Melanoma is one of the top 5 cancer types, causes most deaths among skin cancers, and can be frequently misdiagnosed. Recent pathology image foundation models remain difficult to make accurate differential diagnosis across over forty melanocytic neoplasm histologic subtypes. Motivated by the diagnostic reasoning process of dermatopathologists, we curated a high-quality image and knowledge corpus database containing 2893 images and 1102 knowledge entries annotated by expert dermatopathologists at the University of Pennsylvania. Leveraging this multi-modal dataset, we present "Melan-Dx", a knowledge-enhanced AI framework that augments frozen pathology vision-language models through retrieval from a curated vision-knowledge database, improving differential diagnosis at both patch and whole-slide levels. Melan-Dx, at its best performance, demonstrates 0.869 accuracy for binary classification, 0.699 Top-1 accuracy among forty-class classification, 0.915 ROC AUC for few-shot WSI tasks, and 0.925 AUPRC for fully supervised WSI tasks. Across all experimental settings, Melan-Dx shows improvements up to 13.8% over linear and fully finetuned methods, 23-70.6% over zero-shot approaches and up to 8.4% improvements in whole slide image classification. These findings suggest that a query database with a knowledge-enhanced AI framework can further improve existing pathology foundation models without fine-tuning the vision backbone. The code is publicly available at https://www.github.com/zhihuanglab/Melan-Dx-code .

BAP1 inactivated melanocytic tumors (BIMTs) are recognized for their potential for significant morphologic atypia including nuclear atypia, expansile growth, and mitotic activity, making it difficult to form firm morphologic criteria for malignancy. Next generation sequencing (NGS) is becoming increasingly utilized in melanocytic pathology. We conducted a two-phase survey with 26 dermatopathologists from the International Melanoma Pathology Study Group to assess the impact of NGS on diagnostic accuracy and interobserver agreement in 31 BIMTs. After NGS results, interobserver agreement improved from fair on Survey 1 (κ = 0.348) to moderate on Survey 2 (κ = 0.441). Respondents were 1.7 times more likely to be correct on Survey 2 after NGS results (OR = 1.67, 95% CI [1.16-2.44], p = 0.005). When accounting for case variability and difficulty, respondents were 8.7 times more likely to provide a correct diagnosis for a given case (CMH OR = 8.69, 95% CI [4.89-15.44], p < 0.001). Among the 8 BAP1 inactivated melanomas in this study, 3 transitioned from a majority of votes for benign/intermediate grade BIMT to a majority of votes for melanoma after seeing NGS data. Genomic aberrations exclusive to malignant cases included pathogenic variants in TERT-p, CDKN2A, PTEN, and amplification of MYC. Our study suggests NGS has the potential to improve diagnostic accuracy and interobserver agreement for BAP1 inactivated melanocytic tumors. With the advent of increasingly effective therapies for melanoma, there is value in forming a definitive diagnosis of melanoma when appropriate. Additional studies with greater case numbers and follow-up are needed to further validate these findings.

Half of the participants in this randomized online experiment of 1655 Australian adults would prefer to not have a wide local excision (WLE) after a completely excised low-risk melanocytic lesion, if offered this option. Using the term ‘low-risk melanocytic neoplasm’ instead of ‘melanoma in situ’ reduced anxiety and the proportion choosing a WLE. Across all label groups, most participants preferred to attend routine 6-monthly clinic visits for follow-up, most likely reflecting the high prevalence of this in the Australian context.

Melanoma is a clinically and genetically heterogeneous malignancy that can recur long after initial treatment. We report the case of a 70-year-old man who presented with metastatic cutaneous melanoma 36 years after the initial diagnosis. Initially diagnosed with nodular melanoma on the left heel at age 34 years, the patient experienced metastatic spread to the left groin lymph nodes by age 36 years, followed by various systemic therapies, including interferon and cytokine therapy, and subsequent observation, over 15 years. Two years before his current presentation, the patient noted a growing mass in his right thigh and an enlarged left inguinal lymph node. Fine-needle aspiration biopsy of the lymph node confirmed the recurrence of melanoma. He subsequently underwent inguinofemoral lymph node dissection and resection of the right thigh mass. Histopathological evaluation revealed melanoma characterized by tumorigenic proliferation of pleomorphic epithelioid and spindle cells with abundant eosinophilic cytoplasm, large nuclei with prominent nucleoli, sparse lymphocyte infiltration, and minimal necrosis, consistent with an initial diagnosis of Spitzoid melanoma. Genetic profiling using targeted next-generation sequencing identified a novel TMEM106B::BRAF fusion, along with CHEK2 and MUTYH mutations. The BRAF fusion supports the diagnosis of Spitz melanoma, a genetically defined subset of Spitzoid melanoma. This case represents the first report of a TMEM106B::BRAF fusion in melanoma, emphasizing the critical role of molecular profiling in diagnosing and managing this malignancy, and suggesting a potential avenue for future therapeutic exploration.

