Artificial intelligence in digital pathology of cutaneous lymphomas: A review of the current state and future perspectives.

Primary cutaneous lymphomas (CLs) represent a heterogeneous group of T-cell lymphomas and B-cell lymphomas that present in the skin without evidence of extracutaneous involvement at time of diagnosis. CLs are largely distinct from their systemic counterparts in clinical presentation, histopathology, and biological behavior and, therefore, require different therapeutic management. Additional diagnostic burden is added by the fact that several benign inflammatory dermatoses mimic CL subtypes, requiring clinicopathological correlation for definitive diagnosis. Due to the heterogeneity and rarity of CL, adjunct diagnostic tools are welcomed, especially by pathologists without expertise in this field or with limited access to a centralized specialist panel. The transition into digital pathology workflows enables artificial intelligence (AI)-based analysis of patients' whole-slide pathology images (WSIs). AI can be used to automate manual processes in histopathology but, more importantly, can be applied to complex diagnostic tasks, especially suitable for rare disease like CL. To date, AI-based applications for CL have been minimally explored in literature. However, in other skin cancers and systemic lymphomas, disciplines that are recognized here as the building blocks for CLs, several studies demonstrated promising results using AI for disease diagnosis and subclassification, cancer detection, specimen triaging, and outcome prediction. Additionally, AI allows discovery of novel biomarkers or may help to quantify established biomarkers. This review summarizes and blends applications of AI in pathology of skin cancer and lymphoma and proposes how these findings can be applied to diagnostics of CL.

Trends in Incidence and Survival of 1496 Patients with Mucosal Melanoma in The Netherlands (1990-2019).

BACKGROUND: Mucosal melanoma (MM) is a rare tumour with a poor prognosis. Over the years, immune and targeted therapy have become available and have improved overall survival (OS) for patients with advanced cutaneous melanoma (CM). This study aimed to assess trends in the incidence and survival of MM in the Netherlands against the background of new effective treatments that became available for advanced melanoma. METHODS: We obtained information on patients diagnosed with MM during 1990-2019 from the Netherlands Cancer Registry. The age-standardized incidence rate and estimated annual percentage change (EAPC) were calculated over the total study period. OS was calculated using the Kaplan-Meier method. Independent predictors for OS were assessed by applying multivariable Cox proportional hazards regression models. RESULTS: In total, 1496 patients were diagnosed with MM during 1990-2019, mostly in the female genital tract (43%) and the head and neck region (34%). The majority presented with local or locally advanced disease (66%). The incidence remained stable over time (EAPC 3.0%, p = 0.4). The 5-year OS was 24% (95%CI: 21.6-26.0%) with a median OS of 1.7 years (95%CI: 1.6-1.8). Age ≥ 70 years at diagnosis, higher stage at diagnosis, and respiratory tract location were independent predictors for worse OS. Diagnosis in the period 2014-2019, MM located in the female genital tract, and treatment with immune or targeted therapy were independent predictors for better OS. CONCLUSION: Since the introduction of immune and targeted therapies, OS has improved for patients with MM. However, the prognosis of MM patients is still lower compared to CM, and the median OS of patients treated with immune and targeted therapies remains fairly short. Further studies are needed to improve outcomes for patients with MM.

Ambiguous melanocytic lesions: A retrospective cohort study of incidence and outcome of melanocytic tumor of uncertain malignant potential (MELTUMP) and superficial atypical melanocytic proliferation of uncertain significance (SAMPUS) in the Netherlands.

BACKGROUND: Melanocytic tumor of uncertain malignant potential (MELTUMP) and superficial atypical melanocytic proliferation of uncertain significance (SAMPUS) are descriptive and provisional terms for melanocytic tumors with ambiguous histopathological features that are not easily classified as either benign or malignant. OBJECTIVE: To investigate the incidence and clinical outcome of MELTUMP and SAMPUS in the Netherlands. METHODS: In this retrospective cohort study, we reviewed all diagnoses of MELTUMP and SAMPUS from the Dutch Nationwide Pathology Databank from 1991 to October 1, 2021. Clinical outcome was studied for cases diagnosed until October 1, 2018. RESULTS: A total of 1685 MELTUMP and 1957 SAMPUS were identified with an annual incidence of 150 to 300 cases. Metastatic behavior was seen in 0.7% of all initially diagnosed MELTUMP. All SAMPUS remained free of metastases. LIMITATIONS: Reassessment of pathology slides and confirmation of clonality between primary and metastatic lesions remained outside the scope of this study. CONCLUSION: Despite the 'uncertainty' in the nomenclature, our results demonstrate a low malignant potential for MELTUMP and no malignant potential for SAMPUS. We emphasize the importance of consultation for ambiguous melanocytic lesions and to limit the MELTUMP/SAMPUS terminology to legitimately uncertain or unclassifiable cases.

