Effect of NFX-179 MEK inhibitor on cutaneous neurofibromas in persons with neurofibromatosis type 1.

This phase 2a trial investigated the efficacy of NFX-179 Topical Gel, a metabolically labile MEK inhibitor, in the treatment of cutaneous neurofibromas (cNFs) in neurofibromatosis type 1. Forty-eight participants were randomized to four treatment arms: NFX-179 Topical Gel 0.05%, 0.15%, and 0.5% or vehicle applied once daily to five target cNFs for 28 days. Treatment with NFX-179 Topical Gel resulted in a dose-dependent reduction in p-ERK levels in cNFs at day 28, with a 47% decrease in the 0.5% NFX-179 group compared to the vehicle (P = 0.0001). No local or systemic toxicities were observed during the treatment period, and systemic concentrations of NFX-179 remained below 1 ng/ml. In addition, 20% of cNFs treated with 0.5% NFX-179 Topical Gel showed a ≥50% reduction in volume compared to 6% in the vehicle group by ruler measurement with calculated volume (P = 0.021). Thus, NFX-179 Topical Gel demonstrated significant inhibition of MEK in cNF with excellent safety and potential therapeutic benefit.

Combining public datasets for automated tooth assessment in panoramic radiographs.

OBJECTIVE: Panoramic radiographs (PRs) provide a comprehensive view of the oral and maxillofacial region and are used routinely to assess dental and osseous pathologies. Artificial intelligence (AI) can be used to improve the diagnostic accuracy of PRs compared to bitewings and periapical radiographs. This study aimed to evaluate the advantages and challenges of using publicly available datasets in dental AI research, focusing on solving the novel task of predicting tooth segmentations, FDI numbers, and tooth diagnoses, simultaneously. MATERIALS AND METHODS: Datasets from the OdontoAI platform (tooth instance segmentations) and the DENTEX challenge (tooth bounding boxes with associated diagnoses) were combined to develop a two-stage AI model. The first stage implemented tooth instance segmentation with FDI numbering and extracted regions of interest around each tooth segmentation, whereafter the second stage implemented multi-label classification to detect dental caries, impacted teeth, and periapical lesions in PRs. The performance of the automated tooth segmentation algorithm was evaluated using a free-response receiver-operating-characteristics (FROC) curve and mean average precision (mAP) metrics. The diagnostic accuracy of detection and classification of dental pathology was evaluated with ROC curves and F1 and AUC metrics. RESULTS: The two-stage AI model achieved high accuracy in tooth segmentations with a FROC score of 0.988 and a mAP of 0.848. High accuracy was also achieved in the diagnostic classification of impacted teeth (F1 = 0.901, AUC = 0.996), whereas moderate accuracy was achieved in the diagnostic classification of deep caries (F1 = 0.683, AUC = 0.960), early caries (F1 = 0.662, AUC = 0.881), and periapical lesions (F1 = 0.603, AUC = 0.974). The model's performance correlated positively with the quality of annotations in the used public datasets. Selected samples from the DENTEX dataset revealed cases of missing (false-negative) and incorrect (false-positive) diagnoses, which negatively influenced the performance of the AI model. CONCLUSIONS: The use and pooling of public datasets in dental AI research can significantly accelerate the development of new AI models and enable fast exploration of novel tasks. However, standardized quality assurance is essential before using the datasets to ensure reliable outcomes and limit potential biases.

Long-term safety and effectiveness of roflumilast cream 0.3% in adults with chronic plaque psoriasis: A 52-week, phase 2, open-label trial.

BACKGROUND: Efficacy and/or safety profiles limit topical psoriasis treatments. OBJECTIVE: Evaluate long-term effects of once-daily roflumilast cream 0.3% in patients with psoriasis. METHODS: In this open-label phase 2 trial, adult patients (N = 332) with psoriasis who completed the phase 2b parent trial or were newly enrolled applied roflumilast once-daily for 52 weeks. Safety and effectiveness were assessed. RESULTS: Overall, 244 patients (73.5%) completed the trial; 13 patients (3.9%) discontinued due to adverse events (AEs) and 3 (0.9%) due to lack of efficacy. Twelve patients (3.6%) reported treatment-related AEs; none were serious. ≥97% of patients had no irritation. No tachyphylaxis was observed with 44.8% of the patients achieving Investigator Global Assessment (IGA) Clear or Almost Clear at Week 52. LIMITATIONS: Intertriginous-IGA and Psoriasis Area and Severity Index (PASI) were not evaluated in all patients. CONCLUSIONS: In this long-term trial, once-daily roflumilast cream was well-tolerated and efficacious up to 64 weeks in patients in the earlier trial, suggesting it is suitable for chronic treatment, including the face and intertriginous areas.