The 5th edition of the World Health Organization Classification of Tumours (WCT) serves as a foundation for global diagnostic standards in tumour pathology. Similar to other volumes in this series, the Skin Tumours (Skin5) edition follows a standardized approach. This edition introduces two new chapters: 'Tumours of the nail unit' and 'Metastases to skin', along with new entities across relevant chapters. This review article provides an overview of the updates in Skin5 based on currently published evidence, with emphasis on newly introduced chapters and newly described entities that involve the skin, in particular, epidermal, melanocytic and appendageal tumours.

Immunohistochemical (IHC) stains play a vital role in a pathologist's analysis of medical images, providing crucial diagnostic information for various diseases. However, obtaining IHC staining is not always readily available and often costly. Virtual staining from hematoxylin and eosin (H&E)-stained whole slide images (WSIs) produces useful IHC stains without the expensive physical staining process. However, current virtual WSI generation methods based on tile-wise processing often suffer from inconsistencies in content, texture’ and color at tile boundaries. These inconsistencies lead to artifacts that compromise image quality and potentially hinder the adoption of virtual WSI and accurate clinical assessment. To address this limitation, this paper proposes a novel consistent whole slide image (WSI) synthesis network, CC-WSI-Net, which generates seamless and realistic synthetic WSIs from hematoxylin and eosin (H&E)-stained images. Our method addresses the limitations of current virtual WSI generation methods by integrating a content and color consistency supervisor, ensuring consistency across tiles and accurate detection of clinically relevant features. CC-WSI-Net is validated via image quality analysis, detection assessments, and a survey conducted with pathologists. Notably, in 67% of cases, pathologists could not distinguish between traditionally stained slides and the synthetic slides from CC-WSI-Net.

Abstract Purpose: Neoadjuvant anti–PD-1 therapy in melanoma may increase tumor-infiltrating lymphocytes (TIL), and more TIL are associated with better treatment response. A major pathologic response (MPR) in melanoma after neoadjuvant anti–PD-1 therapy usually comprises tumor necrosis and fibrosis. The role of TIL in necrotic tumor necrosis (nTIL) has not been explored. Experimental Design: We performed CD3 and CD8 IHC stains on 41 melanomas with geographic necrosis. Of the 41, 14 were immunotherapy-naïve, and 27 had been treated with one dose of neoadjuvant anti–PD-1 in two clinical trials. CD3+ and CD8+ nTIL were graded as absent/minimal or moderate/brisk. The percentage of necrotic areas in the tumor bed before and after treatment was quantified. The endpoints were MPR and 5-year recurrence-free survival (RFS). Results: In the immunotherapy-naïve cohort, 3/14 (21%) specimens had moderate/brisk CD3+, and 2/14 (14%) had moderate/brisk CD8+ nTIL. In the treated cohort, 16/27 (59%) specimens had moderate/brisk CD3+, and 15/27 (56%) had moderate/brisk CD8+ nTIL, higher than those of the naïve cohort (CD3, P = 0.046; CD8, P = 0.018). Tumor necrosis was significantly increased after anti–PD-1 therapy (P = 0.007). In the treated cohort, moderate/brisk CD3+ and CD8+ nTIL correlated with MPR (P = 0.042; P = 0.019, respectively). Treated patients with moderate/brisk CD3+ nTIL had higher 5-year RFS than those with absent/minimal nTIL (69% vs. 0%; P = 0.006). This persisted on multivariate analysis (HR, 0.16; 95% confidence interval, 0.03–0.84; P = 0.03), adjusted for pathologic response, which was borderline significant (HR, 0.26; 95% confidence interval, 0.07–1.01; P = 0.051). Conclusions: CD3+ and CD8+ nTIL are associated with pathologic response and 5-year RFS in patients with melanoma after neoadjuvant anti–PD-1 therapy.

