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.

We present a three-dimensional (3-D) computational method to detect soft tissue sarcomas with the goal of automatic surgical margin assessment based on optical coherence tomography (OCT) images. Three parameters are investigated and quantified from OCT images as the indicators for the tissue diagnosis including the signal attenuation (A-line slope), the standard deviation of the signal fluctuations (speckles), and the exponential decay coefficient of its spatial frequency spectrum. The detection of soft tissue sarcomas relies on the combination of these three parameters, which are related to the optical attenuation characteristics and the structural features of the tissue. Pilot experiments were performed on ex vivo human tissue samples with homogeneous pieces (both normal and abnormal) and tumor margins. Our results demonstrate the feasibility of this computational method in the differentiation of soft tissue sarcomas from normal tissues. The features of A-line-based detection and 3-D quantitative analysis yield promise for a computer-aided technique capable of accurately and automatically identifying resection margins of soft tissue sarcomas during surgical treatment.

The present paper studies the applicability of a portable cost‐effective spectroscopic system for the optical screening of skin tumors. in vivo studies of Raman scattering and autofluorescence (AF) of skin tumors with the 785 nm excitation laser in the near‐infrared region included malignant melanoma, basal cell carcinoma and various types of benign neoplasms. The efficiency of the portable system was evaluated by comparison with a highly sensitive spectroscopic system and with the diagnosis accuracy of a human oncologist. Partial least square analysis of Raman and AF spectra was performed; specificity and sensitivity of various skin oncological pathologies detection varied from 78.9% to 100%. Hundred percent accuracy of benign and malignant skin tumors differentiation is possible only with a combined analysis of Raman and AF signals.

The differentiation of skin melanomas and basal cell carcinomas (BCCs) was demonstrated based on combined analysis of Raman and autofluorescence spectra stimulated by visible and NIR lasers. It was ex vivo tested on 39 melanomas and 40 BCCs. Six spectroscopic criteria utilizing information about alteration of melanin, porphyrins, flavins, lipids, and collagen content in tumor with a comparison to healthy skin were proposed. The measured correlation between the proposed criteria makes it possible to define weakly correlated criteria groups for discriminant analysis and principal components analysis application. It was shown that the accuracy of cancerous tissues classification reaches 97.3% for a combined 6-criteria multimodal algorithm, while the accuracy determined separately for each modality does not exceed 79%. The combined 6-D method is a rapid and reliable tool for malignant skin detection and classification.

Malignant skin tumors of different types were studied in vivo using optical coherence tomography (OCT), backscattering (BS), and Raman spectroscopy (RS). A multimodal method is proposed for early cancer detection based on complex analysis of OCT images by their relative alteration of scattered-radiation spectral intensities between malignant and healthy tissues. An increase in average accuracy of diagnosis was observed for a variety of cancer types (9% sensitivity, 8% specificity) by a multimodal RS-BS-OCT system in comparison with any of the three methods used separately. The proposed approach equalizes the processing rates for all methods and allows for simultaneous imaging and classification of tumors.