A 3-dimensional histology computer model of malignant melanoma and its implications for digital pathology.

BACKGROUND: Historically, cancer diagnoses have been made by pathologists using two-dimensional histological slides. However, with the advent of digital pathology and artificial intelligence, slides are being digitised, providing new opportunities to integrate their information. Since nature is 3-dimensional (3D), it seems intuitive to digitally reassemble the 3D structure for diagnosis. OBJECTIVE: To develop the first human-3D-melanoma-histology-model with full data and code availability. Further, to evaluate the 3D-simulation together with experienced pathologists in the field and discuss the implications of digital 3D-models for the future of digital pathology. METHODS: A malignant melanoma of the skin was digitised via 3 µm cuts by a slide scanner; an open-source software was then leveraged to construct the 3D model. A total of nine pathologists from four different countries with at least 10 years of experience in the histologic diagnosis of melanoma tested the model and discussed their experiences as well as implications for future pathology. RESULTS: We successfully constructed and tested the first 3D-model of human melanoma. Based on testing, 88.9% of pathologists believe that the technology is likely to enter routine pathology within the next 10 years; advantages include a better reflectance of anatomy, 3D assessment of symmetry and the opportunity to simultaneously evaluate different tissue levels at the same time; limitations include the high consumption of tissue and a yet inferior resolution due to computational limitations. CONCLUSIONS: 3D-histology-models are promising for digital pathology of cancer and melanoma specifically, however, there are yet limitations which need to be carefully addressed.

Cuticular Poroma: A Rare Poroma Variant Simulating a Malignant Neoplasm That Often Harbors YAP1::NUTM1 Fusions Similar to Their Conventional Counterparts.

ABSTRACT: Cuticular poroma is a rare variant of poroma composed of exclusively or predominantly cuticular cells, namely of large cells with ample eosinophilic cytoplasm. We report 7 cases of this rare tumor identified among 426 neoplasms diagnosed as poroma or porocarcinoma. The patients were 4 males and 3 females, ranging in age from 18 to 88 years. All presented with a solitary asymptomatic nodule. The location included knee (2 cases), shoulder, thigh, shin, lower arm, and neck (each 1). All lesions were surgically removed. No evidence of disease was observed in 5 patients with available follow-up (range 12-124 months).Microscopically, all neoplasms were composed of variably sized, focally closed packed, or interconnecting nodules constituted mostly of cuticular cells. Small poroid cells were a focal feature in 5 tumors, whereas in the remaining 2 cases, poroid cells with conspicuous but still in minority. Five neoplasms were somewhat asymmetric, with irregular outlines. Ductal differentiation and intracytoplasmic vacuoles were seen in 6 tumors. Other features variably encountered were conspicuous intranuclear pseudoinclusions, cystic change, occasional multinucleated cells, increased mitoses, and stromal desmoplasia. Four of the 5 tumors analyzed with next-generation sequencing yielded YAP1::NUTM1 fusions. In addition, various mutations, mostly of unknown significance were identified in one neoplasm.

Metabolic Signature of Atypical Fibroxanthoma and Pleomorphic Dermal Sarcoma: Expression of Hypoxia-inducible Factor-1α and Several of Its Downstream Targets.

Metabolic reprogramming mediated by hypoxia-inducible factors play a crucial role in many human cancers. HIF-1α is activated under hypoxic conditions and is considered a key regulator of oxygen homoeostasis during tumor proliferation under hypoxia. Aim of this research was to analyze the immunohistochemical expression of HIF-1α, VEGF-A, Glut-1, MCT4, and CAIX in atypical fibroxanthoma (AFX) and pleomorphic dermal sarcoma (PDS). 21 paraffin-embedded AFX and 22 PDS were analysed by immunohistochemistry, namely HIF-1α, VEGF-A (referred to as VEGF throughout the manuscript), Glut-1, MCT4, and CAIX. To quantify the protein expression, we considered the percentage of positive tumor cells (0: 0%, 1: up to 1%, 2: 2-10%, 3: 11-50%, 4: >50%) in relation to the staining intensity (0: negative, 1: low, 2: medium, 3: strong). HIF-1α expression (mean ± SD) in AFX (9.33±2.92) was significantly stronger than that in PDS (5.90±4.38; P= 0.007), whereas the expression of VEGF, Glut-1, MCT4, and CAIX did not show differences between AFX and PDS. When comparing all tumors without subgroup stratification, the expression of HIF-1α (P= 0.044) and MCT4 (P= 0.036) was significantly stronger in ulcerated tumors than in tumors without ulceration. Our findings provide the first evidence that HIF-1α-induced metabolic reprogramming may contribute to the pathogenesis of AFX and PDS. HIF-1α expression seems to be higher in AFX than in PDS, and ulcerated tumors show higher expression levels of HIF-1α and MCT4 irrespective of the diagnosis.

