Parametric Acne Severity (PAS) Score and Lesion Counts From Multi-Modality Facial Image Analysis Correlates Strongly with Investigator Assessment.

Variability in acne lesion counting and assessing global severity necessitates large sample sizes that increase trial costs. Lack of standardized measures for these outcomes precludes the conduct of meta-analyses needed to compare efficacy of acne treatments. The goal of this study was to evaluate objective measures of lesion counts and global severity using analysis of multimodal photography. An algorithm for counting lesions was trained and validated in 30 acne subjects and compared to parallel assessments by 2 expert raters. A composite of photographic data representative of acne lesion topography, erythema, and C Acnes fluorescence was used to generate a Parametric Acne Severity (PAS) score. No relationship was identified between lesion counts and IGA. The correlation coefficients between raters and the algorithm when compared per view for the inflammatory and non-inflammatory lesion counts were 0.77 (P=0.001) and 0.85 (P=0.001), respectively. The correlation coefficient between the raters’ IGA grades and the PAS score was 0.82 (P<0.05). These data demonstrate that the lesion counting, and PAS are objective measures that strongly correlate with investigator assessments. Inclusion of these measure in clinical trials may reduce variability, standardize outcomes, and provide insights into treatment effects on photographic parameters associated with acne. J Drugs Dermatol. 2021;20(6):642-647. doi:10.36849/JDD.6165.

Development and qualification of a machine learning algorithm for automated hair counting.

OBJECTIVE: Determining the amount of hair on the scalp has always been an important metric of patient satisfaction for hair growth and hair retention technologies. While simple in concept, this measurement is a difficult, resource intensive task for the dermatologist and the research scientist. Specifically, counting and measuring hair in phototrichogram images is very time consuming and labour intensive. Due to cost, often only a fraction of available images is manually analysed. There is a need for an automated method that can significantly increase speed and throughput while reducing the cost of counting and measuring hair in phototrichogram images. METHODS: Recent advances in machine learning and deep convolutional neural networks (deep learning) have led to a revolution in the analysis of image, video, speech, text and other sensor data. Image diagnostics have seen remarkable improvements with completely automated methods outperforming both human experts and human-engineered analysis methods. Deep learning methods can also provide speed and cost benefits. To enable use of a deep learning, we created a data set of 288 manually annotated phototrichogram images with marked location and length of each hair (the training dataset). We designed a custom neural network architecture and custom image processing algorithms to best utilize the available training data and to maximize performance for hair counting and length measurement. The performance of the algorithm was qualified by comparing hair count and length measurements to an independent ground truth method, the semi-manual Canfield's Hair Metrix method. RESULTS: Leveraging deep neural networks, we have developed capability to apply machine learning to reduce the time needed to acquire data from phototrichograms of patients' scalp from months to seconds. Our algorithm enables fast and fully automated hair counting and length measurement. The algorithm shows high agreement with human manually assisted analysis (ground truth). CONCLUSIONS: We have trained and deployed an algorithm utilizing this technology and have demonstrated the reproducibility, accuracy and speed of this algorithm that, once deployed, requires little to no recurring cost or manual intervention for its operation. The method allows fast analysis of large number of images, reducing study cost and significantly reducing study analysis time.

A Single-Centre, Randomized, Double-Blind, Placebo-Controlled Clinical Trial to Investigate the Efficacy and Safety of Minoxidil Topical Foam in Frontotemporal and Vertex Androgenetic Alopecia in Men.

BACKGROUND: 5% minoxidil formulations twice daily are effective in treating vertex male androgenetic alopecia (AGA); however, efficacy and safety data in frontotemporal regions are lacking. OBJECTIVES: To assess the efficacy of 5% minoxidil topical foam (5% MTF) in the frontotemporal region of male AGA patients after 24 weeks of treatment compared to placebo treatment and to the vertex region. METHODS: Seventy males with moderate AGA applied 5% MTF or placebo foam (plaTF) twice daily for 24 weeks in frontotemporal and vertex regions. Target area non-vellus hair count (TAHC) was the primary end point. RESULTS: Frontotemporal and vertex TAHC and target area cumulative non-vellus hair width (TAHW) showed similar responses to 5% MTF with significant increases up to week 16 compared to baseline (p < 0.001). After 24 weeks of treatment, frontotemporal TAHW increased significantly in the 5% MTF group compared to the plaTF group (p = 0.017), while TAHC showed a similar non-significant increase from baseline in both regions. At 24 weeks, 5% MTF users rated a significant improvement in scalp coverage for the frontotemporal (p = 0.016) and vertex areas (p = 0.027). CONCLUSIONS: 5% MTF twice a day promotes hair density and width in both frontotemporal and vertex regions in men with moderate stages of AGA. © 2015 S. Karger AG, Basel.

Auto-classification of acne lesions using multimodal imaging.

Differentiating inflammatory and non-inflammatory acne lesions and obtaining lesion counts is pivotal part of acne evaluation. Manual lesion counting has reliably demonstrated the clinical efficacy of anti-acne products for decades. However, maintaining assessment consistency within and across acne trials is an important consideration since lesion counting can be subjective to the individual evaluators, and the technique has not been rigorously standardized. VISIA-CR is a multi-spectral and multi-modal facial imaging system. It captures fluorescence images of Horn and Porphyrin, absorption images of Hemoglobin and Melanin, and skin texture and topography characterizing broad-spectrum polarized and non-polarized images. These images are analyzed for auto-classification of inflammatory and non-inflammatory acne lesion, measurement of erythema, and post-acne pigmentation changes. In this work the accuracy of this acne lesion auto-classification technique is demonstrated by comparing the auto-detected lesions counts with those counted by expert physicians. The accuracy is further substantiated by comparing and confirming the facial location and type of every auto-identified acne lesion with those identified by the physicians. Our results indicate a strong correlation between manual and auto-classified lesion counts (correlation coefficient >0.9) for both inflammatory and non inflammatory lesions This technology has the potential to eliminate the tedium of manual lesion counting, and provide an accurate, reproducible, and clinically relevant evaluation of acne lesions. As an aid to physicians it will allow development of a standardized technique for evaluating acne in clinical research, as well as accurately choosing treatment options for their patients according to the severity of a specific lesion type in clinical practice

A randomized, single-blind trial of 5% minoxidil foam once daily versus 2% minoxidil solution twice daily in the treatment of androgenetic alopecia in women.