Next-generation sequencing (NGS) is increasingly being utilized as an ancillary tool for diagnostically challenging melanocytic neoplasms. It is incumbent upon the pathology community to perform studies assessing the benefits and limitations of these tools in specific diagnostic scenarios. One of the most challenging diagnostic scenarios faced by skin pathologists involves accurate diagnosis of desmoplastic melanocytic neoplasms (DMNs). In this study, 20 expert melanoma pathologists rendered a diagnosis on 47 DMNs based on hematoxylin and eosin sections with demographic information. After submitting their diagnosis, the experts were given the same cases, but this time with comprehensive genomic sequencing results, and asked to render a diagnosis again. Identification of desmoplastic melanoma (DM) improved by 7%, and this difference was statistically significant ( P <0.05). In addition, among the 15 melanoma cases, in the pregenomic assessment, only 12 were favored to be DM by the experts, while after genomics, this improved to 14 of the cases being favored to be DM. In fact, some cases resulting in metastatic disease had a substantial increase in the number of experts recognizing them as DM after genomics. The impact of the genomic findings was less dramatic among benign and intermediate-grade desmoplastic tumors (BIDTs). Interobserver agreement also improved, with the Fleiss multirater Kappa being 0.36 before genomics to 0.4 after genomics. NGS has the potential to improve diagnostic accuracy in the assessment of desmoplastic melanocytic tumors. The degree of improvement will be most substantial among pathologists with some background and experience in bioinformatics and melanoma genetics.

The incidence of melanoma has risen rapidly, at least until recently, while the mortality rate has changed only a little, a phenomenon suggestive of overdiagnosis, which can be defined as the diagnosis as "melanoma" of a lesion that would not have had the competence to cause death or symptoms even if it had not been excised. Overdiagnosis has been attributed to efforts at early diagnosis ("overdetection") and to changes in criteria resulting in diagnosis as melanoma of lesions previously termed nevi ("overdefinition"). In terms of overdefinition, there is evidence that criteria for the histopathologic diagnosis of melanoma have changed over a period of approximately two decades. Specialization may play a role in overdefinition; research has shown that when pathologists interpret the same lesion, dermatopathologists are more likely to diagnose low-stage (American Joint Committee on Cancer T1a) melanomas and general and/or surgical pathologists are more likely to diagnose atypical nevi. An important subset that contributes to overdiagnosis is melanomas that lack the property of tumorigenic vertical growth phase, thus lacking metastatic competence and perhaps not warranting diagnosis as overt melanomas. Studies have defined subsets of patients with very low-stage lesions diagnosed as melanomas in which observed survival has been 100%. In the past, many of these lesions would have been diagnosed as nevi, constituting overdefinition. Other key characteristics for very low-risk (or no-risk) lesions that are currently termed invasive "melanomas" include low Breslow thickness, Clark's level II invasion, absence of mitoses, and clinically, lack of observed or experienced dynamic changes. We propose a provisional terminology for diagnosing extremely low-risk subgroups as "melanocytic neoplasms of low malignant potential," aimed at reducing the negative personal and social effects of a cancer diagnosis for patients whose health and wellbeing are in reality not affected by an overdiagnosed "melanoma." With additional confirmation and appropriate consensus, it is likely that some of these subgroups can be reclassified as atypical or dysplastic nevi.

BACKGROUND:A common terminology for diagnosis is critically important for clinical communication, education, research and artificial intelligence. Prevailing lexicons are limited in fully representing skin neoplasms. OBJECTIVES:To achieve expert consensus on diagnostic terms for skin neoplasms and their hierarchical mapping. METHODS:Diagnostic terms were extracted from textbooks, publications and extant diagnostic codes. Terms were hierarchically mapped to super-categories (e.g. 'benign') and cellular/tissue-differentiation categories (e.g. 'melanocytic'), and appended with pertinent-modifiers and synonyms. These terms were evaluated using a modified-Delphi consensus approach. Experts from the International-Skin-Imaging-Collaboration (ISIC) were surveyed on agreement with terms and their hierarchical mapping; they could suggest modifying, deleting or adding terms. Consensus threshold was >75% for the initial rounds and >50% for the final round. RESULTS:Eighteen experts completed all Delphi rounds. Of 379 terms, 356 (94%) reached consensus in round one. Eleven of 226 (5%) benign-category terms, 6/140 (4%) malignant-category terms and 6/13 (46%) indeterminate-category terms did not reach initial agreement. Following three rounds, final consensus consisted of 362 terms mapped to 3 super-categories and 41 cellular/tissue-differentiation categories. CONCLUSIONS:We have created, agreed upon, and made public a taxonomy for skin neoplasms and their hierarchical mapping. Further study will be needed to evaluate the utility and completeness of the lexicon.

