A new procedure, free from human assessment, that automatically grades some facial skin signs in men from selfie pictures. Application to changes induced by a severe aerial chronic urban pollution

OBJECTIVE

These were two folds: at first, to develop an automatic grading system specifically dedicated to some facial signs of men, similar to the one previously validated on women of different ethnic ancestry and second, to assess its potential in detecting and grading the possible impacts of a severe aerial urban pollution on some facial signs of Chinese men.

METHODS

In both studies, selfie images were obtained from differently aged men. Nine facial signs were automatically graded through a specific A.I-based algorithm and clinically assessed by a panel of experts and dermatologists. Selfie pictures were taken from individual smartphones of variable optical properties. The first study, designed for developing an automatic grading system, involved three comparable cohorts of men from three different regional ancestries (African, Asian, Caucasian, 110 each) the selfie images of which were acquired under four different lighting conditions. As a second use case study, the facial signs of two cohorts of Chinese men (101 and 100, each), differently aged, regularly exposed to very different aerial urban pollution conditions (UP) were analysed by the same algorithm, selfies being taken under only one lighting condition.

RESULTS

-The new automatic grading system of facial signs suits well to men, showing comparable results than that the one dedicated to women and provides data in close agreement with experts' assessments. -In both cases (expert's or automatic methodology), the accuracy of the scores appeared ethnic-dependent. -The applied case confirmed previous results obtained clinically, that is, that many facial signs were found of an increased severity among men exposed to a severe urban pollution, as compared to those living in a less polluted city. -In both studies, statistical agreements between the automatic grading system and expert's assessments were reached. In some facial signs, the automatic grading system seems offering a slightly better accuracy than the assessments made by the experts.

CONCLUSION

Apart from some minor limitations, this A.I-based automatic grading system, free from human intervention, performed as well as the one previously developed in women, in close agreement with expert's assessments. In epidemiological studies, this system offers an easy, fast, affordable and confidential approach in the detection and quantification of male facial signs.

Spherical wavelet transform for ODF sharpening

The choice of local HARDI reconstruction technique is crucial for discerning multiple fiber orientations, which is itself of substantial importance for tractography, and reliable and accurate assessment of white matter fiber geometry. Due to the complexity of the diffusion process and its milieu, distinct diffusion compartments can have different frequency signatures, making the HARDI signal spread over multiple frequency bands. Therefore, we put forth the idea of multiscale analysis with localized basis functions, ensuring that different frequency ranges are probed. With the aim of truthful recovery of fiber orientations, we reconstruct the orientation distribution function (ODF), by incorporating a spherical wavelet transform (SWT) into the Funk-Radon transform. First, we apply and validate our proposed SWT method on real physical phantoms emulating fiber bundle crossings. Then, we apply the SWT method to a real brain data set. The analysis of the real data set suggests that different angular frequencies may capture different information, thus stressing the importance of multiscale analysis. For both phantom and real data, we compare the SWT reconstruction with state-of-the-art q-ball imaging and spherical deconvolution reconstruction methods. We demonstrate the algorithm efficiency in diffusion ODF denoising and sharpening that is of particular importance for applications to fiber tracking (especially for probabilistic approaches), and brain connectome mapping. Also, the algorithm results in considerable data compression that could prove beneficial in applications to fiber bundle segmentation, and for HARDI based white matter morphometry methods.