Genetic Stability of Driver Alterations in Primary Cutaneous Diffuse Large B-Cell Lymphoma, Leg Type and Their Relapses: A Rationale for the Use of Molecular-Based Methods for More Effective Disease Monitoring.

Primary cutaneous diffuse large B-cell lymphoma, leg type (PCDLBCL-LT) is a rare, aggressive cutaneous lymphoma with a 5-year disease-specific survival of only ~55%. Despite high response rates to initial immune-polychemotherapy, most patients experience a disease relapse. The genetic evolution of primary and relapsed/refractory disease has only scarcely been studied in PCDLBCL-LT patients. Therefore, in this retrospective cohort study, 73 primary/pre-treatment and relapsed/refractory biopsies of 57 patients with PCDLBCL-LT were molecularly characterized with triple FISH and targeted next-generation sequencing for 52 B-cell-lymphoma-relevant genes, including paired analysis in 16 patients. In this cohort, 95% of patients harboured at least one of the three main driver alterations (mutations in MYD88/CD79B and/or CDKN2A-loss). In relapsed/refractory PCDLBCL-LT, these oncogenic aberrations were persistently present, demonstrating genetic stability over time. Novel alterations in relapsed disease affected mostly CDKN2A, MYC, and PIM1. Regarding survival, only MYC rearrangements and HIST1H1E mutations were statistically significantly associated with an inferior outcome. The stable presence of one or more of the three main driver alterations (mutated MYD88/CD79B and/or CDKN2A-loss) is promising for targeted therapies addressing these alterations and serves as a rationale for molecular-based disease monitoring, improving response evaluation and early identification and intervention of disease relapses in these poor-prognostic PCDLBCL-LT patients.

The sensitivity of pan-TRK immunohistochemistry in solid tumours: A meta-analysis.

INTRODUCTION: Since the approval of neurotrophic tropomyosin receptor kinase (NTRK) tyrosine kinase inhibitors for fist-line advanced stage pan-cancer therapy, pathologists and molecular biologists have been facing a complex question: how should the large volume of specimens be screened for NTRK fusions? Immunohistochemistry is fast and cheap, but the sensitivity compared to RNA NGS is unclear. METHODS: We performed RNA-based next-generation sequencing on 1,329 cases and stained 24 NTRK-rearranged cases immunohistochemically with pan-TRK (ERP17341). Additionally, we performed a meta-analysis of the literature. After screening 580 studies, 200 additional NTRK-rearranged cases from 13 studies, analysed with sensitive molecular diagnostics as well as pan-TRK IHC, were included. RESULTS: In the included 224 NTRK-rearranged solid tumours, the sensitivity for pan-TRK IHC was 82% and the false-negative rate was 18%. NTRK3 fusions had more false negatives (27%) compared to NTRK1 (6%) and NTRK2 (14%) (p = 0.0006). Membranous, nuclear and peri-nuclear staining patterns strongly correlated with different fusion products, with membranous staining being more prevalent in NTRK1 and NTRK2, nuclear in NTRK3, and perinuclear in NTRK1. CONCLUSION: Despite a reduction in the number of molecular analysis, using pan-TRK immunohistochemistry as a prescreening method to detect NTRK fusions in solid tumours will miss 18% of all NTRK-fused cases (especially involving NTRK3). Therefore, the most comprehensive and optimal option to detect NTRK fusions is to perform molecular testing on all eligible cases. However, in case of financial or logistical limitations, an immunohistochemistry-first approach is defensible in tumours with a low prevalence of NTRK fusions.

Towards diagnostic criteria for malignant deep penetrating melanocytic tumors using single nucleotide polymorphism array and next-generation sequencing.