Dataset for the Reporting of Merkel Cell Carcinoma: Recommendations From the International Collaboration on Cancer Reporting (ICCR).

Accurate and complete pathology reports are critical for the optimal management of cancer patients. Protocols for the pathologic reporting of Merkel cell carcinoma (MCC) have been developed independently by the Royal College of Pathologists (UK) and the College of American Pathologists. In this study, data elements for pathologic reporting of MCC were analyzed by an international panel of pathologists and clinicians with the aim of developing a common, internationally agreed upon dataset useful for clinical practice. The International Collaboration on Cancer Reporting expert review panel developed a protocol containing "core" (required) and "noncore" (recommended) elements. Core elements were defined as those that had evidentiary support and were unanimously agreed upon by the review panel as essential for the clinical management, staging, and/or assessment of prognosis in patients with MCC. Noncore elements were those considered to be clinical of interest, but with lesser degrees of supportive evidence or nonactionable implications. Ten core data elements for pathology reports on primary MCC were defined. Development and agreement on this evidence-based protocol at an international level was accomplished in a timely and efficient manner. The template developed for melanoma reporting was used as a structural base for this initiative. It is applicable to, and may facilitate the development of, protocols for other tumor types. Widespread utilization of an internationally agreed upon structured pathology dataset for MCC can be expected to lead to improved patient management. It should also facilitate collaborative clinical research.

A rare case of cutaneous metastasis of distal phalanx chondrosarcoma.

Chondrosarcoma is the second-most common primary malignant bone tumor but chondrosarcoma of small bones of the hand is extremely rare, representing less than 2% of all cases, with exceedingly rare skin metastases. Cutaneous metastases of chondrosarcoma represent less than 3% of all cutaneous metastases. According to PubMed, there are only four previous case reports of cutaneous metastases originating from chondrosarcoma of small bones of the hand. We present an additional case of cutaneous metastases of phalangeal chondrosarcoma with a unique immunophenotype.

Genetic and methylation profiles distinguish benign, malignant and spitzoid melanocytic tumors.

Accurate classification of melanocytic tumors is important for prognostic evaluation, treatment and follow-up protocols of patients. The majority of melanocytic proliferations can be classified solely based on clinical and pathological criteria, however in select cases a definitive diagnostic assessment remains challenging and additional diagnostic biomarkers would be advantageous. We analyzed melanomas, nevi, Spitz nevi and atypical spitzoid tumors using parallel sequencing (exons of 611 genes and 507 gene translocation analysis) and methylation arrays (850k Illumina EPIC). By combining detailed genetic and epigenetic analysis with reference-based and reference-free DNA methylome deconvolution we compared Spitz nevi to nevi and melanoma and assessed the potential for these methods in classifying challenging spitzoid tumors. Results were correlated with clinical and histologic features. Spitz nevi were found to cluster independently of nevi and melanoma and demonstrated a different mutation profile. Multiple copy number alterations and TERT promoter mutations were identified only in melanomas. Genome-wide methylation in Spitz nevi was comparable to benign nevi while the Leukocytes UnMethylation for Purity (LUMP) algorithm in Spitz nevi was comparable to melanoma. Histologically difficult to classify Spitz tumor cases were assessed which, based on methylation arrays, clustered between Spitz nevi and melanoma and in terms of genetic profile or copy number variations demonstrated worrisome features suggesting a malignant neoplasm. Comprehensive sequencing and methylation analysis verify Spitz nevi as an independent melanocytic entity distinct from both nevi and melanoma. Combined genetic and methylation assays can offer additional insights in diagnosing difficult to classify Spitzoid tumors.

Explainable artificial intelligence in skin cancer recognition: A systematic review.