Intra-oral scan segmentation using deep learning.

OBJECTIVE: Intra-oral scans and gypsum cast scans (OS) are widely used in orthodontics, prosthetics, implantology, and orthognathic surgery to plan patient-specific treatments, which require teeth segmentations with high accuracy and resolution. Manual teeth segmentation, the gold standard up until now, is time-consuming, tedious, and observer-dependent. This study aims to develop an automated teeth segmentation and labeling system using deep learning. MATERIAL AND METHODS: As a reference, 1750 OS were manually segmented and labeled. A deep-learning approach based on PointCNN and 3D U-net in combination with a rule-based heuristic algorithm and a combinatorial search algorithm was trained and validated on 1400 OS. Subsequently, the trained algorithm was applied to a test set consisting of 350 OS. The intersection over union (IoU), as a measure of accuracy, was calculated to quantify the degree of similarity between the annotated ground truth and the model predictions. RESULTS: The model achieved accurate teeth segmentations with a mean IoU score of 0.915. The FDI labels of the teeth were predicted with a mean accuracy of 0.894. The optical inspection showed excellent position agreements between the automatically and manually segmented teeth components. Minor flaws were mostly seen at the edges. CONCLUSION: The proposed method forms a promising foundation for time-effective and observer-independent teeth segmentation and labeling on intra-oral scans. CLINICAL SIGNIFICANCE: Deep learning may assist clinicians in virtual treatment planning in orthodontics, prosthetics, implantology, and orthognathic surgery. The impact of using such models in clinical practice should be explored.

Once-daily roflumilast foam 0.3% for scalp and body psoriasis: a randomized, double-blind, vehicle-controlled phase IIb study.

BACKGROUND: Scalp psoriasis affects most patients with psoriasis, but it can be difficult to treat. OBJECTIVES: To evaluate the efficacy and safety of once-daily roflumilast foam 0.3% on scalp and body psoriasis. METHODS: In a phase IIb randomized controlled trial, adults and adolescents aged ≥ 12 years with scalp and body psoriasis were randomized (2 : 1) to roflumilast foam 0.3% or vehicle for 8 weeks. The primary efficacy endpoint was scalp Investigator Global Assessment (S-IGA) success (score of 'clear' or 'almost clear' plus ≥ 2-grade improvement from baseline) at week 8. Safety and tolerability were also evaluated. RESULTS: Significantly more roflumilast-treated patients (59.1%) than vehicle-treated patients (11.4%) achieved S-IGA success at week 8 (P < 0.001); differences favoured roflumilast as early as the first postbaseline visit at week 2 (P < 0.001). Significant improvements were also seen for secondary endpoints, including body IGA success, Scalp Itch Numeric Rating Scale and the Psoriasis Scalp Severity Index. The safety of roflumilast was generally similar to vehicle. Patients treated with roflumilast experienced low rates of treatment-emergent adverse events (AEs), with few discontinuations due to an AE. Few patients with skin of colour (11%) and few adolescents (0.7%) were included. CONCLUSIONS: The results support the further development of roflumilast foam for treating scalp and body psoriasis.

Efficacy of Roflumilast Foam, 0.3%, in Patients With Seborrheic Dermatitis: A Double-blind, Vehicle-Controlled Phase 2a Randomized Clinical Trial.

Importance: Current topical treatment options for seborrheic dermatitis are limited by efficacy and/or safety. Objective: To assess safety and efficacy of roflumilast foam, 0.3%, in adult patients with seborrheic dermatitis affecting the scalp, face, and/or trunk. Design, Setting, and Participants: This multicenter (24 sites in the US and Canada) phase 2a, parallel group, double-blind, vehicle-controlled clinical trial was conducted between November 12, 2019, and August 21, 2020. Participants were adult (aged ≥18 years) patients with a clinical diagnosis of seborrheic dermatitis for a 3-month or longer duration and Investigator Global Assessment (IGA) score of 3 or greater (at least moderate), affecting 20% or less body surface area, including scalp, face, trunk, and/or intertriginous areas. Data analysis was performed from September to October 2020. Interventions: Once-daily roflumilast foam, 0.3% (n = 154), or vehicle foam (n = 72) for 8 weeks. Main Outcomes and Measures: The main outcome was IGA success, defined as achievement of IGA score of clear or almost clear plus 2-grade improvement from baseline, at week 8. Secondary outcomes included IGA success at weeks 2 and 4; achievement of erythema score of 0 or 1 plus 2-grade improvement from baseline at weeks 2, 4, and 8; achievement of scaling score of 0 or 1 plus 2-grade improvement from baseline at weeks 2, 4, and 8; change in Worst Itch Numeric Rating Scale (WI-NRS) score from baseline; and WI-NRS success, defined as achievement of 4-point or greater WI-NRS score improvement in patients with baseline WI-NRS score of 4 or greater. Safety and tolerability were also assessed. Results: A total of 226 patients (mean [SD] age, 44.9 [16.8] years; 116 men, 110 women) were randomized to roflumilast foam (n = 154) or vehicle foam (n = 72). At week 8, 104 (73.8%) roflumilast-treated patients achieved IGA success compared with 27 (40.9%) in the vehicle group (P < .001). Roflumilast-treated patients had statistically significantly higher rates of IGA success vs vehicle at week 2, the first time point assessed. Mean (SD) reductions (improvements) on the WI-NRS at week 8 were 59.3% (52.5%) vs 36.6% (42.2%) in the roflumilast and vehicle groups, respectively (P < .001). Roflumilast was well tolerated, with the rate of adverse events similar to that of the vehicle foam. Conclusions and Relevance: The results from this phase 2a randomized clinical trial of once-daily roflumilast foam, 0.3%, demonstrated favorable efficacy, safety, and local tolerability in the treatment of erythema, scaling, and itch caused by seborrheic dermatitis, supporting further investigation as a nonsteroidal topical treatment. Trial Registration: ClinicalTrials.gov Identifier: NCT04091646.

