Recent incidence patterns of cutaneous T-cell lymphoma (CTCL) in the US are not well described. We sought to describe recent incidence trends by tumor subtype, sex, age, race and ethnicity, socioeconomic status (SES), and geography.Methods | Incidence data were derived from 18 populationbased registries of the Surveillance, Epidemiology, and End Results (SEER) Program for 2000 to 2018. We included histologically confirmed cases of first primary CTCL with malignant behavior and primary site of involvement skin (C44.0-C44.9). Patient characteristics included sex, age, race and ethnicity, and geographic region (metropolitan vs nonmetropolitan counties). 1 Area-level SES information was available from 2000 to 2016 and was categorized into quintile; Q1 lowest, Q5 highest. 2 We used the 2000 US standard population to calculate age-adjusted annual incidence rates (IR) per million people. Annual percent change (APC) was calculated by using the weighted least squares method. Statistical calculations used SEER*Stat statistical software (version 8.3.9.2) in January 2022. The Stanford institutional review board deemed this study exempt from review and waived the requirement for patient informed consent because only deidentified data were used.Results | We identified 14 942 new cases of CTCL from 2000 to 2018. Table 1 shows the number of cases, IR, and APC of IR of CTCL by International Statistical Classification of Diseases and Related Health Problems for Oncology (ICD-O) diagnosis. Mycosis fungoides (MF) was the most common diagnosis, followed by primary CTCL (PCTCL) and primary cutaneous ana-
Pyoderma gangrenosum is often associated with a systemic disease. Cocaine-induced pyoderma gangrenosum, most probably caused by levamisole, has been described recently and typically presents as multiple, large cribriform ulcers. Peri-nuclear antineutrophil cytoplasmic antibody is the most common serological finding. A strong counseling for cocaine cessation, combined with wound care and immunosuppressive therapy, is the mainstay of treatment. We present two cases of cocaine-induced pyoderma gangrenosum and correlate their findings with the typical clinical, histological and serological presentation.
Despite the proliferation and clinical deployment of artificial intelligence (AI)-based medical software devices, most remain black boxes that are uninterpretable to key stakeholders including patients, physicians, and even the developers of the devices. Here, we present a general model auditing framework that combines insights from medical experts with a highly expressive form of explainable AI that leverages generative models, to understand the reasoning processes of AI devices. We then apply this framework to generate the first thorough, medically interpretable picture of the reasoning processes of machine-learning–based medical image AI. In our synergistic framework, a generative model first renders "counterfactual" medical images, which in essence visually represent the reasoning process of a medical AI device, and then physicians translate these counterfactual images to medically meaningful features. As our use case, we audit five high-profile AI devices in dermatology, an area of particular interest since dermatology AI devices are beginning to achieve deployment globally. We reveal how dermatology AI devices rely both on features used by human dermatologists, such as lesional pigmentation patterns, as well as multiple, previously unreported, potentially undesirable features, such as background skin texture and image color balance. Our study also sets a precedent for the rigorous application of explainable AI to understand AI in any specialized domain and provides a means for practitioners, clinicians, and regulators to uncloak AI's powerful but previously enigmatic reasoning processes in a medically understandable way.
Building trustworthy and transparent image-based medical AI systems requires the ability to interrogate data and models at all stages of the development pipeline: from training models to post-deployment monitoring. Ideally, the data and associated AI systems could be described using terms already familiar to physicians, but this requires medical datasets densely annotated with semantically meaningful concepts. Here, we present a foundation model approach, named MONET (Medical cONcept rETriever), which learns how to connect medical images with text and generates dense concept annotations to enable tasks in AI transparency from model auditing to model interpretation. Dermatology provides a demanding use case for the versatility of MONET, due to the heterogeneity in diseases, skin tones, and imaging modalities. We trained MONET on the basis of 105,550 dermatological images paired with natural language descriptions from a large collection of medical literature. MONET can accurately annotate concepts across dermatology images as verified by board-certified dermatologists, outperforming supervised models built on previously concept-annotated dermatology datasets. We demonstrate how MONET enables AI transparency across the entire AI development pipeline from dataset auditing to model auditing to building inherently interpretable models.
Hypomelanosis of Ito was first described by Minor Ito in 1952 in a 22-year-old woman with linear symmetric hypopigmentation of her trunk and arms. 1 Over the years, hypomelanosis of Ito became an umbrella term referring to cutaneous hypopigmentation along Blaschko's lines, presenting with or without associated extracutaneous findings in various systems, particularly neurological, skeletal, and ophthalmological. 2 Diagnostic criteria have been proposed by Ruiz-Maldonado and al. in 1992, 3 but no consensus or formal definition has been adopted to this day. Unjustified investigations for the patient and unnecessary stress for the parents could be avoided with a better delineation of syndromic patterned hypopigmentation.Identification of postzygotic variants in vascular anomalies, such as port-wine stains and Sturge-Weber syndrome (GNAQ), and hamartomatous skin disorders, such as sebaceous nevi and Schimmelpenning syndrome (KRAS and HRAS), 4,5 stimulated the search for the genetic basis of pigmentary mosaicism. To this day, three distinct mosaic hypopigmentation syndromes 6-8 have been identified with postzygotic variants in MTOR, TFE3, and RHOA genes. | C A S E REP ORTA girl born at term by spontaneous delivery to non-consanguineous French-Canadian (Caucasian) parents after an uneventful pregnancy
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.