Objective measurement of erythema in psoriasis using digital color photography with color calibration

Artificial Intelligence: A Snapshot of Its Application in Chronic Inflammatory and Autoimmune Skin Diseases

Immuno-correlated dermatological pathologies refer to skin disorders that are closely associated with immune system dysfunction or abnormal immune responses. Advancements in the field of artificial intelligence (AI) have shown promise in enhancing the diagnosis, management, and assessment of immuno-correlated dermatological pathologies. This intersection of dermatology and immunology plays a pivotal role in comprehending and addressing complex skin disorders with immune system involvement. The paper explores the knowledge known so far and the evolution and achievements of AI in diagnosis; discusses segmentation and the classification of medical images; and reviews existing challenges, in immunological-related skin diseases. From our review, the role of AI has emerged, especially in the analysis of images for both diagnostic and severity assessment purposes. Furthermore, the possibility of predicting patients' response to therapies is emerging, in order to create tailored therapies.

Effect of camera distance and angle on color of diverse skin tone-based standards in smartphone photos

Accurate and reproducible color capture is vital in medical photography. Camera distance and angle are particularly important as they are highly variable in a clinical setting. To account for variability in illumination, camera technology, and geometric effects, color standards are often used for color correction. To explore how geometry affects color, we quantified the change in CIELAB color value of a color standard for diverse skin tones at varying smartphone camera distances and angles. Whereas both chromaticity (a* and b*) and lightness (L*) were affected by angle, distance only affected L* (standard error of measurement, SEM > 1 CIELAB unit). Flash usage did not generally reduce distance and angle associated variability. Compared to compressed (JPG) format, raw (DNG) images had decreased median variability across different distances and angles. These findings suggest that in medical photography, inconsistent camera distance and angle can increase variability in photographed skin appearance over time.

Color variations during digital imaging of facial prostheses subjected to unfiltered ambient light and image calibration techniques within dental clinics: An in vitro analysis

Background

The study aimed to evaluate 1) the amount of color variations presents within clinical images of maxillofacial prosthetic silicone specimens when photographed under different clinically relevant ambient lighting conditions, and 2) whether white balance calibration (WBC) methods were able to mitigate variations in ambient lighting.

Methods

432 measurements were acquired from standardized images of the pigmented prosthetic silicone specimens within different ambient lighting conditions (i.e., 2 windowed and 2 windowless clinics) at noon with no light modifying apparatus. The specimens were photographed once without any white balance calibration (raw), then independently alongside an 18% neutral gray card and Macbeth color chart for calibration in a post-processing (PPWBC) software, and once after camera calibration (CWBC) using a gray card. The LAB color values were extracted from the images and color variations (ΔE) were calculated after referring to the corresponding spectrophotometric values as control.

Results

Images in windowless and windowed clinics exhibited highly significant differences (p < 0.001) with spectrophotometer (control). CWBC demonstrated no significant differences (p > 0.05) in LAB values across windowed clinics. PPWBC using Macbeth color chart produced no significant differences for a* values (p > 0.05) across all clinics while PPWBC by gray card showed no significant differences (p > 0.05) in LAB values when only similar clinics (either windowed or windowless) were compared.

Conclusion

Significant color variations were present for maxillofacial prosthetic specimens owing to natural ambient light. CWBC and PPWBC using color charts were more suitable for color correction across windowed clinics while CWBC and PPWBC using gray cards had better outcomes across windowless setups.

Can artificial intelligence be used for accurate remote scoring of the Psoriasis Area and Severity Index (PASI) in adult patients with plaque psoriasis? A Critically Appraised Topic

A 47-year-old man with chronic plaque psoriasis and type II diabetes mellitus on ustekinumab 45mg 12 weekly injections, his first biologic therapy, was switched to adalimumab 40mg alternate weeks (10/02/2020) when his Psoriasis Area and Severity Index (PASI) was 11.4 due to loss of effectiveness. Due to the COVID-19 outbreak, the U.K Prime Minister advised clinically vulnerable people, including people on immunosuppressive medication with comorbidities including diabetes, to stay home avoiding face-to-face contact (23/03/2020). We performed a Critically Appraised Topic review to understand whether it was possible to remotely assess his response to adalimumab with AI assistance.

