Correct classification of skin lesions is a key step in skin cancer screening, which requires high accuracy and interpretability. This paper proposes a multimodal method for differentiating various clinical forms of basal cell carcinoma and benign neoplasms that includes machine learning. This study was conducted on 37 neoplasms, including benign neoplasms and five different clinical forms of basal cell carcinoma. The proposed multimodal screening method combines diffuse reflectance spectroscopy, optical coherence tomography and high-frequency ultrasound. Using diffuse reflectance spectroscopy, the coefficients of melanin pigmentation, erythema, hemoglobin content, and the slope coefficient of diffuse reflectance spectroscopy in the wavelength range 650–800 nm were determined. Statistical texture analysis of optical coherence tomography images was used to calculate first- and second-order statistical parameters. The analysis of ultrasound images assessed the shape of the tumor according to parameters such as area, perimeter, roundness and other characteristics. Based on the calculated parameters, a machine learning algorithm was developed to differentiate the various clinical forms of basal cell carcinoma. The proposed algorithm for classifying various forms of basal cell carcinoma and benign neoplasms provided a sensitivity of 70.6 ± 17.3%, specificity of 95.9 ± 2.5%, precision of 72.6 ± 14.2%, F1 score of 71.5 ± 15.6% and mean intersection over union of 57.6 ± 20.1%. Moreover, for differentiating basal cell carcinoma and benign neoplasms without taking into account the clinical form, the method achieved a sensitivity of 89.1 ± 8.0%, specificity of 95.1 ± 0.7%, F1 score of 89.3 ± 3.4% and mean intersection over union of 82.6 ± 10.8%.
Current study presents an advanced method for improving the visualization of subsurface blood vessels using laser speckle contrast imaging (LSCI), enhanced through principal component analysis (PCA) filtering. By combining LSCI and laser speckle entropy imaging with PCA filtering, the method effectively separates static and dynamic components of the speckle signal, significantly improving the accuracy of blood flow assessments, even in the presence of static scattering layers located above and below the vessel. Experiments conducted on optical phantoms, with the vessel depths ranging from 0.6 to 2 mm, and in vivo studies on a laboratory mouse ear demonstrate substantial improvements in image contrast and resolution. The method’s sensitivity to blood flow velocity within the physiologic range (0.98–19.66 mm/s) is significantly enhanced, while its sensitivity to vessel depth is minimized. These results highlight the method’s ability to assess blood flow velocity independently of vessel depth, overcoming a major limitation of conventional LSCI techniques. The proposed approach holds great potential for non-invasive biomedical imaging, offering improved diagnostic accuracy and contrast in vascular imaging. These findings may be particularly valuable for advancing the use of LSCI in clinical diagnostics and biomedical research, where high precision in blood flow monitoring is essential. Graphical Abstract