Cutaneous deep penetrating melanocytic neoplasms frequently simulate melanoma and might occasionally progress to metastatic melanoma. Distinguishing deep penetrating nevi (DPN) and deep penetrating melanocytomas (DPM) from malignant deep penetrating tumors (MDPT) is difficult based on histopathology alone, and diagnostic criteria for MDPT are currently lacking. Using a molecular workup, we aimed to provide readily available diagnostic tools for classification of deep penetrating tumors. We used clinical follow-up and Single Nucleotide Polymorphism (SNP) array for tumor classification of 20 deep penetrating neoplasms to identify associations with histopathological, immunohistochemistry, and NGS findings. Ten neoplasms were classified as MDPT, four as DPM, and six as DPN. Two MDPT showed metastases. The following parameters were statistically significantly associated with MDPT: severe nuclear atypia (risk ratio [RR] 2.9, p < 0.05), absence of a nevus component (RR 10.0, p = 0.04), positive PRAME expression (RR 9.0, p = 0.02), complete loss of p16 expression (RR 3.5, p = 0.003), TERT-p and APC mutations (RR 11.0, p = 0.01 and RR 2.7, p = 0.002, respectively), and ≥1 additional pathogenic mutation (RR 9.0, p = 0.02). Ki-67 expression ≥ 5% was not significantly associated with MDPTs, although it was <5% in all DPNs. Three MDPT did not show nuclear ß-catenin expression despite having a CTNNB1 (n = 2) or an APC mutation (n = 1). Our findings suggest that complete loss of p16 and positive PRAME expression, a driver mutation in APC, ≥ 1 additional pathogenic mutation, especially in TERT-p, support an MDPT diagnosis in deep penetrating neoplasms. Besides severe nuclear atypia and possibly severe inflammation, we did not identify specific histopathological criteria for malignancy. Non-aberrant nuclear ß-catenin expression might not exclude a deep penetrating signature in MDPT.

Cell-of-origin classification using the Hans and Lymph2Cx algorithms in primary cutaneous large B-cell lymphomas.

Primary cutaneous diffuse large B-cell lymphoma, leg type (PCDLBCL-LT) and primary cutaneous follicle center lymphoma with a diffuse population of large cells (PCFCL-LC) are both primary cutaneous B-cell lymphomas with large-cell morphology (CLBCL) but with different clinical characteristics and behavior. In systemic diffuse large B-cell lymphoma, not otherwise specified (DLBCL-NOS), gene-expression profiling (GEP) revealed two molecular subgroups based on their cell-of-origin (COO) with prognostic significance: the germinal center B-cell-like (GCB) subtype and the activated B-cell-like (ABC) subtype. This study investigated whether COO classification is a useful tool for classification of CLBCL. For this retrospective study, 51 patients with PCDLBCL-LT and 15 patients with PCFCL-LC were analyzed for their COO according to the immunohistochemistry-based Hans algorithm and the NanoString GEP-based Lymph2Cx algorithm. In PCFCL-LC, all cases (100%) classified as GCB by both Hans and Lymph2Cx. In contrast, COO classification in PCDLBCL-LT was heterogeneous. Using Hans, 75% of the PCDLBCL-LT patients classified as non-GCB and 25% as GCB, while Lymph2Cx classified only 18% as ABC, 43% as unclassified/intermediate, and 39% as GCB. These COO subgroups did not differ in the expression of BCL2 and IgM, mutations in MYD88 and/or CD79B, loss of CDKN2A, or survival. In conclusion, PCFCL-LC uniformly classified as GCB, while PCDLBCL-LT classified along the COO spectrum of DLBCL-NOS using the Hans and Lymph2Cx algorithms. In contrast to DLBCL-NOS, the clinical relevance of COO classification in CLBCL using these algorithms has limitations and cannot be used as an alternative for the current multiparameter approach in differentiation of PCDLBCL-LT and PCFCL-LC.

Predictive Biomarkers for Outcomes of Immune Checkpoint Inhibitors (ICIs) in Melanoma: A Systematic Review.

Immune checkpoint inhibitors (ICIs) have strongly improved the survival of melanoma patients. However, as durable response to ICIs are only seen in a minority, there is an unmet need to identify biomarkers that predict response. Therefore, we provide a systematic review that evaluates all biomarkers studied in association with outcomes of melanoma patients receiving ICIs. We searched Pubmed, COCHRANE Library, Embase, Emcare, and Web of Science for relevant articles that were published before June 2020 and studied blood, tumor, or fecal biomarkers that predicted response or survival in melanoma patients treated with ICIs. Of the 2536 identified reports, 177 were included in our review. Risk of bias was high in 40%, moderate in 50% and low in 10% of all studies. Biomarkers that correlated with response were myeloid-derived suppressor cells (MDSCs), circulating tumor cells (CTCs), CD8+ memory T-cells, T-cell receptor (TCR) diversity, tumor-infiltrating lymphocytes (TILs), gene expression profiling (GEP), and a favorable gut microbiome. This review shows that biomarkers for ICIs in melanoma patients are widely studied, but heterogeneity between studies is high, average sample sizes are low, and validation is often lacking. Future studies are needed to further investigate the predictive utility of some promising candidate biomarkers.

