Automatic segmentation and analysis of gills from X-ray computed tomography data

Research topic/area: Image analysis, Computer science, Micro computed tomography
Type of thesis: Bachelor / Master
Start time: 04.05.2026
Application deadline: 30.04.2026
Duration of the thesis: 6 Months

Description

The coordination of organ growth represents one of the most fundamental questions in biology. How organs grow in proportion to each other and to the overall body size is critical for understanding development, homeostasis, and regenerative processes. Teleost fish provide a particularly interesting model for studying these phenomena due to their capacity for lifelong growth, allowing to investigate growth dynamics across different life stages.
Preliminary data in medaka species indicate notable differences in the relative volumes of several organs, suggesting species-specific growth patterns and organ scaling mechanisms. Quantifying these differences through detailed morphometric analysis, however, is an extremely time-consuming and labor-intensive task, limiting the throughput and scope of such studies.
Therefore, a central aim of this thesis is to develop an automated pipeline for complex organ segmentation. Such a tool would enable high-throughput, precise, and reproducible measurement of organ volumes, facilitating large-scale comparative studies across species and developmental stages. Your tasks would be:

Collect and preprocess imaging data from medaka fish.
Develop and implement automated pipelines for organ segmentation.
Perform statistical and morphometric analyses.
Present results in lab meetings or write reports/manuscripts.

By integrating computational imaging with biological analysis, this work aims to provide a robust framework for systematically investigating organ growth coordination in teleost fish and uncovering the underlying principles that govern organ size regulation.

Requirement

Requirements for students

Familiarity with imaging techniques (microscopy, MRI, CT)
Familiarity with programming and image analysis tools (Python, MATLAB, Fiji/ImageJ)
Ability to analyze and interpret quantitative morphometric data using machine learning.

Faculty departments

Engineering sciences
Biological engineering

Supervision

Title, first name, last name: Prof. Dr. Venera Weinhardt
Organizational unit: IMT, KIT
Email address: venera.weinhardt@kit.edu
Link to personal homepage/personal page: Website

Application via email

Application documents

Cover letter
Curriculum vitae
Grade transcript

E-Mail Address for application
Senden Sie die oben genannten Bewerbungsunterlagen bitte per Mail an venera.weinhardt@kit.edu

Back