Search

In this study, patient data were combined with Raman and autofluorescence spectral parameters for more accurate identification of skin tumors. The spectral and patient data of skin tumors were classified by projection on latent structures and discriminant analysis. The importance of patient risk factors was determined using statistical improvement of ROC AUCs when spectral parameters were combined with risk factors. Gender, age and tumor localization were found significant for classification of malignant versus benign neoplasms, resulting in improvement of ROC AUCs from 0.610 to 0.818 (p < 0.05). To distinguish melanoma versus pigmented skin tumors, the same factors significantly improved ROC AUCs from 0.709 to 0.810 (p < 0.05) when analyzed together according to the spectral data, but insignificantly (p > 0.05) when analyzed individually. For classification of melanoma versus seborrheic keratosis, no statistical improvement of ROC AUC was observed when the patient data were added to the spectral data. In all three classification models, additional risk factors such as occupational hazards, family history, sun exposure, size, and personal history did not statistically improve the ROC AUCs. In summary, combined analysis of spectral and patient data can be significant for certain diagnostic tasks: patient data demonstrated the distribution of skin tumor incidence in different demographic groups, whereas tumors within each group were distinguished using the spectral differences. [ABSTRACT FROM AUTHOR]

In this study, we performed in vivo diagnosis of skin cancer based on implementation of a portable low‐cost spectroscopy setup combining analysis of Raman and autofluorescence spectra in the near‐infrared region (800–915 nm). We studied 617 cases of skin neoplasms (615 patients, 70 melanomas, 122 basal cell carcinomas, 12 squamous cell carcinomas and 413 benign tumors) in vivo with a portable setup. The studies considered the patients examined by GPs in local clinics and directed to a specialized Oncology Dispensary with suspected skin cancer. Each sample was histologically examined after excisional biopsy. The spectra were classified with a projection on latent structures and discriminant analysis. To check the classification models stability, a 10‐fold cross‐validation was performed. We obtained ROC AUCs of 0.75 (0.71–0.79; 95% CI), 0.69 (0.63–0.76; 95% CI) and 0.81 (0.74–0.87; 95% CI) for classification of a) malignant and benign tumors, b) melanomas and pigmented tumors and c) melanomas and seborrhoeic keratosis, respectively. The positive and negative predictive values ranged from 20% to 52% and from 73% to 99%, respectively. The biopsy ratio varied from 0.92:1 to 4.08:1 (at sensitivity levels from 90% to 99%). The accuracy of automatic analysis with the proposed system is higher than the accuracy of GPs and trainees, and is comparable or less to the accuracy of trained dermatologists. The proposed approach may be combined with other optical techniques of skin lesion analysis, such as dermoscopy‐ and spectroscopy‐based computer‐assisted diagnosis systems to increase accuracy of neoplasms classification. [ABSTRACT FROM AUTHOR]

• CNN analysis of Raman spectra significantly outperforms PLS-DA. • ROC AUC of 0.96 (0.94–0.97; 95% CI) was achieved for CNN discrimination of malignant and benign skin tumors based on Raman spectra analysis. • The performance of the proposed technique based on CNN analysis of Raman spectra is higher or comparable to the accuracy provided by trained dermatologists. Skin cancer is the most common malignancy in whites accounting for about one third of all cancers diagnosed per year. Portable Raman spectroscopy setups for skin cancer "optical biopsy" are utilized to detect tumors based on their spectral features caused by the comparative presence of different chemical components. However, low signal-to-noise ratio in such systems may prevent accurate tumors classification. Thus, there is a challenge to develop methods for efficient skin tumors classification. We compare the performance of convolutional neural networks and the projection on latent structures with discriminant analysis for discriminating skin cancer using the analysis of Raman spectra with a high autofluorescence background stimulated by a 785 nm laser. We have registered the spectra of 617 cases of skin neoplasms (615 patients, 70 melanomas, 122 basal cell carcinomas, 12 squamous cell carcinomas and 413 benign tumors) in vivo with a portable Raman setup and created classification models both for convolutional neural networks and projection on latent structures approaches. To check the classification models stability, a 10-fold cross-validation was performed for all created models. To avoid models overfitting, the data was divided into a training set (80% of spectral dataset) and a test set (20% of spectral dataset). The results for different classification tasks demonstrate that the convolutional neural networks significantly (p <0.01) outperforms the projection on latent structures. For the convolutional neural networks implementation we obtained ROC AUCs of 0.96 (0.94 – 0.97; 95% CI), 0.90 (0.85–0.94; 95% CI), and 0.92 (0.87 – 0.97; 95% CI) for classifying a) malignant vs benign tumors, b) melanomas vs pigmented tumors and c) melanomas vs seborrheic keratosis respectively. The performance of the convolutional neural networks classification of skin tumors based on Raman spectra analysis is higher or comparable to the accuracy provided by trained dermatologists. The increased accuracy with the convolutional neural networks implementation is due to a more precise accounting of low intensity Raman bands in the intense autofluorescence background. The achieved high performance of skin tumors classifications with convolutional neural networks analysis opens a possibility for wide implementation of Raman setups in clinical setting. [ABSTRACT FROM AUTHOR]