Color Normalization for Histology Image Processing
Advisor: Prof. Dr. Nassir Navab
Supervision by: Dr. Tingying Peng
, Dr. Lichao Wang
Automated image processing and quantification are increasingly gaining attention in the field of digital pathology. However, a common problem in histology images is the color variation introduced by the use of different microscopies, scanners or inconsistencies in tissue preparation (an example of color variation is shown in Fig.1.). This creates difficulty in image interpretation by both pathologists and computational pathology software trained on a particular stain appearance.e.g. learning-based method. This project is to address the challenging issue of color inconsistency in histology and to develop a fast, accurate and robust color normalization technique.
The difficulty of the project will be adapted to an IDP, Bachelor or Master Thesis.
Figure 1: Same tissue section under different scanner (left) Aperio scanner (right) Hamamatsu scanner.
- Extend our existing color normalization technique
- Integration of the color normalization with common microscopy image format and viewer (e.g. OpenSlide?, http://openslide.org)
- Validation of the technique on clinical data
- You need to have very good experience of using Matlab. Good Python/Java skills will be an advantage.
- Experience in image processing with machine learning methods is highly desired.
 A. Vahadane, T. Peng, S. Albarqouni, M. Baust, K. Steiger, M. Schlitter, A. Sethi, N. Navab: "Structure-preserved Color Normalization For Histological Images". ISBI(2015).
| Students.ProjectForm |
| Title: || Color Normalization for Histology Image Processing |
| Abstract: || Automated image processing and quantification are increasingly gaining attention in the field of digital pathology. However, a common problem that encumbers computerized analysis is the color variation in histology, due to the use of different microscopies, scanners or inconsistencies in tissue preparation. This project is to address the issue of color inconsistency in histology and develop an effective normalization technique. |
| Student: || |
| Director: || Prof. Dr. Nassir Navab |
| Supervisor: || Dr. Tingying Peng, Dr. Lichao Wang |
| Type: || DA/MA/BA |
| Area: || Machine Learning |
| Status: || open |
| Start: || |
| Finish: || |
| Thesis (optional): || |
| Picture: || |