithm is developed based on the fused data from a time-of-flight camera and a color camera. The algorithm is divided into two stages, an annealed particle filter based coarse pose estimation stage and a gradient decent based accurate pose optimization stage. In the first stage, each particle is evaluated with sparse representation. In this stage, the large inter-frame motion of the target can be well handled. In the second stage, the range data based conventional Iterative Closest Point is extended by incorporating the target appearance information and used for calculating the accurate pose by refining the coarse estimate from the first stage. For dealing with significant illumination variations during the tracking, spherical harmonic illumination modeling is investigated and integrated into both stages. The robustness and accuracy of the proposed algorithm are demonstrated through experiments on various objects in both indoor and outdoor environments. Moreover, real-time performance can be achieved with graphics processing unit acceleration.},
  subject      = {Mustererkennung},
  language  = {en}
}