BACKGROUND: Due to their ability to solve complex problems, deep neural networks (DNNs) are becoming increasingly popular in medical applications. However, decision-making by such algorithms is essentially a black-box process that renders it difficult for physicians to judge whether the decisions are reliable. The use of explainable artificial intelligence (XAI) is often suggested as a solution to this problem. We investigate how XAI is used for skin cancer detection: how is it used during the development of new DNNs? What kinds of visualisations are commonly used? Are there systematic evaluations of XAI with dermatologists or dermatopathologists? METHODS: Google Scholar, PubMed, IEEE Explore, Science Direct and Scopus were searched for peer-reviewed studies published between January 2017 and October 2021 applying XAI to dermatological images: the search terms histopathological image, whole-slide image, clinical image, dermoscopic image, skin, dermatology, explainable, interpretable and XAI were used in various combinations. Only studies concerned with skin cancer were included. RESULTS: 37 publications fulfilled our inclusion criteria. Most studies (19/37) simply applied existing XAI methods to their classifier to interpret its decision-making. Some studies (4/37) proposed new XAI methods or improved upon existing techniques. 14/37 studies addressed specific questions such as bias detection and impact of XAI on man-machine-interactions. However, only three of them evaluated the performance and confidence of humans using CAD systems with XAI. CONCLUSION: XAI is commonly applied during the development of DNNs for skin cancer detection. However, a systematic and rigorous evaluation of its usefulness in this scenario is lacking.

[Immunohistochemical analysis of a hypoxia-associated signature in melanomas with positive and negative sentinel lymph nodes : Hypoxia-associated signature of primary cutaneous melanomas]. / Immunhistochemische Analyse einer Hypoxie-assoziierten Signatur in Melanomen mit positivem und negativem Schildwächterlymphknoten : Hypoxie-assoziierte Signatur primär kutaner Melanome.

Metabolic reprogramming mediated by hypoxia-inducible factors and its downstream targets plays a crucial role in many human malignancies. Excessive proliferation of tumor cells under hypoxic conditions leads to metabolic reprogramming and altered gene expression enabling tumors to adapt to their hypoxic environment. Here we analyzed the metabolic signatures of primary cutaneous melanomas with positive and negative sentinel node status in order to evaluate potential differences in their metabolic signature. We found a positive correlation of the expression of glucose transporter 1 (GLUT-1) with tumor thickness and ulceration in all melanomas with subgroup analyses as well as in the subgroup with a negative sentinel node. Furthermore, the expression of vascular endothelial growth factor (VEGF) was positively correlated with the presence of ulceration in melanomas with positive sentinel node.

Rubella vaccine-induced granulomas are a novel phenotype with incomplete penetrance of genetic defects in cytotoxicity.

BACKGROUND: Rubella virus-induced granulomas have been described in patients with various inborn errors of immunity. Most defects impair T-cell immunity, suggesting a critical role of T cells in rubella elimination. However, the molecular mechanism of virus control remains elusive. OBJECTIVE: This study sought to understand the defective effector mechanism allowing rubella vaccine virus persistence in granulomas. METHODS: Starting from an index case with Griscelli syndrome type 2 and rubella skin granulomas, this study combined an international survey with a literature search to identify patients with cytotoxicity defects and granuloma. The investigators performed rubella virus immunohistochemistry and PCR and T-cell migration assays. RESULTS: This study identified 21 patients with various genetically confirmed cytotoxicity defects, who presented with skin and visceral granulomas. Rubella virus was demonstrated in all 12 accessible biopsies. Granuloma onset was typically before 2 years of age and lesions persisted from months to years. Granulomas were particularly frequent in MUNC13-4 and RAB27A deficiency, where 50% of patients at risk were affected. Although these proteins have also been implicated in lymphocyte migration, 3-dimensional migration assays revealed no evidence of impaired migration of patient T cells. Notably, patients showed no evidence of reduced control of concomitantly given measles, mumps, or varicella live-attenuated vaccine or severe infections with other viruses. CONCLUSIONS: This study identified lymphocyte cytotoxicity as a key effector mechanism for control of rubella vaccine virus, without evidence for its need in control of live measles, mumps, or varicella vaccines. Rubella vaccine-induced granulomas are a novel phenotype with incomplete penetrance of genetic disorders of cytotoxicity.

Skin cancer classification via convolutional neural networks: systematic review of studies involving human experts.