The new revised MPATH-Dx (Version 2.0) reporting schema for melanocytic lesions is presented herein. Principal changes include the simplification of the previous five-class Version 1.0 to a four-class hierarchy of melanocytic lesions to improve diagnostic agreement and to provide more explicit guidance in the management of patients. Version 2.0 also has clearly defined histopathological criteria for classification of Class I and II lesions now designated as low-grade (mild to moderate) atypia and high-grade (high-end moderate to severe) atypia, respectively. This new revised schema, also includes specific provisions for the less common WHO pathways to melanoma, provides guidance for classifying “intermediate” Class II tumors (melanocytomas), and recognizes a subset of pT1a melanomas with very low risk and possible eventual reclassification as a neoplasm falling short of fully-evolved melanoma.

During the illustrious career of Martin C. Mihm Jr., MD, the diagnosis of melanoma underwent significant changes, to which he made many contributions. In early descriptions, melanomas were fungating tumor masses that were obviously malignant, and highly lethal. In seminal work by Dr. Mihm and his mentor, Wallace H. Clark, Jr., MD, the early phases of development of these neoplasms were recognized and distinguished from the more advanced disease. It was generally believed that the early stage of melanoma, termed radial growth phase (RGP) and characterized by absence of vertical growth phase (VGP) and by favorable microstaging attributes could be recognized, excised, and cured, thus preventing the development of advanced disease. However, strenuous efforts in this direction over several decades have resulted in little or no change in mortality, leading to the recognition that many of these neoplasms, at least, may not be true biological malignancies, and to the conclusion that overdiagnosis commonly occurs in this disease, which is defined as representing diagnosis as melanoma of a neoplasm that would not have had the capacity to cause death or symptoms in the lifetime of the host. Although there may be other subsets of neoplasms in this category, an important category of overdiagnosis in melanomas is concentrated in T1a melanomas that lack VGP. If these neoplasms can be recognized with sensitive and specific criteria, which may already be available, changes in terminology may be appropriate, recognizing that some of them may have low malignant potential, whereas others may have no capacity at all for metastasis and may not warrant the use of the term "melanoma."

ImportancePathologic assessment to diagnose skin biopsies, especially for cutaneous melanoma, can be challenging, and immunohistochemistry (IHC) staining has the potential to aid decision-making. Currently, the temporal trends regarding the use of IHC for the examination of skin biopsies on a national level have not been described.ObjectiveTo illustrate trends in the use of IHC for the examination of skin biopsies in melanoma diagnoses.Design, Setting, and ParticipantsA retrospective cross-sectional study was conducted to examine incident cases of melanoma diagnosed between January 2000 and December 2017. The analysis used the SEER-Medicare linked database, incorporating data from 17 population-based registries. The study focused on incident cases of in situ or malignant melanoma of the skin diagnosed in patients 65 years or older. Data were analyzed between August 2022 and November 2023.Main Outcomes and MeasuresThe main outcomes encompassed the identification of claims for IHC within the month of melanoma diagnoses and extending up to 14 days into the month following diagnosis. The SEER data on patients with melanoma comprised demographic, tumor, and area-level characteristics.ResultsThe final sample comprised 132 547 melanoma tumors in 116 117 distinct patients. Of the 132 547 melanoma diagnoses meeting inclusion criteria from 2000 to 2017, 43 396 cases had accompanying IHC claims (33%). Among these cases, 28 298 (65%) were diagnosed in male patients, 19 019 (44%) were diagnosed in patients aged 65 years to 74 years, 16 444 (38%) in patients aged 75 years to 84 years, and 7933 (18%) in patients aged 85 years and older. In 2000, 11% of melanoma cases had claims for IHC at or near the time of diagnosis. This proportion increased yearly, with 51% of melanoma cases having associated IHC claims in 2017. Increasing IHC use is observed for all stages of melanoma, including in situ melanoma. Claims for IHC in melanomas increased in all 17 SEER registries but at different rates. In 2017, the use of IHC for melanoma diagnosis ranged from 39% to 68% across registries.Conclusions and RelevanceConsidering the dramatically rising and variable use of IHC in diagnosing melanoma by pathologists demonstrated in this retrospective cross-sectional study, further investigation is warranted to understand the clinical utility and discern when IHC most improves diagnostic accuracy or helps patients.

