Fluorescence imaging modalities are currently a routine tool for the assessment of marker distribution within biological tissues, including monitoring of fluorescent photosensitizers (PSs) in photodynamic therapy (PDT). Conventional fluorescence imaging techniques provide en-face two-dimensional images, while depth-resolved techniques require complicated tomographic modalities. In this paper, we report on a cost-effective approach for the estimation of fluorophore localization depth based on dual-wavelength probing. Owing to significant difference in optical properties of superficial biotissues for red and blue ranges of optical spectra, simultaneous detection of fluorescence excited at different wavelengths provides complementary information from different measurement volumes. Here, we report analytical and numerical models of the dual-wavelength fluorescence imaging of PS-containing biotissues considering topical and intravenous PS administration, and demonstrate the feasibility of this approach for evaluation of the PS localization depth based on the fluorescence signal ratio. The results of analytical and numerical simulations, as well as phantom experiments, were translated to the in vivo imaging to interpret experimental observations in animal experiments, human volunteers, and clinical studies. The proposed approach allowed us to estimate typical accumulation depths of PS localization which are consistent with the morphologically expected values for both topical PS administration and intravenous injection.

The aim of the study was to assess the capabilities of combined application of dual-wavelength fluorescence visualization and contactless skin thermometry during photodynamic therapy monitoring (PDT) of basal cell cancer. Materials and Methods. The study was performed at the University Clinic of Privolzhsky Research Medical University (Nizhny Novgorod). Nine clinically, dermatoscopically, and histologically verified foci of basal cell skin cancer were exposed to PDT sessions (wavelength of 662 nm, light dose density of 150 J/cm(2)) with systemic application of chlorin-based photosensitizer Fotoditazin. A semiconductor laser system Latus-T (Russia) was employed for irradiation. Dual-wavelength fluorescence visualization and contactless thermometry with an IR pyrometer were used to monitor the PDT sessions. Results. The PDT sessions of nine foci of basal cell cancer were carried out under the control of fluorescence imaging and contactless thermometry. Photosensitizer photobleaching in all foci amounted to 40% signifying a percent of photosensitizer involved in the photodynamic reaction. It has been shown that the combined employment of dual-wavelength fluorescence monitoring and contactless thermometry during the PDT of basal cell skin cancer allows oncologists to control simultaneously the degree of photosensitizer photobleaching and the depth of the photodynamic effect in tissues, the extent of involving the mechanisms associated with hyperthermia as well as the correctness of the procedure conducting. In the course of 9-month dynamic follow-up after the treatment, no clinical and dermatoscopic signs of recurrence were found. Conclusion. A bimodal control of PDT enables the assessment of the correctness and efficacy of the procedure performance. The contactless control of tissue heating allows ensuring the temperature mode for hyperthermia realization, while the fluorescence monitoring makes it possible to evaluate the accumulation of the photosensitizer in the tumor and the depth of the PDT action as well as to predict the procedure efficacy based on the photobleaching data. The complementary use of these techniques allows the adjustment of the mode directly in the course of the PDT procedure. The acquisition of the sufficient statistical data on the combined monitoring will result in the development of a novel PDT protocol.

Artificial intelligence is a term used to describe computer technology in the modeling of intelligent behavior and critical thinking comparable to that of humans. To date, some of the first areas of medicine to be influenced by advances in artificial intelligence technologies will be those most dependent on imaging. These include ophthalmology, radiology, and dermatology. In connection with the emergence of numerous medical applications, scientists have formulated criteria for their assessment. This list included: clinical validation, regular application updates, functional focus, cost, availability of an information block for specialists and patients, compliance with the conditions of government regulation, and registration. One of the applications that meet all the requirements is the ProRodinki software package, developed for use by patients and specialists in the Russian Federation. Taking into account a widespread and rapidly developing competitive environment, it is necessary to soberly treat the resources of such applications, not exaggerating their capabilities and not considering them as a substitute for a specialist.

A comparative analysis of 3 AI-based smartphone applications for self-service skin cancer risk assessment: ProRodinki, Skinive and Skin Vision. Analysis consists of description of applications and its ways of work, and results, such as sensitivity and specificity, done on the base of the practical experiment conducted with processing 516 images of the skin neoplasms and pathologies confirmed by histological research via each app. Every application is unique and differs from each other by its principles or work, algorithms, user experience and design, and of course AI model and the set of input data that is analyzed by neural networks. Current research and practical experiment were made with focus on images processing and the app risk assessment for each of the image, other details and mole prescription information were set neutral. This leads to a conclusion that there is a lack of methodology for testing and analysis of different AI-based applications and services. Having such methodology, the comparison analysis results can be more objective and transparent.

