Medical Imaging

Contact: Professor Lasse Lensu

Medical imaging is among the most important application areas of computer vision and image analysis. In the recent years, MVPR has conducted research on processing retinal images and automatic detection of lesions of diabetic retinopathy from fundus images. The laboratory has published the DiaRetDB1 database for benchmarking diabetic retinopathy detection methods and the database has become one of the standard benchmarks in the field.

See: DiaRetDB1 V2.1.

Featured projects

Retinal Blood Vessel Segmentation and Characterisation (2014-2016)

Retinal blood vessel structure is an important indicator of many retinal and systemic diseases, which has motivated the development of various image segmentation and characterisation methods for the blood vessels. In this project, supervised and unsupervised segmentation methods were reviewed and compared as part of further characterisation of the vessel structure. The research was carried out in collaboration with the University of Birmingham, the University of Eastern Finland, and the University of Tampere.

Supplementary information for our paper Performance Comparison of Publicly Available Retinal Blood Vessel Segmentation Methods can be found under this project.

ReVision (2012-2015)

ReVision was a multidisciplinary research project focusing on improving retinal imaging, image processing, and computational analysis of the image data to enable efficient automatic and semi-automatic methods for eye health. The consortium partners were the University of Eastern Finland (responsible institution; photonics) and the University of Tampere (ophthalmology). The project had strong international collaboration with the University of Birmingham and Tokyo Institute of Technology. The project was funded by the Academy of Finland.

ReVision produced image processing and analysis methods for spectral retinal images, an enhanced prototype of a spectral fundus camera and a tunable spectral light source, a few scientific publications and one doctor of science in technology (Lauri Laaksonen, LUT).

ImageRet (2006-2009)

The ultimate goal of the Imageret project was to develop new imaging hardware and novel image processing methods to efficiently and reliably assist in medical decision making in diabetic retinopathy diagnosis.

The goal was achievable by combining the knowledge from medical science, optics, and image processing and via the scientific research provide new results to be used in medics. Furthermore, by educating new young masters and doctors within the field of medical image processing and medical image acquisition the future requirements of the health care can be met.

Biomolecular Vision

Contact: Professor Lasse Lensu

Molecular computing is a relatively new field of science where novel computing approaches are searched from the domain of molecules and atoms. More specifically, the aim is to understand how to control molecular reactions for information processing. Despite the fact that the Moore's "law" still holds, these studies are motivated by the increasing technical difficulties to further develop the CMOS transistors as the building blocks of computing devices. These difficulties are already realising because the microelectronics industry has already pushed multicore and other parallel architectures to the market.

Biomolecules offer several advantages over synthetic ones. In their natural environment, their functionality and robustness is usually close to optimal due to evolutionary steps during the development of their structure and function. Therefore, many things can be learned from nature by studying the biomolecules and their interactions. Most of the studies concerning information processing using biomolecules have concentrated in DNA and photoactive biomolecules, for example, rhodopsins, chloroplasts, photosynthetic reaction centers and light-harvesting complexes, and retinal proteins. Bacteriorhodopsin (BR) is a retinal protein which has been intensively studied and proposed for various applications.

Featured projects

MolComp

The purpose of MolComp is to study biomolecules and their usage in technical applications and information processing. The goal of MolComp is to understand especially the photoelectric functionality of bacteriorhodopsin and its applicability to implement colour-sensitive artificial retina.

Molecular computing has been studied in Lappeenranta from the year 1995. The research group has participated to the national nanotechnology research program funded by the Academy of Finland, and material science technology program funded by the Finnish Funding Agency for Technology and Innovation. The most important results up till now are as follows:

  1. Cultivation of the archaea, Halobacterium salinarum as the source of bacteriorhodopsin, and preparation of bacteriorhodopsin-in-polyvinylalcohol thick films.
  2. Single-element optoelectronic sensors based on wild-type BR and its variants.

    Single-element optoelectronic
element based on wild-type BR

  3. Colour-sensitive digital camera based on three types of BR.

    Camera matrix based on
wild-type BR Camera matrix based on
three types of BR

  4. Models for colour vision systems based on, e.g., BR.
  5. Simulation environment for the reduced photocycle of BR.