Image analysis and processing methods in verifying the correctness of performing low-invasive esthetic medical procedures

Abstract

BackgroundEfficacy and safety of various treatments using fractional laser or radiofrequency depend, to a large extent, on precise movement of equipment head across the patient’s skin. In addition, they both depend on uniform distribution of emitted pulses throughout the treated skin area. The pulses should be closely adjacent but they should not overlap. Pulse overlapping results in amplification of irradiation dose and carries the danger of unwanted effects.MethodsImages obtained in infrared mode (Flir SC5200 thermovision camera equipped with photon detector) were entered into Matlab environment. Thermal changes in the skin were forced by CO2RE laser. Proposed image analysis and processing methods enable automatic recognition of CO2RE laser sites of action, making possible to assess the correctness of performed cosmetic procedures.Results80 images were acquired and analyzed. Regions of interest (ROI) for the entire treatment field were determined automatically. In accordance with the proposed algorithm, laser-irradiated Li areas (ROI) were determined for the treatment area. On this basis, error values were calculated and expressed as percentage of area not covered by any irradiation dose (δo) and as percentage area which received double dose (δz). The respective values for the analyzed images were δo=17.87±10.5% and δz=1.97±1.5%, respectively.ConclusionsThe presented method of verifying the correctness of performing low-invasive esthetic medical (cosmetic) procedures has proved itself numerous times in practice. Advantages of the method include: automatic determination of coverage error values δo and δz, non-invasive, sterile and remote-controlled thermovisual mode of measurements, and possibility of assessing dynamics of patient’s skin temperature changes.

Blood pulsation measurement using cameras operating in visible light: limitations

“…The initial image acquisition performed with a camera confirmed that the size of a single cluster of noise is not greater than 4 pixels. Therefore, the sufficient mask size was M h × N h = 9 × 9 pixels [ 26 ]. The filtered sequence of images L MED ( m,n,s,i ) was further subjected to stabilization.…”

Algorithm for Analyzing Thermal Images of Laser Irradiated Human Skin

“…As mentioned before, thermal parameters like active time are the ones dominating laser-skin interaction in port wine stain's treatment. Works that implement thermal vision to analyze the skin treatment process can be found, as in [13][14][15] (those works are focused on area temperature observing), or to detect the presence of vascular disorders as in. 16 Our method is targeted toward the laser treatment itself, and it implements accurate single beam tracking assuming considerable movements that would translate the laser beam within the camera field of view during the treatment.…”

Some selected quantitative methods of thermal image analysis in Matlab

“…If the maximum number of a single distortion is not greater than 4 pixels, the optimum mask size is M h × N h = 3 × 3 pixels. In practice, the most common choice of the median filter is mainly due to the fact that it does not introduce new temperature values ​​for the analysed pixels. The filtered input image L GRAY ( m,n ) results in the image L MED ( m , n ).…”