H-scan imaging and quantitative measurement to distinguish melanoma metastasis

The H-scan analysis has been developed as a sensitive measure of ultrasound scattering types. In this study, we aim to distinguish between two different melanoma tumors: YUMM and YUMMER. To characterize the tumor tissues, H-scan was applied to the melanoma samples, resulting in estimation of several parameters. Multiparametric analysis was performed by measuring the H-scan blue fraction, attenuation coefficient, H-scan signal-to-noise ratio (SNR), and B-scan SNR. Principal component analysis was applied to the parameters, forming clusters in 2D space. These were assigned as the inputs for support vector machine (SVM) classification. H-scan imaging was able to differentiate between YUMM and YUMMER; YUMMER showed as more blue (higher frequency) in color. The H-scan parameters of blue fraction and SNR show significant differences between the two types of melanoma. Combining the four parameters, principal components formed clusters of YUMM and YUMMER. The clusters were separated by the decision planes obtained using SVM analysis with 88.5% classification accuracy. We anticipate clinical use of H-scan parameters for melanoma diagnosis.