Deep learning for dermatologists: Part II. Current applications.

Because of a convergence of the availability of large data sets, graphics-specific computer hardware, and important theoretical advancements, artificial intelligence has recently contributed to dramatic progress in medicine. One type of artificial intelligence known as deep learning has been particularly impactful for medical image analysis. Deep learning applications have shown promising results in dermatology and other specialties, including radiology, cardiology, and ophthalmology. The modern clinician will benefit from an understanding of the basic features of deep learning to effectively use new applications and to better gauge their utility and limitations. In this second article of a 2-part series, we review the existing and emerging clinical applications of deep learning in dermatology and discuss future opportunities and limitations. Part 1 of this series offered an introduction to the basic concepts of deep learning to facilitate effective communication between clinicians and technical experts.

Deep learning for dermatologists: Part I. Fundamental concepts.

Artificial intelligence is generating substantial interest in the field of medicine. One form of artificial intelligence, deep learning, has led to rapid advances in automated image analysis. In 2017, an algorithm demonstrated the ability to diagnose certain skin cancers from clinical photographs with the accuracy of an expert dermatologist. Subsequently, deep learning has been applied to a range of dermatology applications. Although experts will never be replaced by artificial intelligence, it will certainly affect the specialty of dermatology. In this first article of a 2-part series, the basic concepts of deep learning will be reviewed with the goal of laying the groundwork for effective communication between clinicians and technical colleagues. In part 2 of the series, the clinical applications of deep learning in dermatology will be reviewed and limitations and opportunities will be considered.

Evolution of Dupilumab-Associated Cutaneous Atypical Lymphoid Infiltrates.

BACKGROUND: Observations highlighting the "unmasking" of cutaneous T-cell lymphoma after treatment with dupilumab for atopic dermatitis (AD) have been recently reported. However, there remains a paucity of literature describing the evolution of clinical and histopathological features that characterizes this phenomenon. OBJECTIVE: To define the clinical and histopathologic evolution of atypical lymphoid infiltrates after the administration of dupilumab for AD. METHODS: A cross-sectional study of clinical and histopathologic features in 7 consecutive patients with a diagnosis of "atypical lymphoid infiltrate" or mycosis fungoides (MF) on dupilumab for AD was performed. RESULTS: Seven patients with atypical lymphoid infiltrates or MF in evolution after dupilumab therapy (age range 27-74 years) were reviewed. Average duration of AD before MF diagnosis was 5.7 years, and the average duration on dupilumab treatment was 9.8 months. Notable histopathologic features across predupilumab and postdupilumab biopsies included progressive increase in the densities of the atypical lymphoid infiltrates (7/7), presence of atypical epidermotropic lymphocytes (6/7), and papillary dermal fibrosis (6/7). LIMITATIONS: Small retrospective cohort study. CONCLUSION: These cases highlight the transformation of lymphoid infiltrates after dupilumab treatment for AD and emphasize the importance of clinical and histopathologic evaluation before and during treatment with dupilumab for treatment-refractory presumed AD.

Acneiform Presentations of Folliculotropic Mycosis Fungoides.

BACKGROUND: Folliculotropic mycosis fungoides (FMF) is a variant of cutaneous T-cell lymphoma that has clinical overlap with a variety of inflammatory follicular unit disorders. However, we describe distinctive presentations of FMF with acneiform features that can be diagnostically challenging, leading to diagnostic delay. OBJECTIVE: To highlight the importance of histopathologic and immunohistochemical evaluation for diagnostic confirmation of presumed inflammatory follicular unit-based disorders that are unusual in presentation or unresponsive to standard therapies. METHODS: A cross-sectional retrospective study of 5 consecutive patients with a histopathologic diagnosis of FMF was conducted. The clinical, histopathologic, immunophenotypic, and molecular genetic features of cases are presented. RESULTS: We describe 5 patients with clinical and histopathologic presentations of FMF masquerading as hidradenitis suppurativa, furunculosis, or acne vulgaris (age range 34-66 years, 4:1 female to male). Clinical morphologies included open and closed comedones, inflammatory pustules, papules and nodules, follicular papules with keratotic plugging, cysts, and scarring involving the face, trunk, and intertriginous areas. All patients failed to respond to standard therapies, including topical and oral antibiotics, topical and oral retinoids, or topical corticosteroids, before receiving the diagnosis of FMF. Lesional skin biopsies showed a perifollicular CD4-positive T-lymphocytic infiltrate with pilotropism, intrafollicular mucin deposition, foreign-body granulomatous inflammation, acute inflammation, and follicular epithelial necrosis. None had concurrent systemic mycosis fungoides. LIMITATIONS: Small retrospective cohort study. CONCLUSION: We present these cases to expand the clinical and histopathologic spectrum of FMF that may strikingly resemble acneiform disorders and to highlight the importance of diagnostic reconsideration with histopathologic evaluation.

