Katrina Boločko

Image quality enhancement for skin cancer optical diagnostics

The research presents image quality analysis and enhancement proposals in biophotonic area. The sources of image problems are reviewed and analyzed. The problems with most impact in biophotonic area are analyzed in terms of specific biophotonic task – skin cancer diagnostics. The results point out that main problem for skin cancer analysis is the skin illumination problems. Since it is often not possible to prevent illumination problems, the paper proposes image post processing algorithm – low frequency filtering. Practical results show diagnostic results improvement after using proposed filter. Along that, filter do not reduces diagnostic results’ quality for images without illumination defects. Current filtering algorithm requires empirical tuning of filter parameters. Further work needed to test the algorithm in other biophotonic applications and propose automatic filter parameter selection.

Semi-automated non-invasive diagnostics method for melanoma differentiation from nevi and pigmented basal cell carcinomas

The incidence of skin cancer is still increasing mostly in in industrialized countries with light- skinned people. Late tumour detection is the main reason of the high mortality associated with skin cancer. The accessibility of early diagnostics of skin cancer in Latvia is limited by several factors, such as high cost of dermatology services, long queues on state funded oncologist examinations, as well as inaccessibility of oncologists in the countryside regions - this is an actual clinical problem. The new strategies and guidelines for skin cancer early detection and post-surgical follow-up intend to realize the full body examination (FBE) by primary care physicians (general practitioners, interns) in combination with classical dermoscopy. To implement this approach, a semi- automated method was established. Developed software analyses the combination of 3 optical density images at 540 nm, 650 nm, and 950 nm from pigmented skin malformations and classifies them into three groups- nevi, pigmented basal cell carcinoma or melanoma.