Topical Isotretinoin (TMB-001) Treatment for 12 Weeks Did Not Result in Clinically Relevant Laboratory Abnormalities in Participants with Congenital Ichthyosis in the Phase 2b CONTROL Study.

INTRODUCTION: Treatment with oral retinoids can be effective in patients with congenital ichthyosis (CI) but may be associated with clinically significant laboratory changes. In this Phase 2b CONTROL study analysis, we characterize the effects of TMB-001, a novel topical isotretinoin formulation, on laboratory values in participants with X-linked recessive (XLRI) and autosomal recessive lamellar (ARCI-LI) ichthyosis at 12 weeks. METHODS: A randomized, double-blind, vehicle-controlled, Phase 2b study was conducted with participants ≥ 9 years of age with confirmed XLRI and ARCI-LI. Participants were randomized 1:1:1 and stratified by CI subtype to receive TMB-001 0.05%:TMB-001 0.1%:vehicle twice daily for 12 weeks. Laboratory analyses were performed at screening and Week 12. RESULTS: Among 33 enrolled participants (TMB-001 0.05% n = 11, TMB-001 0.1% n = 10, and vehicle n = 12), 52% had ARCI-LI and 48% had XLRI. At 12 weeks, there were single reports of anemia, neutropenia, leukopenia, lymphocytosis, and leukocytosis after vehicle treatment; neutropenia was reported in one participant receiving TMB-001 0.1%. There were single reports of abnormal biochemistry values-liver enzymes, creatinine, urea nitrogen, hyperkalemia, and hyperproteinemia-across treatment cohorts. Non-fasting hyperglycemia was observed in three participants receiving TMB-001 0.1% and one participant receiving vehicle. Urinalysis abnormalities reported in > 1 participant included urobilinogen (TMB-001 0.1% n = 2, vehicle n = 2), protein (TMB-001 0.1% n = 3, vehicle n = 2), and leukocyte esterase (TMB-001 0.1% n = 2). Laboratory parameter changes were asymptomatic and did not require study discontinuation or drug withdrawal. CONCLUSION: There were no clinically significant laboratory changes in participants receiving TMB-001 isotretinoin ointment through 12 weeks of treatment, which differs from reported results for systemic isotretinoin. TRIAL REGISTRATION: NCT04154293.

Positional assessment of lower third molar and mandibular canal using explainable artificial intelligence.

OBJECTIVE: The aim of this study is to automatically assess the positional relationship between lower third molars (M3i) and the mandibular canal (MC) based on the panoramic radiograph(s) (PR(s)). MATERIAL AND METHODS: A total of 1444 M3s were manually annotated and labeled on 863 PRs as a reference. A deep-learning approach, based on MobileNet-V2 combination with a skeletonization algorithm and a signed distance method, was trained and validated on 733 PRs with 1227 M3s to classify the positional relationship between M3i and MC into three categories. Subsequently, the trained algorithm was applied to a test set consisting of 130 PRs (217 M3s). Accuracy, precision, sensitivity, specificity, negative predictive value, and F1-score were calculated. RESULTS: The proposed method achieved a weighted accuracy of 0.951, precision of 0.943, sensitivity of 0.941, specificity of 0.800, negative predictive value of 0.865 and an F1-score of 0.938. CONCLUSION: AI-enhanced assessment of PRs can objectively, accurately, and reproducibly determine the positional relationship between M3i and MC. CLINICAL SIGNIFICANCE: The use of such an explainable AI system can assist clinicians in the intuitive positional assessment of lower third molars and mandibular canals. Further research is required to automatically assess the risk of alveolar nerve injury on panoramic radiographs.

