Deep learning model shows pathologist-level detection of sentinel node metastasis of melanoma and intra-nodal nevi on whole slide images.

Introduction: Nodal metastasis (NM) in sentinel node biopsies (SNB) is crucial for melanoma staging. However, an intra-nodal nevus (INN) may often be misclassified as NM, leading to potential misdiagnosis and incorrect staging. There is high discordance among pathologists in assessing SNB positivity, which may lead to false staging. Digital whole slide imaging offers the potential for implementing artificial intelligence (AI) in digital pathology. In this study, we assessed the capability of AI to detect NM and INN in SNBs. Methods: A total of 485 hematoxylin and eosin whole slide images (WSIs), including NM and INN from 196 SNBs, were collected and divided into training (279 WSIs), validation (89 WSIs), and test sets (117 WSIs). A deep learning model was trained with 5,956 manual pixel-wise annotations. The AI and three blinded dermatopathologists assessed the test set, with immunohistochemistry serving as the reference standard. Results: The AI model showed excellent performance with an area under the curve receiver operating characteristic (AUC) of 0.965 for detecting NM. In comparison, the AUC for NM detection among dermatopathologists ranged between 0.94 and 0.98. For the detection of INN, the AUC was lower for both AI (0.781) and dermatopathologists (range of 0.63-0.79). Discussion: In conclusion, the deep learning AI model showed excellent accuracy in detecting NM, achieving dermatopathologist-level performance in detecting both NM and INN. Importantly, the AI model showed the potential to differentiate between these two entities. However, further validation is warranted.

Langerhans Cells, T Cells, and B Cells in Oral Lichen Planus and Oral Leukoplakia.

Although oral lichen planus (OLP) and oral leukoplakia (LPL) have different pathogenetic profiles, both may involve chronic inflammation. The aim of this observational study was to evaluate the inflammatory cell profiles of OLP and LPL. The inflammatory cell infiltrates in patients with OLP and LPL were analyzed for the presence of Langerhans cells (LCs; CD1a), T cells (CD3), and B cells (CD20), as well as for the proliferation marker Ki-67. Biopsied specimens from patients with OLP (N = 14) and LPL without dysplasia (N = 13) were immunohistochemically stained with antibodies directed against CD1a, CD3, CD20, and Ki-67, followed by quantitative analyses. A significant increase in the number of CD3+ cells and CD20+ cells was found in the submucosa of OLP, as compared to LPL (p < 0.01). Likewise, the number of CD3+ cells was significantly higher in the epithelium of OLP than of LPL (p < 0.05). No differences were found in the expression of Ki-67 and the number of CD1a+ cells between the two groups. Although an immune response is elicited in both conditions, there are differences at the cellular level between OLP and LPL. A more robust immune activation involving T cells and B cells is seen in OLP. The role of B cells in OLP needs to be further elucidated. Although the number of B cells in LPL is low, their role in the inflammatory response cannot be ruled out.