Novel techniques for enhancement and segmentation of acne vulgaris lesions

Attention Mechanism Guided Deep Regression Model for Acne Severity Grading

Acne vulgaris is the common form of acne that primarily affects adolescents, characterised by an eruption of inflammatory and/or non-inflammatory skin lesions. Accurate evaluation and severity grading of acne play a significant role in precise treatment for patients. Manual acne examination is typically conducted by dermatologists through visual inspection of the patient skin and counting the number of acne lesions. However, this task costs time and requires excessive effort by dermatologists. This paper presents automated acne counting and severity grading method from facial images. To this end, we develop a multi-scale dilated fully convolutional regressor for density map generation integrated with an attention mechanism. The proposed fully convolutional regressor module adapts UNet with dilated convolution filters to systematically aggregate multi-scale contextual information for density maps generation. We incorporate an attention mechanism represented by prior knowledge of bounding boxes generated by Faster R-CNN into the regressor model. This attention mechanism guides the regressor model on where to look for the acne lesions by locating the most salient features related to the understudied acne lesions, therefore improving its robustness to diverse facial acne lesion distributions in sparse and dense regions. Finally, integrating over the generated density maps yields the count of acne lesions within an image, and subsequently the acne count indicates the level of acne severity. The obtained results demonstrate improved performance compared to the state-of-the-art methods in terms of regression and classification metrics. The developed computer-based diagnosis tool would greatly benefit and support automated acne lesion severity grading, significantly reducing the manual assessment and evaluation workload.

Inhibitory Effect of Quercetin on Propionibacterium acnes-induced Skin Inflammation

Quercetin is a well-known antioxidant and a plant polyphenolic of flavonoid group found in many fruits, leaves, and vegetables. Propionibacterium acnes is a key skin pathogen involved in the progression of acne inflammation. Although quercetin has been applied to treat various inflammatory diseases, the effects of quercetin on P. acnes-induced skin inflammation have not been explored. This study investigated the effects of quercetin on P. acnes-induced inflammatory skin disease in vitro and in vivo. The results showed that quercetin suppressed the production of pro-inflammatory cytokines in P. acnes-stimulated HaCaT, THP-1 and RAW 264.7 cells. Additionally, quercetin reduced the production of TLR-2 and the phosphorylation of p38, ERK and JNK MAPKs in P. acnes-stimulated HaCaT and THP-1 cells. It also suppressed MMP-9 mRNA levels in two cell lines exposed to P. acnes in vitro. In the case of in vivo, P. acnes was intradermally injected into the ears of mice and it resulted in cutaneous erythema, swelling, and a granulomatous response. Treatment with quercetin markedly reduced ear thickness and swelling. These results suggested that quercetin can be a potential therapeutic agent against P. acnes-induced skin inflammation and may have diverse pharmaceutical and cosmetics applications.

Development and accuracy of an artificial intelligence algorithm for acne grading from smartphone photographs

We developed an artificial intelligence algorithm (AIA) for smartphones to determine the severity of facial acne using the GEA scale and to identify different types of acne lesion (comedonal, inflammatory) and postinflammatory hyperpigmentation (PIHP) or residual hyperpigmentation. Overall, 5972 images (face, right and left profiles) obtained with smartphones (IOS and/or Android) from 1072 acne patients were collected. Three trained dermatologists assessed the acne severity for each patient. One acne severity grade per patient (grade given by the majority of the three dermatologists from the two sets of three images) was used to train the algorithm. Acne lesion identification was performed from a subgroup of 348 images using a tagging tool; tagged images served to train the algorithm. The algorithm evolved and was adjusted for sensibility, specificity and correlation using new images. The correlation between the GEA grade and the quantification and qualification of acne lesions both by the AIA and the experts for each image were evaluated for all AIA versions. At final version 6, the GEA grading provided by AIA reached 68% and was similar to that provided by the dermatologists. Between version 4 and version 6, AIA improved precision results multiplied by 1.5 for inflammatory lesions, 2.5 for non-inflammatory lesions and by 2 for PIHP; recall was improved by 2.6, 1.6 and 2.7. The weighted average of precision and recall or F1 score was 84% for inflammatory lesions, 61% for non-inflammatory lesions and 72% for PIHP.

Prioritizing treatment outcomes: How people with acne vulgaris decide if their treatment is working

OBJECTIVE

To collect information about how people with acne make day-to-day decisions concerning the effectiveness of their treatment.

METHODS

Between May and August 2013, an optional question was embedded in the James Lind Alliance Acne Priority Setting Partnership's online survey to collect treatment uncertainties. The question asked people with acne to "Tell us in your own words how you decide if your treatment has been effective."

RESULTS

A total of 742 respondents specified at least one outcome or means of assessing change (outcome measure). Fewer spots were the most commonly cited outcome, identified by 272 respondents (36.7%). Other frequently mentioned outcomes were in descending order: less redness (19.4%), reduction in spot size (12.1%), and less pain/discomfort (11.4%). Signs were much more commonly used than symptoms and surrogate outcomes such as changes in aspects of life quality were infrequently mentioned. Visual inspection of the skin was the most widely adopted outcome measure (16.3%).

CONCLUSIONS

Although the most frequently used methods map well onto the outcome measures adopted in the majority of acne trials, namely physician-assessed changes in lesion counts and global acne severity, people with acne often take into account several factors that cannot be assessed by a third party at a single point in time. The minimal use of changes in psychosocial wellbeing and mood may reflect that these are regarded as secondary consequences of improvements in appearance. The robustness of these findings now requires independent evaluation. If confirmed, they could form the basis of a new patient-reported outcome measure.