Characteristics and outcomes for participants with congenital ichthyosis who responded to treatment with the topical isotretinoin formulation TMB-001: results from the Phase IIb CONTROL study.

BACKGROUND: Emollients and keratolytics are frequently used to manage symptoms of congenital ichthyosis (CI). Systemic retinoid treatment is complicated by teratogenicity and dose-limiting adverse effects. OBJECTIVES: This analysis from the randomized Phase IIb CONTROL study investigated the characteristics of participants who responded to treatment with TMB-001, a novel topical isotretinoin ointment formulation. METHODS: Participants ≥ 9 years of age with genetically confirmed CI and ≥ 2 (out of 4) Visual Index for Ichthyosis Severity (VIIS) assessment areas with ≥ 3 scaling score were randomized 1 : 1 : 1 to TMB-001 0.05%, TMB-001 0.1% or vehicle, twice daily for 12 weeks. Efficacy endpoints included the proportion of participants with ≥ 50% reduction in VIIS-scaling (VIIS-50) compared with baseline and ≥ 2-grade reduction in Investigator's Global Assessment (IGA)-scaling score compared with baseline. Changes in body surface area (BSA) involvement, Dermatology Life Quality Index (DLQI) scores and Itch-Numeric Rating Scale (I-NRS) scores were assessed. RESULTS: Among the 33 participants (11 randomized to TMB-001 0.05%, 10 to TMB-001 0.1% and 12 to vehicle), median age was 29 years (range 9-80), and most were male (64%) and White (79%). Baseline demographics were generally similar among participants who did or did not achieve TMB-001 treatment success. Participants who had lower mean BSA involvement and higher DLQI and I-NRS scores at baseline were more likely to achieve VIIS-50. Similarly, higher baseline DLQI and I-NRS scores were associated with IGA response; BSA involvement was similar for IGA responders vs. nonresponders. CONCLUSIONS: Higher DLQI and I-NRS scores at baseline were associated with participants achieving treatment success by VIIS-50 and IGA response. Lower BSA involvement was associated with VIIS-50 success.

The Safety and Efficacy of Roflumilast Cream 0.15% and 0.05% in Patients With Atopic Dermatitis: Randomized, Double-Blind, Phase 2 Proof of Concept Study.

BACKGROUND: Patients with atopic dermatitis (AD) need safe and effective topical treatments. OBJECTIVE: To assess safety and efficacy of roflumilast cream in patients with mild to moderate AD. METHODS: In this phase 2, proof of concept trial, patients (N=136) aged ≥12 years with AD were randomized to once-daily roflumilast cream 0.15%, roflumilast cream 0.05%, or vehicle cream for 4 weeks. Absolute change from baseline in Eczema Area and Severity Index (EASI) score at week 4 (primary endpoint), percentage change and responder rates, Validated Investigator Global Assessment-AD (vIGA-AD), and safety were assessed. RESULTS: At week 4, mean absolute changes in EASI were −6.4 (P=0.097 vs vehicle), −6.0 (P=0.356), and −4.8 with roflumilast 0.15%, roflumilast 0.05%, and vehicle, respectively. Significant improvements were observed for percentage change from baseline in EASI, patients reaching 75% improvement in EASI, and patients achieving vIGA-AD score of “clear” or “almost clear.” Treatment-related adverse events (AEs) occurred in 2 (2.2%) patients receiving roflumilast (mild rash and moderate application site pain). Only 1 (1.1%) patient receiving roflumilast discontinued study/drug due to an AE. LIMITATIONS: Small number of patients. CONCLUSIONS: Results support additional larger clinical trials of roflumilast cream to assess its potential as a once-daily, nonsteroidal topical AD treatment. CLINICALTRIALS: gov identifier NCT03916081 J Drugs Dermatol. 2023;22(2):139-147. doi:10.36849/JDD.7295.

Phase IIb randomized CONTROL study demonstrates a novel topical isotretinoin formulation, TMB-001, is safe and effective in participants with either recessive X-linked or autosomal recessive lamellar congenital ichthyosis.