Machine Learning Applications in the Evaluation and Management of Psoriasis: A Systematic Review

Background

Machine learning (ML), a subset of artificial intelligence (AI) that aims to teach machines to automatically learn tasks by inferring patterns from data, holds significant promise to aid psoriasis care. Applications include evaluation of skin images for screening and diagnosis as well as clinical management including treatment and complication prediction.

Objective

To summarize literature on ML applications to psoriasis evaluation and management and to discuss challenges and opportunities for future advances.

Methods

We searched MEDLINE, Google Scholar, ACM Digital Library, and IEEE Xplore for peer-reviewed publications published in English through December 1, 2019. Our search queries identified publications with any of the 10 computing-related keywords and "psoriasis" in the title and/or abstract.

Results

Thirty-three studies were identified. Articles were organized by topic and synthesized as evaluation- or management-focused articles covering 5 content categories: (A) Evaluation using skin images: (1) identification and differential diagnosis of psoriasis lesions, (2) lesion segmentation, and (3) lesion severity and area scoring; (B) clinical management: (1) prediction of complications and (2) treatment.

Conclusion

Machine learning has significant potential to aid psoriasis evaluation and management. Current topics popular in ML research on psoriasis are the evaluation of medical images, prediction of complications, and treatment discovery. For patients to derive the greatest benefit from ML advancements, it is helpful for dermatologists to have an understanding of ML and how it can effectively aid their assessments and decision-making.

Evaluation of Erythema Severity in Dermatoscopic Images of Canine Skin: Erythema Index Assessment and Image Sampling Reliability

The regular monitoring of erythema, one of the most important skin lesions in atopic (allergic) dogs, is essential for successful anti-allergic therapy. The smartphone-based dermatoscopy enables a convenient way to acquire quality images of erythematous skin. However, the image sampling to evaluate erythema severity is still done manually, introducing result variability. In this study, we investigated the correlation between the most popular erythema indices (EIs) and dermatologists’ erythema perception, and we measured intra- and inter-rater variability of the currently-used manual image-sampling methods (ISMs). We showed that the EI_BRG, based on all three RGB (red, green, and blue) channels, performed the best with an average Spearman coefficient of 0.75 and a typical absolute disagreement of less than 14% with the erythema assessed by clinicians. On the other hand, two image-sampling methods, based on either selecting specific pixels or small skin areas, performed similarly well. They achieved high intra- and inter-rater reliability with the intraclass correlation coefficient (ICC) and Krippendorff’s alpha well above 0.90. These results indicated that smartphone-based dermatoscopy could be a convenient and precise way to evaluate skin erythema severity. However, better outlined, or even automated ISMs, are likely to improve the intra- and inter-rater reliability in severe erythematous cases.

Evaluation of skin erythema severity by dermatoscopy in dogs with atopic dermatitis

BACKGROUND

To estimate the extent and severity of atopic dermatitis (AD)-related skin lesions, clinical trials enrolling dogs with AD often use categorical scales such as the Canine Atopic Dermatitis Extent and Severity Index, 4^th iteration (CADESI-04) and Canine Atopic Dermatitis Lesion Index (CADLI). Despite recent progress in the standardization of these AD-grading scales, the evaluation of the severity of skin lesions (including erythema) remains subjective.

OBJECTIVES

To validate an optical set-up with a smartphone and a dermatoscope for the objective estimation of skin erythema severity in atopic dogs.

ANIMALS

Forty-three dogs with AD.

METHODS AND MATERIALS

An erythema index (EI) was calculated from calibrated skin images and compared to the dermatologist's erythema severity estimate using the erythema grading scale used in the CADESI-04, as well as an ad hoc Visual Analog Scale (VAS) with a continuous palette of red shades.

RESULTS

We found a strong correlation based on the Spearman rank correlation coefficient between all erythema valuations: CADESI-04 and VAS: 0.93 [95% CI: (0.85, 0.96)]; CADESI-04 and EI: 0.85 (0.72, 0.92); VAS and EI: 0.82 (0.67, 0.91). There was a good agreement between the objective EI and CADESI-04-based estimates because 71% of samples were classified in the same erythema severity category. When comparing the EI and the VAS, the standard deviation of misestimates was 12% (maximum 100%).

CONCLUSIONS AND CLINICAL RELEVANCE

The proposed optical set-up has the potential to make erythema severity estimation objective, thus leading to more reliable AD severity scales for the use in experimental canine AD models or in clinical trials enrolling atopic dogs.