Drivers of Spitz neoplasms include activating point mutations in HRAS and Spitz-associated genomic fusions. It has become evident that some BRAF -mutated melanocytic neoplasms can morphologically mimic Spitz tumors (STs). These have been termed BRAF mutated and morphologically spitzoid (BAMS). In this study, 17 experts from the International Melanoma Pathology Study Group assessed 54 cases which included 40 BAMS and 14 true STs. The participants reviewed the cases blinded to the genomic data and selected among several diagnostic options, including BAMS, ST, melanoma, and other. A total of 38% of all diagnostic selections in the BAMS cases were for BAMS, whereas 32% were for ST. In 22 of the BAMS cases, the favored diagnosis was BAMS, whereas in 17 of the BAMS cases, the favored diagnosis was ST. Among the 20 cases in the total group of 54 with the highest number of votes for ST, half were BAMS. Of BAMS, 75% had a number of votes for ST that was within the SD of votes for ST seen among true ST cases. There was poor interobserver agreement for the precise diagnosis of the BAMS (kappa = 0.16) but good agreement that these cases were not melanoma (kappa = 0.7). BAMS nevi/tumors can closely mimic Spitz neoplasms. Expert melanoma pathologists in this study favored a diagnosis of ST in nearly half of the BAMS cases. There are BAMS cases that even experts cannot morphologically distinguish from true Spitz neoplasms.

All supplemental data (Supp Figs S1-S4)

As more data become available, the Banff 2007 working classification of skin-containing vascularized composite allograft (VCA) pathology is expected to evolve and develop. This report represents the Banff VCA Working Group's consensus on the first revision of the 2007 scoring system. Prior to the 2022 Banff-CanXadian Society of Transplantation Joint Meeting, 83 clinicians and/or researchers were invited to a virtual meeting to discuss whether the 2007 Banff VCA system called for a revision. Unanimously, it was determined that the vascular changes were to be included in the first revision. Subsequently, 2 international online surveys, each followed by virtual discussions, were launched. The goals were (1) to identify which changes define severe rejection, (2) to grade their importance in the evaluation of severe rejection, and (3) to identify emerging criteria to diagnose rejection. A final hybrid (in-person and virtual) discussion at the Banff/Canadian Society of Transplantation Joint Meeting finalized the terminology, the definition, a scoring system, and a reporting system of the vascular changes. This proposal represents an international consensus on this topic and establishes the first revision of the Banff 2007 working classification of skin-containing vascularized composite allograft pathology.

PURPOSEThe purpose of this study was to develop recommendations for the diagnostic evaluation and surgical management of cutaneous melanoma (CM) and atypical Spitz tumors (AST) and non-Spitz melanocytic tumors (melanocytomas) in pediatric (age 0-10 years) and adolescent (age 11-18 years) patients.METHODSA Children's Oncology Group-led panel with external, multidisciplinary CM specialists convened to develop recommendations on the basis of available data and expertise.RESULTSThirty-three experts from multiple specialties (cutaneous/medical/surgical oncology, dermatology, and dermatopathology) established recommendations with supporting data from 87 peer-reviewed publications.RECOMMENDATIONS(1) Excisional biopsies with 1-3 mm margins should be performed when feasible for clinically suspicious melanocytic neoplasms. (2) Definitive surgical treatment for CM, including wide local excision and sentinel lymph node biopsy (SLNB), should follow National Comprehensive Cancer Network Guidelines in the absence of data from pediatric-specific surgery trials and/or cohort studies. (3) Accurate classification of ASTs as benign or malignant is more likely with immunohistochemistry and next-generation sequencing. (4) It may not be possible to classify some ASTs as likely/definitively benign or malignant after clinicopathologic and/or molecular correlation, and these Spitz tumors of uncertain malignant potential should be excised with 5 mm margins. (5) ASTs favored to be benign should be excised with 1- to 3-mm margins if transected on biopsy. (6) Re-excision is not necessary if the AST does not extend to the biopsy margin(s) when complete/excisional biopsy was performed. (7) SLNB should not be performed for Spitz tumors unless a diagnosis of CM is favored on clinicopathologic evaluation. (8) Non-Spitz melanocytomas have a presumed increased risk for progression to CM and should be excised with 1- to 3-mm margins if transected on biopsy. (9) Re-excision of non-Spitz melanocytomas is not necessary if the lesion is completely excised on biopsy.