Comparative study of skin autofluorescence expression in atopic dermatitis and psoriasis: A prospective in vivo study

Parameter-based transfer learning for severity classification of atopic dermatitis using hyperspectral imaging

BACKGROUND/PURPOSE

Because atopic dermatitis (AD) is a chronic inflammatory skin condition that causes structural changes, there is a growing need for noninvasive research methods to evaluate this condition. Hyperspectral imaging (HSI) captures skin structure features by exploiting light wavelength variations in penetration depth. In this study, parameter-based transfer learning was deployed to classify the severity of AD using HSI. Therefore, we aimed to obtain an optimal combination of classification results from the four models after constructing different source- and target-domain datasets.

METHODS

We designated psoriasis, skin cancer, eczema, and AD datasets as the source datasets, and the set of images acquired via hyperspectral camera as the target dataset for wavelength-specific AD classification. We compared the severity classification performances of 96 combinations of sources, models, and targets.

RESULTS

The highest classification performance of 83% was achieved when ResNet50 was trained on the augmented psoriasis dataset as the source, with the resulting parameters used to train the model on the target Near-infrared radiation (NIR) dataset. The second highest classification accuracy of 81% was achieved when ResNet50 was trained on the unaugmented psoriasis dataset as the source, with the resulting parameters used to train the model on the target R dataset. ResNet50 demonstrated potential as a generalized model for both the source and target data, also confirming that the psoriasis dataset is an effective training resource.

CONCLUSION

The present study not only demonstrates the feasibility of the severity classification of AD based on hyperspectral images, but also showcases combinations and research scalability for domain exploration.

Visualization of Keratin with Diffuse Reflectance and Autofluorescence Imaging and Nonlinear Optical Microscopy in a Rare Keratinopathic Ichthyosis

Keratins are one of the main fluorophores of the skin. Keratinization disorders can lead to alterations in the optical properties of the skin. We set out to investigate a rare form of keratinopathic ichthyosis caused by KRT1 mutation with two different optical imaging methods. We used a newly developed light emitting diode (LED) based device to analyze autofluorescence signal at 405 nm excitation and diffuse reflectance at 526 nm in vivo. Mean autofluorescence intensity of the hyperkeratotic palmar skin was markedly higher in comparison to the healthy control (162.35 vs. 51.14). To further assess the skin status, we examined samples from affected skin areas ex vivo by nonlinear optical microscopy. Two-photon excited fluorescence and second-harmonic generation can visualize epidermal keratin and dermal collagen, respectively. We were able to visualize the structure of the epidermis and other skin changes caused by abnormal keratin formation. Taken together, we were able to show that such imaging modalities are useful for the diagnosis and follow-up of keratinopathic diseases.

Skin Autofluorescence, as a Measure of AGE Accumulation in Individuals Suffering from Chronic Plaque Psoriasis

Background

Psoriasis is currently regarded as a chronic systemic inflammatory disease associated with increased cardiovascular risk. Advanced glycation end products (AGEs) contribute to the development of atherosclerosis.

Objectives

The aim of the study was the assessment of skin autofluorescence (SAF), as a measure of AGE accumulation, in individuals suffering from chronic plaque psoriasis without any comorbid conditions.

Methods

A study group consisted of 70 patients with chronic plaque psoriasis without any comorbid conditions and 59 healthy controls, matched by age and gender. AGE accumulation was assessed by SAF (AGE Reader, DiagnOptics BV) which is a validated and noninvasive technique. Relations between SAF and some clinical and laboratory data were assessed.

Results

SAF was positively correlated with age both in patients with psoriasis and controls (R = 0.722, p < 0.00001 and R = 0.613, p < 0.00001, respectively). There was significantly increased SAF in patients with psoriasis with elevated levels of C-reactive protein (CRP) and increased erythrocyte sedimentation rate (ESR) compared to controls (p < 0.00001; p < 0.00001, respectively, after adjustment to age). Increased SAF was found in psoriatic patients with prediabetes (HbA1c 5.7–6.4%) compared to controls (p < 0.0012, after adjustment to age).

Conclusion

Systemic inflammation (increased CRP level), prediabetes, and aging may influence enhanced AGE accumulation in patients with psoriasis without any comorbidities. SAF may be considered as a useful, noninvasive method to identify patients with psoriasis at increased cardiovascular risk.

Protoporphyrin IX fluorescence as potential indicator of psoriasis severity and progression

BACKGROUND AND OBJECTIVES

In psoriatic lesions, fluorescence diagnosis with blue light can detect protoporphyrin IX accumulation, especially after topical 5-aminolaevulinic acid (ALA) application. However, variable fluorescence distributions, interpersonal variations and long incubation time limit its wide application in clinic. This study is aimed to identify a consistent and convenient method to facilitate diagnosis and evaluation of psoriatic lesions.

METHODS

104 psoriatic lesions from 30 patients were evaluated. Single lesion PSI scoring and fluorescence by macrospectrofluorometry were recorded on each lesion before and after treatment with narrow-band UVB.

RESULTS

Punctate red fluorescence, emitted mainly by protoporphyrin IX, is observed in some psoriatic lesions. According to psoriasis severity index, fluorescence-positive lesions are more severe than lesions without fluorescence. We found a significant positive correlation between psoriasis severity and fluorescence intensity from protoporphyrin IX.

CONCLUSIONS

Protoporphyrin IX-induced red fluorescence can be used as a novel and convenient approach for psoriasis diagnosis and progression evaluation.