BACKGROUND: In two severe congenital ichthyosis subtypes, autosomal recessive lamellar ichthyosis (ARCI-LI) and X-linked recessive ichthyosis (XLRI), cutaneous manifestations include widespread scaling. Approved topical treatment options are limited to emollients and keratolytics. AIM: This analysis from the randomized phase IIb CONTROL study assessed whether the efficacy and safety of TMB-001, a novel topical isotretinoin ointment formulation, differed between ARCI-LI and XLRI subtypes. METHODS: Participants ≥ 9 years with genetically confirmed XLRI or ARCI-LI and ≥ 2 (of 4) Visual Index for Ichthyosis Severity (VIIS) assessment areas with ≥ 3 scaling score were randomized 1 : 1 : 1 to TMB-001 0.05%/TMB-001 0.1%/vehicle, twice daily for 12 weeks. The proportion of participants with ≥ 50% reduction vs. baseline in VIIS scaling (VIIS 50; primary endpoint) and ≥ 2-grade reduction in Investigator's Global Assessment (IGA)-scaling score vs. baseline (key secondary endpoint) were evaluated. Adverse events (AEs) were monitored. RESULTS: Among enrolled participants (TMB-001 0.05%, n = 11; 0.1%, n = 10; and vehicle, n = 12), 52% had ARCI-LI and 48% XLRI subtypes. Mean age was 33.6 and 35.4 years for participants with ARCI-LI and XLRI, respectively. Overall, 33%, 50% and 17% of participants with ARCI-LI and 100%, 33% and 75% of participants with XLRI achieved VIIS 50 in the TMB-001 0.05%, TMB-001 0.1% and vehicle groups, respectively (nominal P = 0.24 for 0.05% vs. vehicle, intent-to-treat population). Improvement of ≥ 2-grade IGA score was observed in 33%, 50% and 0% of participants with ARCI-LI and 83%, 33% and 25% of participants with XLRI in the TMB-001 0.05%, TMB-001 0.1% and vehicle groups, respectively (nominal P = 0.03 for 0.05% vs. vehicle, intention-to-treat population). Most AEs were application-site reactions. CONCLUSION: Regardless of congenital ichthyosis subtype, TMB-001 demonstrated greater proportions of participants achieving VIIS 50 and ≥ 2-grade IGA improvement vs. vehicle.

Effect of Roflumilast Cream (ARQ-151) on Itch and Itch-Related Sleep Loss in Adults with Chronic Plaque Psoriasis: Patient-Reported Itch Outcomes of a Phase 2b Trial.

BACKGROUND: Itch is the most bothersome symptom reported by patients with psoriasis. Safe and effective treatments for psoriasis that also address itch are needed. OBJECTIVES: To report effects of roflumilast cream on itch-related outcomes from a Phase 2b trial. METHODS: Adults with chronic plaque psoriasis were randomized to roflumilast 0.3%, roflumilast 0.15%, or vehicle once-daily for 12 weeks. Psoriasis severity was assessed via the Investigator Global Assessment (IGA; a 5-point scale assessing plaque thickening, scaling, and erythema ranging from 0 [clear] to 4 [severe]) and ≥ 2 on a modified Psoriasis Area and Severity Index (PASI-HD, which combines severity of lesions and area affected, ranging from 0 [no disease] to 72 [maximal disease], with the actual percentage of the anatomical area involved in those patients with < 10% of anatomical area involved [e.g., 0.1 for 1% to 0.9 for 9%]). Itch was evaluated via Worst Itch Numeric Rating Scale (WI-NRS), Psoriasis Symptom Diary (PSD) Items 1 (severity of itch) and 2 (bother of itch), and itch-related sleep loss NRS scores. Post hoc correlation analyses between WI-NRS and PASI, WI-NRS and itch-related sleep loss, and WI-NRS and DLQI were also performed. RESULTS: Roflumilast-treated patients had significantly greater improvements than vehicle-treated patients in WI-NRS and PSD Items 1 and 2 beginning at Week 2 and in itch-related sleep loss Weeks 6 through 12. Among patients with baseline WI-NRS ≥ 6, significantly more patients achieved ≥ 4-point improvement with roflumilast than with vehicle as early as Week 2. Itch severity had low correlation with PASI while WI-NRS and IGA were not always aligned. LIMITATIONS: The first assessment was at 2 weeks, limiting the ability to assess early onset of itch response. CONCLUSION: Roflumilast cream improved itch and itch-related sleep loss associated with chronic plaque psoriasis. GOV IDENTIFIER: NCT03638258.

Effect of Roflumilast Cream vs Vehicle Cream on Chronic Plaque Psoriasis: The DERMIS-1 and DERMIS-2 Randomized Clinical Trials.