BACKGROUND: Multiple studies have compared the performance of artificial intelligence (AI)-based models for automated skin cancer classification to human experts, thus setting the cornerstone for a successful translation of AI-based tools into clinicopathological practice. OBJECTIVE: The objective of the study was to systematically analyse the current state of research on reader studies involving melanoma and to assess their potential clinical relevance by evaluating three main aspects: test set characteristics (holdout/out-of-distribution data set, composition), test setting (experimental/clinical, inclusion of metadata) and representativeness of participating clinicians. METHODS: PubMed, Medline and ScienceDirect were screened for peer-reviewed studies published between 2017 and 2021 and dealing with AI-based skin cancer classification involving melanoma. The search terms skin cancer classification, deep learning, convolutional neural network (CNN), melanoma (detection), digital biomarkers, histopathology and whole slide imaging were combined. Based on the search results, only studies that considered direct comparison of AI results with clinicians and had a diagnostic classification as their main objective were included. RESULTS: A total of 19 reader studies fulfilled the inclusion criteria. Of these, 11 CNN-based approaches addressed the classification of dermoscopic images; 6 concentrated on the classification of clinical images, whereas 2 dermatopathological studies utilised digitised histopathological whole slide images. CONCLUSIONS: All 19 included studies demonstrated superior or at least equivalent performance of CNN-based classifiers compared with clinicians. However, almost all studies were conducted in highly artificial settings based exclusively on single images of the suspicious lesions. Moreover, test sets mainly consisted of holdout images and did not represent the full range of patient populations and melanoma subtypes encountered in clinical practice.

Integrating Patient Data Into Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review.

BACKGROUND: Recent years have been witnessing a substantial improvement in the accuracy of skin cancer classification using convolutional neural networks (CNNs). CNNs perform on par with or better than dermatologists with respect to the classification tasks of single images. However, in clinical practice, dermatologists also use other patient data beyond the visual aspects present in a digitized image, further increasing their diagnostic accuracy. Several pilot studies have recently investigated the effects of integrating different subtypes of patient data into CNN-based skin cancer classifiers. OBJECTIVE: This systematic review focuses on the current research investigating the impact of merging information from image features and patient data on the performance of CNN-based skin cancer image classification. This study aims to explore the potential in this field of research by evaluating the types of patient data used, the ways in which the nonimage data are encoded and merged with the image features, and the impact of the integration on the classifier performance. METHODS: Google Scholar, PubMed, MEDLINE, and ScienceDirect were screened for peer-reviewed studies published in English that dealt with the integration of patient data within a CNN-based skin cancer classification. The search terms skin cancer classification, convolutional neural network(s), deep learning, lesions, melanoma, metadata, clinical information, and patient data were combined. RESULTS: A total of 11 publications fulfilled the inclusion criteria. All of them reported an overall improvement in different skin lesion classification tasks with patient data integration. The most commonly used patient data were age, sex, and lesion location. The patient data were mostly one-hot encoded. There were differences in the complexity that the encoded patient data were processed with regarding deep learning methods before and after fusing them with the image features for a combined classifier. CONCLUSIONS: This study indicates the potential benefits of integrating patient data into CNN-based diagnostic algorithms. However, how exactly the individual patient data enhance classification performance, especially in the case of multiclass classification problems, is still unclear. Moreover, a substantial fraction of patient data used by dermatologists remains to be analyzed in the context of CNN-based skin cancer classification. Further exploratory analyses in this promising field may optimize patient data integration into CNN-based skin cancer diagnostics for patients' benefits.

Deep learning approach to predict sentinel lymph node status directly from routine histology of primary melanoma tumours.

AIM: Sentinel lymph node status is a central prognostic factor for melanomas. However, the surgical excision involves some risks for affected patients. In this study, we therefore aimed to develop a digital biomarker that can predict lymph node metastasis non-invasively from digitised H&E slides of primary melanoma tumours. METHODS: A total of 415 H&E slides from primary melanoma tumours with known sentinel node (SN) status from three German university hospitals and one private pathological practice were digitised (150 SN positive/265 SN negative). Two hundred ninety-one slides were used to train artificial neural networks (ANNs). The remaining 124 slides were used to test the ability of the ANNs to predict sentinel status. ANNs were trained and/or tested on data sets that were matched or not matched between SN-positive and SN-negative cases for patient age, ulceration, and tumour thickness, factors that are known to correlate with lymph node status. RESULTS: The best accuracy was achieved by an ANN that was trained and tested on unmatched cases (61.8% ± 0.2%) area under the receiver operating characteristic (AUROC). In contrast, ANNs that were trained and/or tested on matched cases achieved (55.0% ± 3.5%) AUROC or less. CONCLUSION: Our results indicate that the image classifier can predict lymph node status to some, albeit so far not clinically relevant, extent. It may do so by mostly detecting equivalents of factors on histological slides that are already known to correlate with lymph node status. Our results provide a basis for future research with larger data cohorts.

A Problem of Classification: 2 Cases of Epstein-Barr Virus + Primary Cutaneous Plasmacytoma Arising in Immunocompetent Elderly Patients.

