Utilizing deep learning for dermal matrix quality assessment on in vivo line-field confocal optical coherence tomography images.

BACKGROUND: Line-field confocal optical coherence tomography (LC-OCT) is an imaging technique providing non-invasive "optical biopsies" with an isotropic spatial resolution of ∼1 µm and deep penetration until the dermis. Analysis of obtained images is classically performed by experts, thus requiring long and fastidious training and giving operator-dependent results. In this study, the objective was to develop a new automated method to score the quality of the dermal matrix precisely, quickly, and directly from in vivo LC-OCT images. Once validated, this new automated method was applied to assess photo-aging-related changes in the quality of the dermal matrix. MATERIALS AND METHODS: LC-OCT measurements were conducted on the face of 57 healthy Caucasian volunteers. The quality of the dermal matrix was scored by experts trained to evaluate the fibers' state according to four grades. In parallel, these images were used to develop the deep learning model by adapting a MobileNetv3-Small architecture. Once validated, this model was applied to the study of dermal matrix changes on a panel of 36 healthy Caucasian females, divided into three groups according to their age and photo-exposition. RESULTS: The deep learning model was trained and tested on a set of 15 993 images. Calculated on the test data set, the accuracy score was 0.83. As expected, when applied to different volunteer groups, the model shows greater and deeper alteration of the dermal matrix for old and photoexposed subjects. CONCLUSIONS: In conclusion, we have developed a new method that automatically scores the quality of the dermal matrix on in vivo LC-OCT images. This accurate model could be used for further investigations, both in the dermatological and cosmetic fields.

Development and characterization of a 3D in vitro model mimicking acneic skin.

Acne is an inflammatory skin disease of the pilosebaceous unit, involving four essential factors: hyperseborrhoea combined to a modification of sebum composition, colonization by Cutibacterium (C.) acnes, hyperkeratinization and secreted inflammation. Understanding and mimicking compromised skin is essential to further develop appropriate therapeutic solutions. This study aimed to develop new in vitro 3D models mimicking acneic skin, by combining two main factors involved in the physiopathology, namely, altered sebum composition and C. acnes invasion. Normal human keratinocytes were first used to generate reconstructed human epidermis (RHE) that were then left untreated (control) or treated topically with a combination of both peroxidized squalene and C. acnes cultures. Once validated, this model considered relevant to mimic acneic skin, was further improved by using different phylotypes of C. acnes strains specifically isolated from healthy and acneic patients. While both phylotypes IB and II did not significantly alter RHE, C. acnes IA1 strains induce major acneic skin hallmarks such as hyperkeratinization, secreted inflammation and altered barrier function. Interestingly, these results are obtained independently of the origin of IA1 phylotypes (acneic vs. healthy patient), thus suggesting a role of the ecosystem in controlling C. acnes virulence in healthy skin. In conclusion, by combining two major factors involved in the physiopathology of acne, we (1) succeeded to design in vitro 3D models mimicking this skin disorder and (2) highlighted how C. acnes phylotypes can have an impact on epidermal physiology. These relevant models will be suitable for the substantiation of therapeutic molecules dedicated to acne treatment.

Comparison of line-field confocal optical coherence tomography images with histological sections: Validation of a new method for in vivo and non-invasive quantification of superficial dermis thickness.

BACKGROUND: Line-field confocal optical coherence tomography (LC-OCT) is an imaging technique providing "optical biopsies" of the skin in real time and non-invasively. At a center optical wavelength of 1.3 µm, this innovative technology can be applied to dermo-cosmetic product development due to both high image resolution (~2 µm) and sufficient penetration (~0.5 mm). Nevertheless, the precise dermal area analyzed with LC-OCT has never been identified. In this study, the objective was to compare LC-OCT images with histological sections of the same area, in order to validate a new method for in vivo and non-invasive quantification of superficial dermis thickness. Once validated, this standardized and quantitative method was used to assess age-related changes of the superficial dermis. MATERIALS AND METHODS: Ex vivo LC-OCT acquisitions and hematoxylin-eosin-safran staining were performed on a panel of four healthy Caucasian female volunteers. In vivo LC-OCT study of skin aging was performed on a panel of 37 healthy Caucasian female divided into five different age-groups. RESULTS: Comparison with histological sections revealed that LC-OCT images allow the visualization and the quantification of the superficial portion of papillary dermis. Applied to different age-group of volunteers, LC-OCT images show a constant decrease in this superficial dermis thickness with age. CONCLUSIONS: In conclusion, we have introduced LC-OCT as a novel technique for in vivo and non-invasive evaluation of superficial dermis thickness. This approach could be used in the future to demonstrate visually and quantitatively the capacity of a dermo-cosmetic active ingredient to renormalize the structural properties of the dermis.