Deep Neural Network for Early Image Diagnosis of Stevens-Johnson Syndrome/Toxic Epidermal Necrolysis

Evolving trends in inpatient paediatric dermatology

PURPOSE OF REVIEW

This review provides updates in the evaluation and management of key dermatologic diseases encountered in the hospitalized child.

RECENT FINDINGS

Our understanding of dermatologic disorders in children continues to evolve. Staphylococcal scalded skin syndrome (SSSS) is a potentially severe blistering disorder typically seen in children under the age of 4 with an incidence that is increasing in the United States. Recent research has highlighted that the majority of cases are due to methicillin-sensitive Staphylococcus aureus (MSSA) and most patients can be adequately managed with beta-lactams. Toxic epidermal necrolysis (TEN) is one of the most feared dermatologic disorders. Currently, there is a lack of consensus on the most efficacious first-line systemic therapy. Etanercept is increasingly being used based on studies showing a shorter time to re-epithelization and decreased mortality. Lastly, the COVID-19 pandemic introduced the novel inflammatory condition multisystem inflammatory syndrome in children (MIS-C) in which approximately three out of four children present with a mucocutaneous eruption. Early recognition of the dermatologic features of MIS-C is important in potentially establishing a diagnosis and differentiating it from the many other causes of childhood fever and rash.

SUMMARY

There are no clear universal treatment guidelines for these rare diagnoses, and therefore, clinicians must remain informed of the latest findings in diagnosis and therapeutics.

Updates on the immunopathology and genomics of severe cutaneous adverse drug reactions

Severe cutaneous adverse reactions (SCARs) such as Stevens-Johnson syndrome, toxic epidermal necrolysis (SJS/TEN), and drug reaction with eosinophilia and systemic symptoms (DRESS)/drug-induced hypersensitivity syndrome (DIHS) cause significant morbidity and mortality and impede new drug development. HLA class I associations with SJS/TEN and drug reaction with eosinophilia and systemic symptoms/drug-induced hypersensitivity syndrome have aided preventive efforts and provided insights into immunopathogenesis. In SJS/TEN, HLA class I-restricted oligoclonal CD8+ T-cell responses occur at the tissue level. However, specific HLA risk allele(s) and antigens driving this response have not been identified for most drugs. HLA risk alleles also have incomplete positive and negative predictive values, making truly comprehensive screening currently challenging. Although, there have been key paradigm shifts in knowledge regarding drug hypersensitivity, there are still many open and unanswered questions about SCAR immunopathogenesis, as well as genetic and environmental risk. In addition to understanding the cellular and molecular basis of SCAR at the single-cell level, identification of the MHC-restricted drug-reactive self- or viral peptides driving the hypersensitivity reaction will also be critical to advancing premarketing strategies to predict risk at an individual and drug level. This will also enable identification of biologic markers for earlier diagnosis and accurate prognosis, as well as drug causality and targeted therapeutics.

Convolutional neural network-based skin image segmentation model to improve classification of skin diseases in conventional and non-standardized picture images

BACKGROUND

For dermatological practices, non-standardized conventional photo images are taken and collected as a mixture of variable fields of the image view, including close-up images focusing on designated lesions and long-shot images including normal skin and background of the body surface. Computer-aided detection/diagnosis (CAD) models trained using non-standardized conventional photo images exhibit lower performance rates than CAD models that detect lesions in a localized small area, such as dermoscopic images.

OBJECTIVE

We aimed to develop a convolutional neural network (CNN) model for skin image segmentation to generate a skin disease image dataset suitable for CAD of multiple skin disease classification.

METHODS

We trained a DeepLabv3 + -based CNN segmentation model to detect skin and lesion areas and segmented out areas that satisfy the following conditions: more than 80% of the image will be the skin area, and more than 10% of the image will be the lesion area.

RESULTS

The generated CNN-segmented image database was examined using CAD of skin disease classification and achieved approximately 90% sensitivity and specificity to differentiate atopic dermatitis from malignant diseases and complications, such as mycosis fungoides, impetigo, and herpesvirus infection. The accuracy of skin disease classification in the CNN-segmented image dataset was almost equal to that of the manually cropped image dataset and higher than that of the original image dataset.

CONCLUSION

Our CNN segmentation model, which automatically extracts lesions and segmented images of the skin area regardless of image fields, will reduce the burden of physician annotation and improve CAD performance.

Disease severity and status in Stevens–Johnson syndrome and toxic epidermal necrolysis: Key knowledge gaps and research needs

Stevens–Johnson syndrome and toxic epidermal necrolysis (SJS/TEN) are on a spectrum of cutaneous drug reactions characterized by pan-epidermal necrosis with SJS affecting < 10% of body surface area (BSA), TEN > 30%, and SJS/TEN overlap between 10 and 30%. Severity-of-illness score for toxic epidermal necrolysis (SCORTEN) is a validated tool to predict mortality rates based on age, heart rate, BSA, malignancy and serum urea, bicarbonate, and glucose. Despite improved understanding, SJS/TEN mortality remains constant and therapeutic interventions are not universally accepted for a number of reasons, including rarity of SJS/TEN; inconsistent definition of cases, disease severity, and endpoints in studies; low efficacy of interventions; and variations in treatment protocols. Apart from mortality, none of the other endpoints used to evaluate interventions, including duration of hospitalization, is sufficiently standardized to be reproducible across cases and treatment centers. Some of the gaps in SJS/TEN research can be narrowed through international collaboration to harmonize research endpoints. A case is made for an urgent international collaborative effort to develop consensus on definitions of endpoints such as disease status, progression, cessation, and complete re-epithelialization in interventional studies. The deficiencies of using BSA as the sole determinant of SJS/TEN severity, excluding internal organ involvement and extension of skin necrosis beyond the epidermis, are discussed and the role these factors play on time to healing and mortality beyond the acute stage is highlighted. The potential role of artificial intelligence, biomarkers, and PET/CT scan with radiolabeled glucose as markers of disease status, activity, and therapeutic response is also discussed.

Stevens-Johnson syndrome in children

PURPOSE OF REVIEW

The concept of Stevens-Johnson syndrome (SJS) in children is evolving. This manuscript reviews recent advances with the lens of new terminology namely infection-triggered reactive infectious mucocutaneous eruption and drug-induced epidermal necrolysis, with the objective of integrating this novel terminology practically.

RECENT FINDINGS

Traditionally considered to exist on a spectrum with toxic epidermal necrolysis, SJS in children is more often caused or triggered by infections instead of medications. Proposed pediatric-specific terminology can be applied to literature to gain further insights into blistering severe cutaneous adverse reactions.

SUMMARY

Distinguishing infection-triggered from drug-triggered blistering reactions is useful for 3 main reasons: (1) early clinically recognizable different features such as isolated or predominant mucositis, (2) different initial management depending on trigger, (3) avoiding the label of a drug reaction on cases triggered by infection.