Novel neural network model for predicting susceptibility of facial post-inflammatory hyperpigmentation

Sun, Ninghui; Chen, Binbin; Zhang, Rui; Ye, Wen

doi:10.1016/j.medengphy.2022.103884

Cited by 2 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The exact value of human skin properties is difficult to determine. Therefore, the proposed approach’s performance is evaluated by comparing it with one of the most reliable clinical equipment systems, the VISIA system 11 , 52 , 55 . This implies that the correlation values are a comparison to determine the strength and direction of the relationship between the two systems, rather than an absolute accuracy of skin measurements.…”

Section: Discussionmentioning

confidence: 99%

“…Therefore, the proposed approach’s performance is evaluated by comparing it with one of the most reliable clinical equipment systems, the VISIA system. 11 , 52 , 55 This implies that the correlation values are a comparison to determine the strength and direction of the relationship between the two systems, rather than an absolute accuracy of skin measurements. The proposed model is considered sufficiently trained at around 200 epochs, with correlation coefficients of 0.932 and 0.857 for melanin and hemoglobin, as shown in Fig.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning-based optical approach for skin analysis of melanin and hemoglobin distribution

Jung¹,

Kim²,

Lee³

et al. 2023

J. Biomed. Opt.

View full text Add to dashboard Cite

Significance: Melanin and hemoglobin have been measured as important diagnostic indicators of facial skin conditions for aesthetic and diagnostic purposes. Commercial clinical equipment provides reliable analysis results, but it has several drawbacks: exclusive to the acquisition system, expensive, and computationally intensive.Aim: We propose an approach to alleviate those drawbacks using a deep learning model trained to solve the forward problem of light-tissue interactions. The model is structurally extensible for various light sources and cameras and maintains the input image resolution for medical applications.Approach: A facial image is divided into multiple patches and decomposed into melanin, hemoglobin, shading, and specular maps. The outputs are reconstructed into a facial image by solving the forward problem over skin areas. As learning progresses, the difference between the reconstructed image and input image is reduced, resulting in the melanin and hemoglobin maps becoming closer to their distribution of the input image. Results:The proposed approach was evaluated on 30 subjects using the professional clinical system, VISIA VAESTRO. The correlation coefficients for melanin and hemoglobin were found to be 0.932 and 0.857, respectively. Additionally, this approach was applied to simulated images with varying amounts of melanin and hemoglobin. Conclusion:The proposed approach showed high correlation with the clinical system for analyzing melanin and hemoglobin distribution, indicating its potential for accurate diagnosis. Further calibration studies using clinical equipment can enhance its diagnostic ability. The structurally extensible model makes it a promising tool for various image acquisition conditions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Deep learning-based optical approach for skin analysis of melanin and hemoglobin distribution

Jung¹,

Kim²,

Lee³

et al. 2023

J. Biomed. Opt.

View full text Add to dashboard Cite

show abstract

“…Neural networks predict post-inflammatory hyperpigmentation risk. 4 Gender and age-balanced datasets are vital to mitigate bias. AI enhances personalized care, available through physician and consumer apps that simulate skin changes and product effects, thereby providing location-specific skincare recommendations.…”

mentioning

confidence: 99%

Skin & Digital – The 2023 conversation

du Crest,

Madhumita,

Rossi

et al. 2023

Acad Dermatol Venereol

View full text Add to dashboard Cite

Dear Editor, Digital health is a complex buzzword encompassing several technologies, including artificial intelligence (AI), machine learning (ML), computer vision and large language models (LLMs), 1 to name a few. 'Skin & Digital' interactions constantly evolve, impacting the academic world, regulators, doctors, care providers, consumers, patients, patient groups and the skin industry. The 'Skin & Digital Summit' aims at fostering a conversation linking both worlds. This article presents the Proceedings of the 'Skin & Digital Summit', which took place on 28 January 2023.The core intelligence in AI lies in its capacity to learn and adapt from extensive and diverse datasets. AI in dermatology holds significant promise, especially in understanding complex skin conditions. It analyses patterns between genetic factors and cumulative exposures, aiding early diagnosis, prognosis and treatment of skin conditions through clinical decision support systems.Artificial intelligence algorithms are trained on diverse medical data, improving diagnostic accuracy and decision making. While AI does not replace dermatologists, it enhances care. Digital tools like smartphone apps offer self-monitoring of skin conditions, while automated total body mapping aids in the detection of skin cancer among other conditions. Genetic data analysis helps predict patient treatment responses, leading to more effective and personalized care. 2

show abstract

Novel neural network model for predicting susceptibility of facial post-inflammatory hyperpigmentation

Cited by 2 publications

References 29 publications

Deep learning-based optical approach for skin analysis of melanin and hemoglobin distribution

Deep learning-based optical approach for skin analysis of melanin and hemoglobin distribution

Skin & Digital – The 2023 conversation

Contact Info

Product

Resources

About