Non-invasive clinical and microscopic evaluation of the response to treatment with clobetasol cream vs. calcipotriol/betamethasone dipropionate foam in mild to moderate plaque psoriasis: an investigator-initiated, phase IV, unicentric, open, randomized clinical trial

BACKGROUND

Treatment response for psoriasis is typically evaluated using clinical scores. However, patients can relapse after clinical clearance, suggesting persistent inflammation. Dermoscopy, reflectance confocal microscopy (RCM) and optical coherence tomography (OCT) can non-invasively improve treatment response assessment.

OBJECTIVES

To compare the clinical and non-invasive microscopic features in a psoriatic target lesion treated with clobetasol cream or calcipotriol/betamethasone dipropionate foam (Cal/BD foam).

METHODS

Prospective, unicentric, open, randomized clinical trial comparing clinical data [total clinical score (TCS)] and microscopic data (dermoscopy, RCM and OCT) in psoriasis patients treated with clobetasol or Cal/BD foam.

RESULTS

We included 36 adult patients (22 men). At week 4, more patients treated with Cal/BD foam achieved TCS ≤1 than with clobetasol (63.2% vs. 18.8%, P = 0.016). Treatment satisfaction was higher with Cal/BD foam (P < 0.03). Microscopically, Cal/BD foam induced more reduction in epidermal thickness at week 4 (P < 0.049). Dilated horizontal blood vessels were more common with clobetasol than with Cal/BD foam at week 8 (69.2% vs. 31.2%, P = 0.159). If epidermal hyperplasia was noted at baseline, the response was poorer with clobetasol (P = 0.029).

LIMITATIONS

Small sample size, open study, imaging sampling bias.

CONCLUSION

Cal/BD foam is more effective than clobetasol, has better patient satisfaction and induces greater reduction in the hyperkeratosis/acanthosis, regardless of baseline epidermal hyperplasia.

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included "machine learning" or "artificial intelligence" and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.

Workflow Challenges of Enterprise Imaging: HIMSS-SIIM Collaborative White Paper

With the advent of digital cameras, there has been an explosion in the number of medical specialties using images to diagnose or document disease and guide interventions. In many specialties, these images are not added to the patient's electronic medical record and are not distributed so that other providers caring for the patient can view them. As hospitals begin to develop enterprise imaging strategies, they have found that there are multiple challenges preventing the implementation of systems to manage image capture, image upload, and image management. This HIMSS-SIIM white paper will describe the key workflow challenges related to enterprise imaging and offer suggestions for potential solutions to these challenges.

Changes in skin microcirculation during radiation therapy for breast cancer

BACKGROUND

The majority of breast cancer patients who receive radiation treatment are affected by acute radiation-induced skin changes. The assessment of these changes is usually done by subjective methods, which complicates the comparison between different treatments or patient groups. This study investigates the feasibility of new robust methods for monitoring skin microcirculation to objectively assess and quantify acute skin reactions during radiation treatment.

MATERIAL AND METHODS

Laser Doppler flowmetry, laser speckle contrast imaging, and polarized light spectroscopy imaging were used to measure radiation-induced changes in microvascular perfusion and red blood cell concentration (RBC) in the skin of 15 patients undergoing adjuvant radiation therapy for breast cancer. Measurements were made before treatment, once a week during treatment, and directly after the last fraction.

RESULTS

In the treated breast, perfusion and RBC concentration were increased after 1-5 fractions (2.66-13.3 Gy) compared to baseline. The largest effects were seen in the areola and the medial area. No changes in perfusion and RBC concentration were seen in the untreated breast. In contrast, Radiation Therapy Oncology Group (RTOG) scores were increased only after 2 weeks of treatment, which demonstrates the potential of the proposed methods for early assessment of skin changes. Also, there was a moderate to good correlation between the perfusion (r = 0.52) and RBC concentration (r = 0.59) and the RTOG score given a week later.

CONCLUSION

We conclude that radiation-induced microvascular changes in the skin can be objectively measured using novel camera-based techniques before visual changes in the skin are apparent. Objective measurement of microvascular changes in the skin may be valuable in the comparison of skin reactions between different radiation treatments and possibly in predicting acute skin effects at an earlier stage.