ABSTRACT: Primary extramedullary plasmacytoma is rare monoclonal proliferation of plasma cells, which arise in various nonosseous anatomic locations without detectable underlying systemic disease. Historically, cutaneous infiltrates rich in mature neoplastic plasma cells have fallen into one of the following categories, plasmacytoma, lymphoplasmacytic lymphoma, and marginal zone lymphoma, which included immunocytoma. Since 2005, each of these was subsumed under the marginal zone lymphoma umbrella, largely on the basis of acknowledged diagnostic difficulties in some of these cases. We describe 2 cases in which the cutaneous infiltrates consisted of a pure population of light chain-restricted mature plasma cells in the absence of any other evidence for a marginal zone proliferation, or evidence of extracutaneous involvement, including a paraprotein. We propose that primary cutaneous plasmacytoma is the accurate diagnosis and is consistent with wider nomenclature. The unusual observation of widespread Epstein-Barr virus expression in both tumors is also discussed.

Multicentric dermatofibrosarcoma protuberans in a child with severe combined immunodeficiency due to adenosine deaminase deficiency.

We report the case of a 4-year-old boy, post-human stem cell transplantation for severe combined immunodeficiency (SCID) due to adenosine deaminase deficiency (ADA), who developed multiple dermatofibrosarcoma protuberans (DFSP). We hypothesize a role for chimerism leading to accumulation of toxic metabolites which can cause DNA strand breaks and inhibit lymphocyte activation. Patients with ADA-SCID should remain under lifelong dermatologic surveillance as DFSP lesions can be quite inconspicuous.

Combining CNN-based histologic whole slide image analysis and patient data to improve skin cancer classification.

BACKGROUND: Clinicians and pathologists traditionally use patient data in addition to clinical examination to support their diagnoses. OBJECTIVES: We investigated whether a combination of histologic whole slides image (WSI) analysis based on convolutional neural networks (CNNs) and commonly available patient data (age, sex and anatomical site of the lesion) in a binary melanoma/nevus classification task could increase the performance compared with CNNs alone. METHODS: We used 431 WSIs from two different laboratories and analysed the performance of classifiers that used the image or patient data individually or three common fusion techniques. Furthermore, we tested a naive combination of patient data and an image classifier: for cases interpreted as 'uncertain' (CNN output score <0.7), the decision of the CNN was replaced by the decision of the patient data classifier. RESULTS: The CNN on its own achieved the best performance (mean ± standard deviation of five individual runs) with AUROC of 92.30% ± 0.23% and balanced accuracy of 83.17% ± 0.38%. While the classification performance was not significantly improved in general by any of the tested fusions, naive strategy of replacing the image classifier with the patient data classifier on slides with low output scores improved balanced accuracy to 86.72% ± 0.36%. CONCLUSION: In most cases, the CNN on its own was so accurate that patient data integration did not provide any benefit. However, incorporating patient data for lesions that were classified by the CNN with low 'confidence' improved balanced accuracy.

TERT promoter mutation in sebaceous neoplasms.

TERT promoter (TERTp) mutations widely occur in multiple human neoplasms, and they have been related to different clinicopathological features. To date, this mutation has not been identified in sebaceous tumors. Here, we analyzed TERTp mutations in 91 sebaceous neoplasms (17 adenomas, 45 sebaceomas, and 29 carcinomas). We detected mutations in 26.7% (8 of 29) of sebaceous carcinomas by pyrosequencing and Sanger sequencing. No mutation was detected in adenomas or sebaceomas. The difference was significant between sebaceoma and carcinoma. The most frequent TERTp mutations were C228T and C250T in 37.5% (3 of 8) of mutated cases each one. The mutation was not associated with poor clinical evolution. Using NGS, 20 of 29 (68.5%) sebaceous carcinomas harbored mutations in 8 of the 30 genes analyzed (TP53, TERTp, EGFR, ATRX, PDGFRA, CDKN2A, PTEN, and ACVR1). With immunohistochemistry, only 1 of 8 (12.5%) TERTp-mutated carcinomas lacked mismatch repair (MMR) protein expression compared to 6 of 21 (31.6%) of non-mutated ones. Sebaceous carcinomas with MMR protein expression had significantly higher frequency of total mutations and TP53 and TERTp mutations than MMR protein-deficient carcinomas. In conclusion, TERTp mutation has been detected in sebaceous carcinomas, and its presence could be useful to differentiate sebaceous carcinoma from sebaceoma, a difficult histopathological challenge.