Importance: Once-daily roflumilast cream, 0.3%, a potent phosphodiesterase 4 inhibitor, demonstrated efficacy and was well tolerated in a phase 2b trial of patients with psoriasis. Objective: To evaluate the efficacy of roflumilast cream, 0.3%, applied once daily for 8 weeks in 2 trials of patients with plaque psoriasis. Design, Setting, and Participants: Two phase 3, randomized, double-blind, controlled, multicenter trials (DERMIS-1 [trial 1; n = 439] and DERMIS-2 [trial 2; n = 442]) were conducted at 40 centers (trial 1) and 39 centers (trial 2) in the US and Canada between December 9, 2019, and November 16, 2020, and between December 9, 2019, and November 23, 2020, respectively. Patients aged 2 years or older with plaque psoriasis involving 2% to 20% of body surface area were enrolled. The dates of final follow-up were November 20, 2020, and November 23, 2020, for trial 1 and trial 2, respectively. Interventions: Patients were randomized 2:1 to receive roflumilast cream, 0.3% (trial 1: n = 286; trial 2: n = 290), or vehicle cream (trial 1: n = 153; trial 2: n = 152) once daily for 8 weeks. Main Outcomes and Measures: The primary efficacy end point was Investigator Global Assessment (IGA) success (clear or almost clear status plus ≥2-grade improvement from baseline [score range, 0-4]) at week 8, analyzed using a Cochran-Mantel-Haenszel test stratified by site, baseline IGA score, and intertriginous involvement. There were 9 secondary outcomes, including intertriginous IGA success, 75% reduction in Psoriasis Area and Severity Index (PASI) score, and Worst Itch Numeric Rating Scale score of 4 or higher at baseline achieving 4-point reduction (WI-NRS success) at week 8 (scale: 0 [no itch] to 10 [worst imaginable itch]; minimum clinically important difference, 4 points). Results: Among 881 participants (mean age, 47.5 years; 320 [36.3%] female), mean IGA scores in trial 1 were 2.9 [SD, 0.52] for roflumilast and 2.9 [SD, 0.45] for vehicle and in trial 2 were 2.9 [SD, 0.48] for roflumilast and 2.9 [SD, 0.47]) for vehicle. Statistically significantly greater percentages of roflumilast-treated patients than vehicle-treated patients had IGA success at week 8 (trial 1: 42.4% vs 6.1%; difference, 39.6% [95% CI, 32.3%-46.9%]; trial 2: 37.5% vs 6.9%; difference, 28.9% [95% CI, 20.8%-36.9%]; P < .001 for both). Of 9 secondary end points, statistically significant differences favoring roflumilast vs vehicle were observed for 8 in trial 1 and 9 in trial 2, including intertriginous IGA success (71.2% vs 13.8%; difference, 66.5% [95% CI, 47.1%-85.8%] and 68.1% vs 18.5%; difference, 51.6% [95% CI, 29.3%-73.8%]; P < .001 for both), 75% reduction in PASI score (41.6% vs 7.6%; difference, 36.1% [95% CI, 28.5%-43.8%] and 39.0% vs 5.3%; difference, 32.4% [95% CI, 24.9%-39.8%]; P < .001 for both), WI-NRS success (67.5% vs 26.8%; difference, 42.6% [95% CI, 31.3%-53.8%] and 69.4% vs 35.6%; difference, 30.2% [95% CI, 18.2%-42.2%]; P < .001 for both). The incidence of treatment-emergent adverse events was 25.2% with roflumilast vs 23.5% with vehicle in trial 1 and 25.9% with roflumilast vs 18.4% with vehicle in trial 2. The incidence of serious adverse events was 0.7% with roflumilast vs 0.7% with vehicle in trial 1 and 0% with roflumilast vs 0.7% with vehicle in trial 2. Conclusions and Relevance: Among patients with chronic plaque psoriasis, treatment with roflumilast cream, 0.3%, compared with vehicle cream resulted in better clinical status at 8 weeks. Further research is needed to assess efficacy compared with other active treatments and to assess longer-term efficacy and safety. Trial Registration: ClinicalTrials.gov Identifiers: NCT04211363, NCT04211389.

Setipiprant for Androgenetic Alopecia in Males: Results from a Randomized, Double-Blind, Placebo-Controlled Phase 2a Trial.