BACKGROUND: Although twice-daily application of propylene glycol-containing 2% minoxidil topical solution (MTS) stimulates new hair growth, higher concentrations of minoxidil in a once-daily, propylene glycol-free formulation may improve efficacy and reduce unpleasant side effects. OBJECTIVE: We sought to compare the efficacy, safety, and acceptability and to show noninferiority of once-daily 5% minoxidil topical foam (MTF) with twice-daily 2% MTS in women with androgenetic alopecia. METHODS: A total of 113 women with androgenetic alopecia were randomized to 24 weeks of treatment with 5% MTF or 2% MTS. The primary efficacy parameter was change from baseline in nonvellus target area hair count at week 24. Secondary end points included change in nonvellus target area hair width, overall efficacy by global photographic review as assessed by treatment-blinded evaluators and the subject herself, adverse events, and participants' assessment of product aesthetics. RESULTS: After 24 weeks, women randomized to 5% MTF once daily showed noninferior target area hair count and target area hair width and experienced greater, but nonsignificant, improvements in target area hair count, target area hair width, and overall efficacy by global photographic review than those randomized to 2% MTS used twice daily. 5% MTF was significantly superior to 2% MTS in participants' agreement with "the treatment does not interfere with styling my hair" (P = .002). Women randomized to 5% MTF experienced significantly lower rates of local intolerance (P = .046) especially in pruritus and dandruff compared with 2% MTS. LIMITATION: Because of differences in the formulations tested, study participants were not blinded to treatment. CONCLUSIONS: Once-daily 5% MTF is noninferior and as effective for stimulating hair growth as twice-daily 2% MTS in women with androgenetic alopecia and is associated with several aesthetic and practical advantages.

Quantitative measurement of skin surface oiliness and shine using differential polarized images.

Excess amounts of skin surface oil can lead to adverse psychological consequences. Grease-spot photometry-based techniques measure sebum production rate. However, besides being tedious, these measurements are influenced by contact area, applied pressure, and time of application. Image analysis of polarized images has the potential to provide objective, quantitative information of skin oiliness. This study was designed to set up an imaging device for capturing and enhancing the changes in skin surface oiliness and to clinically and quantitatively, (via image analysis), evaluate varying levels of skin surface oiliness. Mineral oil was used to simulate skin surface oil. 40.5 µL of the mineral oil was applied within a two inch square area of interest on facial skin in twelve steps, from 1 to 40.5 µL, at 40% increments. The results indicate a strong correlation between the quantitative skin surface oiliness measurements and the clinical assessments. This sensitive technique has the potential to be utilized in future studies to evaluate product efficacies in reducing skin oiliness.

Effects of intrinsic aging and photodamage on skin dyspigmentation: an explorative study.

Photoaging is associated with increasing pigmentary heterogeneity and darkening of skin color. However, little is known about age-related changes in skin pigmentation on sun-protected areas. The aim of this explorative study was to measure skin color and dyspigmentation using image processing and to evaluate the reliability of these parameters. Twenty-four volunteers of three age-groups were included in this explorative study. Measurements were conducted at sun-exposed and sun-protected areas. Overall skin-color estimates were similar among age groups. The hyper- and hypopigmentation indices differed significantly by age groups and their correlations with age ranged between 0.61 and 0.74. Dorsal forearm skin differed from the other investigational areas (p<0.001). We observed an increase in dyspigmentation at all skin areas, including sun-protected skin areas, already in young adulthood. Associations between age and dyspigmentation estimates were higher compared to color parameters. All color and dyspigmentation estimates showed high reliability. Dyspigmentation parameters seem to be better biomarkers for UV damage than the overall color measurements.

Safety and efficacy of nonanimal stabilized hyaluronic acid for improvement of mouth corners.

BACKGROUND: Esthetic concern with downturned mouth corners ("mouth frown") is increasing in the aging baby-boomer generation. A new technique to offer structural support using the recently approved filler nonanimal stabilized hyaluronic acid (NASHA; Restylane, Q-med Inc., Uppsala, Sweden) is described. METHOD: Fifteen women with prominent downturned mouth corners met the inclusion criteria for the study. All were photographed before and at 1 week, 3 months, 4.5 months, and 6 months after treatment using a standardized clinical photographic system. NASHA was injected using a standardized technique with nerve block anesthesia to ensure patient comfort. RESULTS: All 15 women noted swelling, redness, and some local discomfort for several days after the injection. All noted an improvement in the downward angulation of their mouth corners at the first post-treatment visit, with at least partial improvement maintained through the 6-month post-treatment follow-up visit. CONCLUSIONS: NASHA injection to support the age-related downturn of lateral lip corners was effective, safe, and well tolerated in a small prospective study of middle-aged female subjects. Esthetic satisfaction was greatest in the first 3 months post-treatment, but 40% of subjects still noted improvement at the 6-month follow-up visit.