Automated grading of dandruff severity is a clinically significant but challenging task due to the inherent ordinal nature of severity levels and the high prevalence of label noise from subjective expert annotations.S...Automated grading of dandruff severity is a clinically significant but challenging task due to the inherent ordinal nature of severity levels and the high prevalence of label noise from subjective expert annotations.Standard classification methods fail to address these dual challenges,limiting their real-world performance.In this paper,a novel,three-phase training framework is proposed that learns a robust ordinal classifier directly from noisy labels.The approach synergistically combines a rank-based ordinal regression backbone with a cooperative,semi-supervised learning strategy to dynamically partition the data into clean and noisy subsets.A hybrid training objective is then employed,applying a supervised ordinal loss to the clean set.The noisy set is simultaneously trained using a dualobjective that combines a semi-supervised ordinal loss with a parallel,label-agnostic contrastive loss.This design allows themodel to learn fromthe entire noisy subset while using contrastive learning to mitigate the risk of error propagation frompotentially corrupt supervision.Extensive experiments on a new,large-scale,multi-site clinical dataset validate our approach.Themethod achieves state-of-the-art performance with 80.71%accuracy and a 76.86%F1-score,significantly outperforming existing approaches,including a 2.26%improvement over the strongest baseline method.This work provides not only a robust solution for a practical medical imaging problem but also a generalizable framework for other tasks plagued by noisy ordinal labels.展开更多
Background/Aim: Dandruff is a common scalp problem associated with flaky and inflamed skin. In this study, we investigated the efficacy of a shampoo containing piroctone olamine and climbazole and the combination of t...Background/Aim: Dandruff is a common scalp problem associated with flaky and inflamed skin. In this study, we investigated the efficacy of a shampoo containing piroctone olamine and climbazole and the combination of this shampoo with a scalp tonic containing piroctone olamine and licochalcone A, derived from Glycyrrhiza inflata root extract, to reduce dandruff. Study Design/Methods: After conditioning, 102 subjects (♂ 56 and 46 ♀) with moderate to very strong dandruff affection underwent a randomized half head study for 4 weeks. The volunteers’ heads were washed regularly either with a placebo or the anti-dandruff shampoo, followed by the anti-dandruff tonic application or no treatment. In a 2-week post-treatment phase, subjects only applied placebo shampoo. Every two weeks, trained experts assessed dandruff affection based on a scale of 1 to 6. At study start and after every 2 weeks, cytokine concentrations and anti-fungal activity of test products were determined in scalp wash-ups by enzyme-linked immunosorbant assays or a Malassezia colony-forming assay, respectively. Results: Results of expert grading and anti-fungal activity revealed a significant reduction in dandruff affection and Malassezia colony-forming units after treatment with the anti-dandruff shampoo or its combination with the tonic. Dandruff affection even remained reduced in the post-treatment phase when levels of Malassezia colony-forming units had returned to baseline. Cytokine analyses proved a significant decrease in pro-inflammatory dandruff markers after treatment with both anti-dandruff products. For the shampoo/tonic combination, a superior reduction of one scalp inflammatory marker was determined even after the post-treatment phase. Conclusion: Both the rinse-off shampoo as well as its combination with the leave-on tonic excellently alleviated dandruff and its associated micro-inflammation. Both treatments showed anti-fungal activity. The superior benefit, exerted by the combination, is primarily based on the known anti-inflammatory effect of licochalcone A and the improved scalp substantivity of the leave-on application.展开更多
文摘Automated grading of dandruff severity is a clinically significant but challenging task due to the inherent ordinal nature of severity levels and the high prevalence of label noise from subjective expert annotations.Standard classification methods fail to address these dual challenges,limiting their real-world performance.In this paper,a novel,three-phase training framework is proposed that learns a robust ordinal classifier directly from noisy labels.The approach synergistically combines a rank-based ordinal regression backbone with a cooperative,semi-supervised learning strategy to dynamically partition the data into clean and noisy subsets.A hybrid training objective is then employed,applying a supervised ordinal loss to the clean set.The noisy set is simultaneously trained using a dualobjective that combines a semi-supervised ordinal loss with a parallel,label-agnostic contrastive loss.This design allows themodel to learn fromthe entire noisy subset while using contrastive learning to mitigate the risk of error propagation frompotentially corrupt supervision.Extensive experiments on a new,large-scale,multi-site clinical dataset validate our approach.Themethod achieves state-of-the-art performance with 80.71%accuracy and a 76.86%F1-score,significantly outperforming existing approaches,including a 2.26%improvement over the strongest baseline method.This work provides not only a robust solution for a practical medical imaging problem but also a generalizable framework for other tasks plagued by noisy ordinal labels.
文摘Background/Aim: Dandruff is a common scalp problem associated with flaky and inflamed skin. In this study, we investigated the efficacy of a shampoo containing piroctone olamine and climbazole and the combination of this shampoo with a scalp tonic containing piroctone olamine and licochalcone A, derived from Glycyrrhiza inflata root extract, to reduce dandruff. Study Design/Methods: After conditioning, 102 subjects (♂ 56 and 46 ♀) with moderate to very strong dandruff affection underwent a randomized half head study for 4 weeks. The volunteers’ heads were washed regularly either with a placebo or the anti-dandruff shampoo, followed by the anti-dandruff tonic application or no treatment. In a 2-week post-treatment phase, subjects only applied placebo shampoo. Every two weeks, trained experts assessed dandruff affection based on a scale of 1 to 6. At study start and after every 2 weeks, cytokine concentrations and anti-fungal activity of test products were determined in scalp wash-ups by enzyme-linked immunosorbant assays or a Malassezia colony-forming assay, respectively. Results: Results of expert grading and anti-fungal activity revealed a significant reduction in dandruff affection and Malassezia colony-forming units after treatment with the anti-dandruff shampoo or its combination with the tonic. Dandruff affection even remained reduced in the post-treatment phase when levels of Malassezia colony-forming units had returned to baseline. Cytokine analyses proved a significant decrease in pro-inflammatory dandruff markers after treatment with both anti-dandruff products. For the shampoo/tonic combination, a superior reduction of one scalp inflammatory marker was determined even after the post-treatment phase. Conclusion: Both the rinse-off shampoo as well as its combination with the leave-on tonic excellently alleviated dandruff and its associated micro-inflammation. Both treatments showed anti-fungal activity. The superior benefit, exerted by the combination, is primarily based on the known anti-inflammatory effect of licochalcone A and the improved scalp substantivity of the leave-on application.
