Skip to main content
main-content

Über dieses Buch

In his master thesis, Sven Painer develops, implements, and evaluates a method to reconstruct the liver surface from monocular mini-laparoscopic sequences. The principal focus of his research is to create a basis for helping clinicians to write reports with quantitative descriptions of the liver surface. A Structure from Motion approach is performed to do a sparse reconstruction of the liver surface and subsequently this information is used in a variation based dense 3D reconstruction. The algorithms are formulated in a causal way, enabling the implementation to be run in real-time on an adequate hardware platform. The results show a significant performance increase and pave the way to give clinicians a feedback during video capturing to improve the quality of the reconstruction in the near future.

Inhaltsverzeichnis

Frontmatter

1. Introduction

Abstract
Mini-laparoscopy is a method to visually inspect the abdomen. It can be used to examine the surface of the liver and detect fibrosis or cirrhosis. At the moment, it is not possible to get any quantitative measurements. Therefore, it is desirable to reconstruct the liver surface and to be able to do quantitative measurements on this reconstruction. In this thesis, a method to reconstruct the liver surface from monocular mini-laparoscopic sequences shall be implemented and evaluated.
Sven Painer

2. Theoretical Background

Abstract
This chapter describes the theoretical background of this thesis. It starts with defining the Legendre-Fenchel transformation that is a prerequisite for the dense reconstruction. Then the possibility to be invariant to illumination change by using photometric invariants is introduced. After these prerequisites, the sparse reconstruction will be defined as its results are needed by the dense reconstruction. In the end, the theory of the dense reconstruction is shown.
Sven Painer

3. Implementation

Abstract
This chapter describes some important aspects of the implementation of the software. The software is implemented in C++ under the usage of some libraries and tools that are listed in Table 3.1.
Sven Painer

4. Evaluation

Abstract
This chapter gives an evaluation of the implemented 3D reconstruction algorithm. It starts with introducing the ground truth data that has been used for all evaluations. Afterwards, the sparse reconstruction and then the dense reconstruction are evaluated. In the end, selected performance test are shown.
Sven Painer

Backmatter

Weitere Informationen

Premium Partner