Mycosis fungoides with spongiosis: A potential diagnostic pitfall.

BACKGROUND: Mycosis fungoides (MF) is characterized by epidermotropic atypical lymphocytes in the absence of spongiosis. However, we describe an unusual presentation of MF with spongiosis, mimicking benign inflammatory dermatoses and highlight the importance of pathologic interpretation for diagnostic confirmation. METHODS: A cross-sectional study of consecutive patients diagnosed with MF with spongiosis was conducted. The clinical, histopathologic, immunophenotypic, and molecular genetic features of cases were reviewed. RESULTS: We identified nine cases of MF (age range 34-82 years; mean 75 years), with an initial diagnosis of dermatitis (6/9), psoriasis (4/9), or other inflammatory dermatoses (2/9). Pruritus, pain, and blisters were common clinical manifestations. The most common areas of involvement were the extremities (8/9). Epidermotropism with spongiosis was a central histopathological feature in all cases. CONCLUSION: These cases highlight prominent spongiosis in MF and overlap with common benign inflammatory dermatoses. We present these cases to show the diagnostic pitfalls associated with spongiotic presentations of MF. Dermatitis, psoriasis, and other inflammatory skin conditions not responsive to standard therapy warrant further work-up including biopsy to rule out MF. Multiple skin biopsies and review by a dermatopathologist with expertise in the diagnosis of cutaneous lymphoma is highly recommended.

Premature Graying of Hair: Review with Updates.

Premature graying of hair (PGH) is defined as graying of hair before the age of 20 years in Caucasians and before 30 years in African American population. It can severely affect the self-esteem of an individual. The exact etiopathogenesis remains unknown, although it has been associated with premature aging disorders, atopy, and autoimmune diseases. Patients, who present with PGH, should be assessed for syndromes and metabolism diseases. Hair dyes remain the main modality of the treatment for cosmetic concerns after nutritional supplementation.

Neurodevelopmental outcomes of premature infants at a tertiary care center in Pakistan.

The low gestational ages and morbidities of premature neonates in neonatal intensive care units exert a significant impact on neurodevelopmental outcomes. This longitudinal cohort study assessed the neurodevelopmental status of premature neonates after discharge from neonatal intensive care units in resource-limited countries such as Pakistan. Developmental assessment involved the Denver Development Screening Test II. One hundred and ten infants discharged from our neonatal intensive care unit completed follow-up at age 6 months. Overall developmental delay was evident in 32% of infants. Birth weight and gestational age exerted significant impacts on development. The mean gestational age of developmentally normal infants was 34 weeks, whereas that of delayed infants was 30.7 weeks (P < 0.01). The mean birth weight of developmentally normal infants was 2.17 kg vs 1.27 kg in delayed infants (P < 0.01). Neonates who developed complications such as respiratory distress syndrome, intraventricular hemorrhage, thrombocytopenia, hypoglycemia, hyponatremia, or hypothermia in neonatal intensive care units proved to be delayed at age 6 months (P < 0.05). Prematurity and its associated complications are linked to adverse neurodevelopmental outcomes.

Morbidity pattern of sick hospitalized preterm infants in Karachi, Pakistan.

Despite recent advances, prematurity is associated with high morbidity and mortality in developing countries. We conducted a descriptive case series to identify frequency of various morbidities in premature neonates at Aga Khan University Hospital (AKUH), Karachi, from November 2008 to April 2009. All inborn premature < or = 37 weeks gestation were included in study. The frequency of preterm birth during study period was 13.3% (251/1885) of which 58% (n = 145) required admission in Neonatal Intensive Care Unit (NICU). Mean gestational age was 33 +/- 2.4 weeks and mean birth weight, was 1.88 +/- 0.5 kg. 25% of patients were small for gestational age (SGA) while 75% appropriate for gestational age (AGA). Metabolic derangement was the most common morbidity, observed in 93% of patients followed by sepsis, seen in 43.6% neonates. Respiratory distress syndrome was observed in 35.5% of neonates while intraventricular haemorrhage was seen only in 3.5% patients. Mean length of stay for preterm infants in NICU was 11.5 +/- 9.6 days, 14% (n = 20) preterm neonates expired during NICU stay.