MYD88 mutations identify a molecular subgroup of diffuse large B-cell lymphoma with an unfavorable prognosis.

The 2016 World Health Organization classification defines diffuse large B-cell lymphoma (DLBCL) subtypes based on Epstein-Barr virus (EBV) infection and oncogenic rearrangements of MYC/BCL2/BCL6 as drivers of lymphomagenesis. A subset of DLBCL, however, is characterized by activating mutations in MYD88/CD79B We investigated whether MYD88/CD79B mutations could improve the classification and prognostication of DLBCL. In 250 primary DLBCL, MYD88/CD79B mutations were identified by allele-specific polymerase chain reaction or next-generation-sequencing, MYC/BCL2/BCL6 rearrangements were analyzed by fluorescence in situ hybridization, and EBV was studied by EBV-encoded RNA in situ hybridization. Associations of molecular features with clinicopathologic characteristics, outcome, and prognosis according to the International Prognostic Index (IPI) were investigated. MYD88 and CD79B mutations were identified in 29.6% and 12.3%, MYC, BCL2, and BCL6 rearrangements in 10.6%, 13.6%, and 20.3%, and EBV in 11.7% of DLBCL, respectively. Prominent mutual exclusivity between EBV positivity, rearrangements, and MYD88/CD79B mutations established the value of molecular markers for the recognition of biologically distinct DLBCL subtypes. MYD88-mutated DLBCL had a significantly inferior 5-year overall survival than wild-type MYD88 DLBCL (log-rank; P=0.019). DLBCL without any of the studied aberrations had superior overall survival compared to cases carrying ≥1 aberrancy (log-rank; P=0.010). MYD88 mutations retained their adverse prognostic impact upon adjustment for other genetic and clinical variables by multivariable analysis and improved the prognostic performance of the IPI. This study demonstrates the clinical utility of defining MYD88-mutated DLBCL as a distinct molecular subtype with adverse prognosis. Our data call for sequence analysis of MYD88 in routine diagnostics of DLBCL to optimize classification and prognostication, and to guide the development of improved treatment strategies.

MYD88 in the driver's seat of B-cell lymphomagenesis: from molecular mechanisms to clinical implications.

More than 50 subtypes of B-cell non-Hodgkin lymphoma (B-NHL) are recognized in the most recent World Health Organization classification of 2016. The current treatment paradigm, however, is largely based on 'one-size-fits-all' immune-chemotherapy. Unfortunately, this therapeutic strategy is inadequate for a significant number of patients. As such, there is an indisputable need for novel, preferably targeted, therapies based on a biologically driven classification and risk stratification. Sequencing studies identified mutations in the MYD88 gene as an important oncogenic driver in B-cell lymphomas. MYD88 mutations constitutively activate NF-κB and its associated signaling pathways, thereby promoting B-cell proliferation and survival. High frequencies of the hotspot MYD88(L265P) mutation are observed in extranodal diffuse large B-cell lymphoma and Waldenström macroglobulinemia, thereby demonstrating this mutation's potential as a disease marker. In addition, the presence of mutant MYD88 predicts survival outcome in B-NHL subtypes and it provides a therapeutic target. Early clinical trials targeting MYD88 have shown encouraging results in relapsed/refractory B-NHL. Patients with these disorders can benefit from analysis for the MYD88 hotspot mutation in liquid biopsies, as a minimally invasive method to demonstrate treatment response or resistance. Given these clear clinical implications and the crucial role of MYD88 in lymphomagenesis, we expect that analysis of this gene will increasingly be used in routine clinical practice, not only as a diagnostic classifier, but also as a prognostic and therapeutic biomarker directing precision medicine. This review focuses on the pivotal mechanistic role of mutated MYD88 and its clinical implications in B-NHL.

High Incidence and Clinical Significance of MYC Rearrangements in Primary Cutaneous Diffuse Large B-Cell Lymphoma, Leg Type.

