Segmentation of dermatoscopic images of skin lesions. Comparison of methods

The work discusses a number of techniques for segmenting dermoscopic images of skin lesions to identify the areas occupied by these lesions. Segmentation is necessary as the first stage of most methods of computer diagnostics of malignancy of neoplasms. A number of techniques, such as ABCDE, use the shape of the tumor as one of the criteria for making a diagnosis; for others, such as the use of convolutional neural networks, identifying the tumor allows one to increase the accuracy of the results obtained. The work discusses three methods of segmentation: thresholding using Otsu's method to calculate the threshold value, a convolutional neural network built on the U-net architecture, and a similar convolutional neural network with an added attention mechanism. The advantages and disadvantages of each method are considered, as well as the possibility of using them together to obtain the best segmentation results.

The paper considers the application of an algorithm based on a morphological projector for determining structural differences for comparing dermoscopic images. This will allow to identify changes that have occurred in skin lesions over time, for a more accurate diagnosis of their malignancy. The proposed algorithm makes it possible to detect differences in images even if there is a significant difference in the brightness and color levels of the compared images, and also ignores small insignificant details, such as noise, dermatoscope optics marks, hair, etc. A method for correcting the desynchronization of images using the structural similarity index as a similarity metric, and the sine-cosine algorithm as an optimization algorithm is proposed. The proposed algorithms were tested on dermatoscopic images and the possibility of their application was demonstrated.

1. Жуковец А.Г., Океанов А.Е., Моисеев П.И. Прокошин А.В. Меланома кожи в Республике Беларусь: эпидемиология, диагностика и результаты лечения // Онкологический журнал. – 2017. – Т. 11, № 1. – С. 35-46.

2. Rigel DS, Russak J, Friedman R. The evolution of melanoma diagnosis: 25 years beyond the ABCDs. CA Cancer J Clin. 2010 Sep-Oct;60(5):301-16.

3. Duarte AF, Sousa-Pinto B, Azevedo LF, Barros AM, Puig S, Malvehy J, Haneke E, Correia O. Clinical ABCDE rule for early melanoma detection. Eur J Dermatol. 2021 Dec 1;31(6):771-778.

4. Mabrouk MS, Sayed AY, Afifi HM, Sheha MA, Sharwy A. Fully Automated Approach for Early Detection of Pigmented Skin Lesion Diagnosis Using ABCD. J Healthc Inform Res. 2020 Mar 3;4(2):151-173.

5. Core Java: Fundamentals, Volume 1 (Oracle Press Java) / Cay Horstmann. – Oracle Press, 2021. – 944 p.

6. N. Otsu. A threshold selection method from gray-level histograms (англ.) // IEEE Trans. Sys., Man., Cyber.: journal. – 1979. – Vol. 9. – P. 62-66.

7. Ronneberger, Olaf & Fischer, Philipp & Brox, Thomas. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. LNCS. 9351. 234-241.

8. Шолле Франсуа. Глубокое обучение на Python. 2-е межд. издание. СПб. : Питер, 2023. – 576 с.

9. Oktay, Ozan et al. “Attention U-Net: Learning Where to Look for the Pancreas.” ArXiv abs/1804.03999 (2018): n. pag