Skip to content

Level-set method for segmentation of HEp-2 cell fluorescence microscope images

Study level


Vacation research experience scheme

Faculty/Lead unit

Topic status

We're looking for students to study this topic.


Dr Jasmine Banks
Division / Faculty
Science and Engineering Faculty


Automated segmentation of the HEp-2 cell plays an important role in diagnosing an autoimmune disease. Specific failures of the immune system leads to many human autoimmune diseases. These diseases are often chronic, but early diagnosis can mean that earlier invention is possible, which can minimize further damage to organs and tissues.

Different technologies used in the medical and biomedical imaging research require a computer-aided diagnosis (CAD) system, based on image-based segmentation and classification by using signal processing techniques and deep learning.

Therefore, we are interested in using level-set method-based FCN-AlexNet for segmentation of HEp-2 cell fluorescence microscope images. These images will be used to design a CAD system to diagnose an autoimmune disease quickly and accurately.

Research activities

Under supervision and feedback from supervisors, you will design a CAD system or code using MATLAB.

Additionally, the project will require the use of a HEp-2 Cell microscopic image database which is available.


The outcome of this project will help pathologists and doctors in hospital and disease research centres to assess any differences in the structure and count types of HEp-2 cells and improve the accuracy of HEp-2 segmentation.

Skills and experience

The project can be tailored to utilise your specific skill set, but generally you should meet at least some of the following criteria:

  • sound knowledge of MATLAB and C/C++ coding languages
  • basic knowledge of signal processing/computational mathematics or the desire to learn
  • willing to be exposed to machine learning and deep learning techniques.


Contact the supervisor for more information.