Non-melanoma skin cancer (NMSC), which includes basal cell (BCC) and cutaneous squamous cell (cSCC) carcinomas in its structure, is the leading among malignant skin tumors (MST). Among the measures for the prevention of invasive forms of MST, the detection and treatment of early forms, which for cSCC include actinic keratosis (AK) and Bowen’s disease (BD) can be mentioned. The use of topical drugs is an alternative method in case of impossibility of surgical removal and radiation therapy of MST for the treatment of AK in the presence of «carcerization fields» and location in esthetically demanding areas. According to the literature, the use of diglycidyl methylphosphonate ointment gives a clinical positive effect in the treatment of MST. A series of cases of diglycidyl methylphosphonate drug use for the treatment of AK, BD and BCC under the control of dermatoscopy is described. Objective. To determine the effectiveness of the diglycidyl methylphosphonate ointment application for the treatment of AK, BD and BCC with low risk of recurrence in the presence of contraindications or patient’s refusal from treatment by method of choice in accordance with the current clinical guidelines under the control of dermatoscopy. Material and methods. The study was conducted on the basis of the PRMU’s center of diagnosis and treatment of skin tumors. Dynamic clinical and dermatoscopic changes of 5 elements of AK, 3 elements of BD and 1 element of BCC on the therapy with diglycidyl methylphosphonate ointment are described. Results. The use of diglycidyl methylphosphonate ointment for the treatment of AK, BD and BCC elements has shown good clinical and cosmetic results. Conclusion. Dermatoscopy is an additional objective method of evaluating the effectiveness of AK, BD and BCC topical therapy. Dynamic monitoring for residual dermatoscopic signs is recommended in case of pronounced clinical effect from the diglycidyl methylphosphonate ointment use for the treatment of AK and BD.

BACKGROUND: In recent years, neural networks have become an integral part of many fields, including medicine. However, the effectiveness of these models directly depends on the quality of the training data on which they are trained. Creating and maintaining a high-quality training dataset is a critical step in the development process of neural networks. AIM: The aim of the research is to identify the key characteristics of the training database for the neural network that influence its subsequent sensitivity and specificity. MATERIALS AND METHODS: A database of verified images of skin neoplasms was created to train a neural network to implement it in large-scale screening examinations. In the first phase of the study, a database was created to train a neural network to classify images of skin neoplasms (NSCa). Between 2017 and 2019, 7,680 digital images were collected from 6,892 patients with verified diagnoses: 5,316 (69,22%) confirmed by pathological examination, and 2,364 (30,78%)) confirmed clinically and dermatoscopically. A dataset containing 7,680 verified clinical images of skin neoplasms was created, and 1,680 images constituted the test sample for analyzing the model's effectiveness. The performance indicators of NSCa were as follows: sensitivity (Se): 70.47%; specificity (Sp): 79.86%; diagnostic accuracy (Ac): 74.68%. Due to the low sensitivity and specificity rates, the following steps were taken: (1) an additional round of training was conducted; (2) image quality control methods were developed; (3) a detection neural network was created, and (4) a new neural (NSCb) was established. RESULTS: The neural network, trained on a verified dataset of clinical images of benign and malignant skin neoplasms and having undergone multiple rounds of training, operates with a sensitivity of 85.32–86.97% and a specificity of 87.59–88.92%. These rates exceed the sensitivity and specificity of skin neoplasm diagnoses made by non-oncological specialists using the naked eye, allowing for the use of this method in population screening. Following the retraining of the neural network and the establishment of NSCb, the creation of neural network, and the development of image quality control methods, an increase in the sensitivity and specificity of the neural network's performance was observed. CONCLUSION: The use of artificial intelligence as a physician's assistant imposes quite high requirements on the performance parameters of the neural network. Mechanical learning, even on a large volume of verified data, did not achieve the desired results. The sequential work aimed at improving the parameters involved conducting an additional round of training, developing image quality control methods, and creating a detection neural network and a classification neural network. As a result, the trained neural network operates with a sensitivity of 85.32% to 86.97% and a specificity of 87.59% to 88.92%, which has enabled the use of the trained neural network as a tool for population screening.