Symplastic hemangioma (SH) is a rare benign vascular lesion marked by striking nuclear atypia in non-endothelial stromal cells, often mimicking malignancy. It is typically seen in older adults, with only four cases reported to date. Pediatric presentations are exceedingly rare. We present a unique case of limbal SH in a 7-year-old female with xeroderma pigmentosa (XP), who presented with a pigmented conjunctival mass clinically suspected to be malignant. Given the high risk of malignancy in patients with XP-including squamous cell carcinoma and melanoma-SH can pose a diagnostic dilemma. Histological evaluation revealed a polypoidal lesion covered by stratified squamous epithelium, with numerous small blood vessels lined by plump endothelial cells and interspersed bizarre, atypical stromal cells. No necrosis, atypical mitosis, or definitive features of malignancy were identified. Immunohistochemistry showed SMA positivity in the atypical cells, confirming vascular origin, while the Ki-67 index was very low (< 1%), supporting a benign nature. These findings ruled out malignancy despite alarming histological features. To our knowledge, this is the first reported case of limbal SH in a pediatric patient with XP. This case highlights the importance of histopathological and immunohistochemical analysis in distinguishing SH from aggressive vascular tumors and avoiding unnecessary aggressive treatment. It adds valuable insight into the rare spectrum of vascular lesions in XP.

The circadian clock regulates multiple physiological processes in the skin, including local hormone synthesis and pigmentation. However, how circadian regulation interacts with epidermal endocrine signalling in melanocytes remains unclear. In this study, we investigated whether core circadian regulators influence melanogenesis in human melanocytes and explored their potential link to epidermal endocrine factors and pigmentary disease. Primary normal human epidermal melanocytes were analysed following siRNA-mediated knockdown of the core clock genes basic helix-loop-helix ARNT-like protein 1 (BMAL1) and CLOCK circadian regulator (CLOCK). Silencing either gene significantly reduced melanin synthesis and altered the expression of hormone-related factors. Notably, expression of the vitamin D-metabolizing enzyme CYP27A1 was markedly decreased after BMAL1 or CLOCK knockdown, changes that were associated with reduced melanogenic activity. Consistently, immunohistochemical analysis revealed diminished CYP27A1 expression in melanocytes within vitiligo lesions. These findings demonstrate that disruption of circadian clock regulators impairs melanogenesis and is accompanied by alterations in vitamin D-related components. Our results suggest that circadian regulation may modulate pigmentation partly through effects on vitamin D metabolism, providing new insight into the mechanisms underlying pigmentary disorders.

Concept Bottleneck Models (CBMs) are devoted to melanoma classification route predictions through a clinically grounded concept layer, which binds interpretability to concept-label consistency. When a dataset contains concept-level inconsistencies, identical concept profiles mapped to conflicting diagnosis labels create an unresolvable bottleneck that imposes a hard ceiling on achievable accuracy. In this paper, we apply rough set theory to the Derm7pt dermoscopy benchmark and characterize, for the first time, the full extent and clinical structure of this inconsistency. Among 305 unique concept profiles formed by the dermoscopic criteria of the 7-point melanoma checklist, 50 (16.4%) are inconsistent and span 306 images (30.3% of the dataset). This yields a theoretical accuracy ceiling of 92.1% for any hard CBM trained on the full raw data, where over half of all melanoma images carry concept signatures belonging to the boundary region. This disproportionate fraction shows that the checklist concepts are less discriminative for melanoma than for non-melanoma lesions. We characterize the conflict-severity distribution and identify the clinical features most responsible for boundary ambiguity. Two filtering strategies are proposed to remove images with inconsistent concept signatures, both producing a benchmark that we refer to as Derm7pt+. The symmetric strategy yields a fully consistent subset of 705 images, while the asymmetric strategy retains all melanoma images and removes only the conflicting non-melanoma counterparts, producing 841 images. We evaluate a hard CBM across 19 backbone architectures from the EfficientNet, DenseNet, ResNet, and Wide ResNet families on both Derm7pt+ variants. Under symmetric filtering, DenseNet-169 achieves the best test macro F1 of [Formula: see text], and EfficientNet-B4 leads under asymmetric filtering with a test macro F1 of [Formula: see text]. Macro-averaged concept accuracy remains moderate yet stable across all configurations, and this level of concept prediction suffices to produce solid label macro F1 scores. This shows that annotation noise rather than backbone capacity is the binding constraint on bottleneck quality. We further apply the Sparseness-Optimized Feature Importance (SOFI) explainer to the true positive melanoma predictions of the best-performing model on the symmetric Derm7pt+. We found that irregular dots and globules drives every melanoma prediction, while irregular streaks, atypical pigment network, and present blue-whitish veil form a consistent secondary tier.

Supergiant basal cell carcinoma is an exceptionally rare presentation of an otherwise highly curable malignancy and is most often associated with prolonged neglect and limited access to care. We report a case of a 94-year-old man with a long-standing infiltrative facial lesion extending from the right preauricular and temporal region to the nasal sidewall and lower eyelid, associated with ectropion. Dermoscopy revealed blue-gray globules and pigmented ovoid nests, along with white structureless areas and a milky-red background. Biopsy confirmed pigmented basal cell carcinoma. Given advanced local invasion, frailty, and the unavailability of hedgehog pathway inhibitors in the public healthcare system, curative treatment was not feasible, and palliative radiotherapy was initiated. The patient deteriorated and died shortly thereafter; no evidence of metastatic disease was identified, and death was not attributed to basal cell carcinoma. This case highlights how delays in diagnosis and limited access to modern systemic therapies can transform a typically low-mortality cancer into a source of significant morbidity. Strengthening early detection strategies and improving access to guideline-based treatments remain critical to preventing such outcomes.

We report the first autopsy-proven case of colony-stimulating factor 1 receptor (CSF1R)-related leukoencephalopathy harboring the CSF1R mutation c.2320T>C (p.Cys774Arg). The patient, a man in his 40s, exhibited progressive neuropsychiatric symptoms with predominant frontal white matter lesions and corpus callosum atrophy. Neuropathological examination revealed frontal-predominant demyelination with a relatively low number of axonal spheroids compared with typical cases, as well as the absence of intracranial calcifications. In addition, prominent cerebral amyloid angiopathy was observed despite an APOE ε3/ε3 genotype. These findings expand the clinicopathological spectrum of CSF1R-related leukoencephalopathy and highlight variability in pathological features associated with different CSF1R mutations.