PURPOSE: To evaluate oral setipiprant versus placebo for scalp hair growth in men with androgenetic alopecia (AGA). PATIENTS AND METHODS: Males aged 18 to 49 years with AGA were enrolled in a double-blind, multicenter, 32-week, phase 2a trial; randomized to twice-daily (BID) 1000-mg (2×500 mg for a total daily dose of 2000 mg) setipiprant tablets or placebo for 24 weeks; and assessed at weeks 4, 8, 16, and 24, with a week 32 follow-up. The study initially included a finasteride 1-mg once-daily group, removed by protocol amendment. Changes from baseline to week 24 in target area hair count (TAHC) and blinded Subject Self-Assessment (SSA) of target area photographs were coprimary efficacy endpoints. Hair growth was also evaluated using blinded Investigator Global Assessment (IGA). Safety assessments included adverse events (AEs) and clinical laboratory tests. Analysis of covariance models were used to test statistical significance for TAHC, SSA, and IGA. Data were summarized without statistical analysis for finasteride. RESULTS: Randomized subjects (N=169) included 74 placebo, 83 setipiprant, and 12 finasteride subjects; 117 (69.2%) and 113 (66.9%) subjects completed week 24 and 32 visits, respectively. Treatment groups had similar baseline characteristics. Neither coprimary efficacy endpoint was met. At week 24, TAHC and SSA findings indicated no hair growth improvements with setipiprant versus placebo. Setipiprant also did not improve hair growth versus placebo per the IGA. Treatment-related AEs, all mild or moderate in severity, occurred in 12.3%, 25.9%, and 25.0% of the placebo, setipiprant, and finasteride groups, respectively. Two treatment-emergent serious AEs (TESAEs), cellulitis and multiple sclerosis, were reported in the placebo group, both unrelated to treatment. No TESAEs were reported with setipiprant or finasteride. CONCLUSION: Setipiprant 1000 mg BID was safe and well tolerated but did not demonstrate efficacy versus placebo for scalp hair growth in men with AGA.

Automated chart filing on panoramic radiographs using deep learning.

OBJECTIVE: The aim of this study is to automatically detect, segment and label teeth, crowns, fillings, root canal fillings, implants and root remnants on panoramic radiographs (PR(s)). MATERIAL AND METHODS: As a reference, 2000 PR(s) were manually annotated and labeled. A deep-learning approach based on mask R-CNN with Resnet-50 in combination with a rule-based heuristic algorithm and a combinatorial search algorithm was trained and validated on 1800 PR(s). Subsquently, the trained algorithm was applied onto a test set consisting of 200 PR(s). F1 scores, as a measure of accuracy, were calculated to quantify the degree of similarity between the annotated ground-truth and the model predictions. The F1-score considers the harmonic mean of precison (positive predictive value) and recall (specificity). RESULTS: The proposes method achieved F1 scores up to 0.993, 0.952 and 0.97 for detection, segmentation and labeling, respectivley. CONCLUSION: The proposed method forms a promising foundation for the further development of automatic chart filing on PR(s). CLINICAL SIGNIFICANCE: Deep learning may assist clinicians in summarizing the radiological findings on panoramic radiographs. The impact of using such models in clinical practice should be explored.

Classification of caries in third molars on panoramic radiographs using deep learning.

The objective of this study is to assess the classification accuracy of dental caries on panoramic radiographs using deep-learning algorithms. A convolutional neural network (CNN) was trained on a reference data set consisted of 400 cropped panoramic images in the classification of carious lesions in mandibular and maxillary third molars, based on the CNN MobileNet V2. For this pilot study, the trained MobileNet V2 was applied on a test set consisting of 100 cropped PR(s). The classification accuracy and the area-under-the-curve (AUC) were calculated. The proposed method achieved an accuracy of 0.87, a sensitivity of 0.86, a specificity of 0.88 and an AUC of 0.90 for the classification of carious lesions of third molars on PR(s). A high accuracy was achieved in caries classification in third molars based on the MobileNet V2 algorithm as presented. This is beneficial for the further development of a deep-learning based automated third molar removal assessment in future.

Phase 3 Trials of Tirbanibulin Ointment for Actinic Keratosis.

BACKGROUND: The tubulin polymerization and Src kinase signaling inhibitor tirbanibulin is being investigated as a topical treatment for actinic keratosis, a precursor of squamous-cell carcinoma. METHODS: In two identically designed double-blind trials, we randomly assigned, in a 1:1 ratio, adults with actinic keratoses on the face or scalp to receive either topical tirbanibulin or vehicle (placebo) ointment. The ointment was applied by the patients to a 25-cm2 contiguous area containing four to eight lesions once daily for 5 consecutive days. The primary outcome was the percentage of patients with a complete (100%) reduction in the number of lesions in the application area at day 57. The secondary outcome was the percentage of patients with a partial (≥75%) reduction in the number of lesions within the application area at day 57. The incidence of recurrence was evaluated at 1 year. Local reactions were scored with the use of 4-point scale (ranging from 0 [absent] to 3 [severe]). RESULTS: A total of 702 patients were enrolled in the two trials (351 patients per trial). Complete clearance in trial 1 occurred in 44% of the patients (77 of 175) in the tirbanibulin group and in 5% of those (8 of 176) in the vehicle group (difference, 40 percentage points; 95% confidence interval [CI], 32 to 47; P<0.001); in trial 2, the percentages were 54% (97 of 178 patients) and 13% (22 of 173), respectively (difference, 42 percentage points; 95% CI, 33 to 51; P<0.001). The percentages of patients with partial clearance were significantly higher in the tirbanibulin groups than in the vehicle groups. At 1 year, the estimated percentage of patients with recurrent lesions was 47% among patients who had had a complete response to tirbanibulin. The most common local reactions to tirbanibulin were erythema in 91% of the patients and flaking or scaling in 82%. Adverse events with tirbanibulin were application-site pain in 10% of the patients and pruritus in 9%, all of which resolved. CONCLUSIONS: In two identically designed trials, tirbanibulin 1% ointment applied once daily for 5 days was superior to vehicle for the treatment of actinic keratosis at 2 months but was associated with transient local reactions and recurrence of lesions at 1 year. Trials comparing tirbanibulin with conventional treatments and that have longer follow-up are needed to determine the effects of tirbanibulin therapy on actinic keratosis. (Funded by Athenex; ClinicalTrials.gov numbers, NCT03285477 and NCT03285490.).