Primary cutaneous diffuse large B-cell lymphoma, leg type (PCDLBCL-LT) and primary cutaneous follicle center lymphoma (PCFCL) are cutaneous B-cell lymphomas (CBCL) with different clinical characteristics and behavior. PCDLBCL-LT is the most aggressive CBCL with a relatively poor prognosis. In nodal diffuse large B-cell lymphoma (DLBCL), rearrangements of the MYC gene, especially in combination with a second hit in BCL2 and/or BCL6, and double protein expression of MYC and BCL2 (DE) are adverse prognostic factors. As the clinical significance of these factors in CBCL is largely unknown, we studied the frequency and prognostic value of MYC rearrangements and DE in a cohort of 44 patients with PCDLBCL-LT and 17 patients with PCFCL. Compared with nodal DLBCL (9% to 14%), the PCDLBCL-LT patients had a high incidence of MYC rearrangements (32%), but only 2 patients (4%) had a second hit, both with BCL6. PCDLBCL-LT patients with a MYC rearrangement showed an inferior disease-specific survival (Log-rank, P=0.036) and disease-free survival (Log-rank, P=0.028), but no significant adverse effect on overall survival (Log-rank, P=0.157) at 5 years compared with patients without a MYC rearrangement. DE, present in 65% of the PCDLBCL-LT patients, was not associated with reduced survival. In the PCFCL group, MYC rearrangements and DE were not detected. In conclusion, this study identifies a high incidence of MYC rearrangements in PCDLBCL-LT compared to nodal DLBCL and further shows that a MYC rearrangement is an inferior prognostic marker in these patients. Therefore, our data suggest that it is useful to perform MYC-FISH in all newly diagnosed PCDLBCL-LT patients.

TOX expression in cutaneous B-cell lymphomas.

Thymocyte selection-associated high-mobility group box (TOX) is aberrantly expressed in cutaneous T-cell lymphomas. In a recent study, TOX expression was noted unexpectedly in the follicle center (germinal center) B-cells of reactive lymph nodes and tonsils, used as external controls. To evaluate whether TOX is also expressed by cutaneous B-cell lymphomas, TOX immunohistochemistry was performed on skin biopsies of 44 patients with primary and secondary cutaneous B-cell proliferations. TOX was expressed not only in the reactive follicle center cells of lymph nodes, tonsils, cutaneous lymphoid hyperplasia, and primary cutaneous marginal zone lymphomas, but also by the neoplastic follicle center cells of 16/17 patients with primary cutaneous follicle center lymphoma (PCFCL) and 7/7 patients with cutaneous manifestations of systemic follicular lymphoma (FL). Notably, TOX showed a very similar expression pattern as BCL6, a marker of germinal center B-cells. In 4/10 patients with a BCL6(+) primary cutaneous diffuse large B-cell lymphoma, leg type (PCDLBCL,LT) and in 2/2 patients with a secondary cutaneous BCL6(+) diffuse large B-cell lymphoma (DLBCL), TOX was expressed by more than 50 % of the neoplastic B-cells. In contrast, in 3/3 BCL6(-) PCDLBCL,LT, TOX was completely negative or weakly expressed by a minor proportion of the neoplastic B-cells. In conclusion, TOX is expressed not only by neoplastic T-cells, but also by both reactive and neoplastic follicle center (germinal center) B-cells and a proportion of BCL6(+) PCDLBCL,LT and secondary cutaneous BCL6(+) DLBCL. The functional significance of TOX expression in reactive and neoplastic B-cells remains to be elucidated.

Hidradenitis suppurativa: a retrospective study of 846 Dutch patients to identify factors associated with disease severity.

BACKGROUND: Few comprehensive studies exist on the epidemiology of hidradenitis suppurativa, a very distressing skin disease. OBJECTIVE: We sought to identify disease-related factors associated with severity, sex, and family history. METHODS: Ordinal logistic regression was used in 846 consecutive Dutch patients with hidradenitis suppurativa to calculate odds ratios (ORs) for severity according to Hurley. Sex and family history were compared using Student t test and χ(2) test. RESULTS: In total, 45.5% of the patients had Hurley I, 41.5% had Hurley II, and 13.0% had Hurley III. Severity was associated with male sex (OR 2.11; P < .001), disease duration (OR 1.03; P < .001), body mass index (OR 1.03; P = .01), smoking pack-years (OR 1.02; P = .001), and axillary (OR 2.24; P < .001), perianal (OR 1.92; P < .001), and mammary lesions (OR 1.48; P = .03). Women had earlier onset, more inguinal and mammary lesions, and more frequent family history for hidradenitis suppurativa. Men more commonly had gluteal, perianal, and atypical lesions, and a history of severe acne. Patients with a family history had earlier onset, longer disease duration, a history of severe acne, more extensive disease, and were more often smokers. LIMITATIONS: Some parameters were patient-reported. CONCLUSION: The severity risk factors identified in this study could help physicians to select patients who need close monitoring and who would benefit from early, aggressive therapy.