Background Cellulite is a common physiological condition of dermis, epidermis, and subcutaneous tissues experienced by 85 to 98% of the post-pubertal females in developed countries. Infrared (IR) thermography combined with artificial intelligence (AI)based automated image processing can detect both early and advanced cellulite stages and open up the possibility of reliable diagnosis. Although the cellulite lesions may have various levels of severity, the quality of life of every woman, both in the physical and emotional sphere, is always an individual concern and therefore requires patient-oriented approach. Objectives The purpose of this work was to elaborate an objective, fast, and cost-effective method for automatic identification of different stages of cellulite based on IR imaging that may be used for prescreening and personalization of the therapy. Materials and methods In this study, we use custom-developed image preprocessing algorithms to automatically select cellulite regions and combine a total of 9 feature extraction methods with 9 different classification algorithms to determine the efficacy of cellulite stage recognition based on thermographic images taken from 212 female volunteers aged between 19 and 22. Results A combination of histogram of oriented gradients (HOG) and artificial neural network (ANN) enables determination of all stages of cellulite with an average accuracy higher than 80%. For primary stages of cellulite, the average accuracy achieved was more than 90%. Conclusions The implementation of computer-aided, automatic identification of cellulite severity using infrared imaging is feasible for reliable diagnosis. Such a combination can be used for early diagnosis, as well as monitoring of cellulite progress or therapeutic outcomes in an objective way. IR thermography coupled to AI sets the vision towards their use as an effective tool for complex assessment of cellulite pathogenesis and stratification, which are critical in the implementation of IR thermographic imaging in predictive, preventive, and personalized medicine (PPPM). Keywords Cellulite. Artificial intelligence. Infrared thermography. Predictive preventive personalized medicine. Prediction and health monitoring Abbreviations ANN Artificial neural network AUC Area under the curve BRISK Binary robust invariant scalable keypoints Cont Contour-based feature DT Decision tree Electronic supplementary material The online version of this article (

Mobile phones have become an indispensable utility to modern society, with international use increasing dramatically each year. The GSM signal operates at 900MHz, 1800MHz and 2250MHz, may potentially cause harm to human tissue. Yet there is no in silico model to aid design these devices to protect from causing potential thermal effect. Here we present a model of sources of heating in a mobile phone device with experimental verification during the phone call. We have developed this mobile phone thermal model using first principles on COMSOL® Multiphysics modelling platform to simulate heating effect in human auricle region due to mobile phone use. In particular, our model considered both radiative and non-radiative heating from components such as the lithium ion battery, CPU circuitry and the antenna. The model showed the distribution and effect of the heating effect due to mobile phone use and considered impact of battery discharge rate, battery capacity, battery cathode material, biological tissue distance, antenna radio-wave frequency and intensity. Furthermore, the lithium ion battery heating was validated during experiments using temperature sensors with an excellent agreement between simulated and experimental data (<1% variation). Mobile phone heating during a typical call has also been simulated and compared with experimental infrared thermographic imaging. Importantly, we found that 1800MHz frequency of data transmission showed the highest temperature increase in the fat/water phantom used in this simulation. We also successfully compared heating distribution in human auricle region during mobile phone use with clinical thermographic images with reasonable qualitative and quantitative agreements. In summary, our model provides a foundation to conceive thermal and other physical effects caused by mobile phone use and allow for the understanding of potential negative health effects thus supporting and promoting personalized and preventive medicine using thermography.