Efficacy and safety of topical terbinafine 10% solution (MOB-015) in the treatment of mild to moderate distal subungual onychomycosis: A randomized, multicenter, double-blind, vehicle-controlled phase 3 study.

BACKGROUND: Onychomycosis is a recalcitrant fungal nail infection. Topical antifungal agents may be preferred over systemic agents due to lack of systemic adverse effects. OBJECTIVE: To investigate the efficacy and safety of topical terbinafine 10% solution (MOB-015) for the treatment of distal and lateral subungual onychomycosis. METHODS: In a multicenter, double-blind, phase III, North American study, patients with mild to moderate distal and lateral subungual onychomycosis involving 20% to 60% of at least 1 great toenail were randomized to once daily application of MOB-015 or matching vehicle for 48 weeks. The primary efficacy variable was complete cure, while the secondary efficacy variables were mycological cure and treatment success. Safety evaluations were also performed. RESULTS: At week 52, the mycological cure (negative culture and potassium hydroxide microscopy) rate in the MOB-015 and vehicle groups was 69.9% and 27.7%, respectively (P < .001), and complete cure (0% clinical disease involvement and mycological cure) was achieved in 4.5% and 0% of patients, respectively (P = .0195). At least 1 adverse event leading to discontinuation of treatment occurred in 2.8% of patients in the MOB-015 group and in 4.2% in the vehicle group. LIMITATION: The follow-up period after end of treatment may not be sufficient to accurately reflect cure in distal and lateral subungual onychomycosis. CONCLUSIONS: MOB-015 is a treatment option for onychomycosis with an adverse event profile similar to vehicle.

Tirbanibulin Ointment 1% as a Novel Treatment for Actinic Keratosis: Phase 1 and 2 Results.

BACKGROUND: Current field-directed treatments of actinic keratosis (AK), a pre-malignant condition, are often limited by severe local reactions and/or complex treatment. Tirbanibulin, a novel potent anti-proliferative synthetic agent that inhibits tubulin polymerization and Src kinase signalling, is being developed as a convenient, safe, and effective field treatment of actinic keratosis. HYPOTHESIS: A short course of tirbanibulin ointment 1% safely reduces AK lesions. METHODS: In the Phase 1 study, 4 treatment cohorts with forearm lesions received tirbanibulin ointment 1% over 25 or 100 cm2 once daily for 3 or 5 days and were evaluated through day 45. In the Phase 2 study, 2 treatment cohorts with face or scalp lesions received tirbanibulin ointment 1% once daily for 3 or 5 days over 25 cm2 and were evaluated through day 57. Lesion reductions, clearance rates, safety, and pharmacokinetics were assessed. RESULTS: Forearm AK lesions were reduced by day 45 in all Phase 1 cohorts (N=30). Complete AK clearance at day 57 for face/scalp AK lesions in Phase 2 cohorts (N=168) was demonstrated in 43% and 32% of participants of the 5-day and 3-day cohorts, respectively. Adverse reactions were mainly transient mild local erythema and flaking/scaling, pruritus, and pain. Tirbanibulin plasma concentrations were low or undetectable. CONCLUSION: Tirbanibulin ointment 1% was well tolerated and active in AK reduction. Based on activity, the 5-day regimen was selected for Phase 3 development. Clinicaltrials.gov: NCT02337205; NCT02838628 J Drugs Dermatol. 2020;19(11):1093-1100. doi:10.36849/JDD.2020.5576THIS ARTICLE HAD BEEN MADE AVAILABLE FREE OF CHARGE. PLEASE SCROLL DOWN TO ACCESS THE FULL TEXT OF THIS ARTICLE WITHOUT LOGGING IN. NO PURCHASE NECESSARY. PLEASE CONTACT THE PUBLISHER WITH ANY QUESTIONS.