NTRK gene fusion testing and management in lung cancer.

Neurotrophic tyrosine receptor kinase (NTRK) gene fusions are recurrent oncogenic drivers found in a variety of solid tumours, including lung cancer. Several tropomyosin receptor kinase (TRK) inhibitors have been developed to treat tumours with NTRK gene fusions. Larotrectinib and entrectinib are first-generation TRK inhibitors that have demonstrated efficacy in patients with TRK fusion lung cancers. Genomic testing is recommended for all patients with metastatic non-small cell lung cancer for optimal drug therapy selection. Multiple testing methods can be employed to identify NTRK gene fusions in the clinic and each has its own advantages and limitations. Among these assays, RNA-based next-generation sequencing (NGS) can be considered a gold standard for detecting NTRK gene fusions; however, several alternatives with minimally acceptable sensitivity and specificity are also available in areas where widespread access to NGS is unfeasible. This review highlights the importance of testing for NTRK gene fusions in lung cancer, ideally using the gold-standard method of RNA-based NGS, the various assays that are available, and treatment algorithms for patients.

The Pathologic Diagnosis of Pediatric Soft Tissue Tumors in the Era of Molecular Medicine: The Sarcoma Pediatric Pathology Research Interest Group Perspective.

CONTEXT.­: Pediatric soft tissue tumors are one of the areas of pediatric pathology that frequently generate consult requests. Evolving classification systems, ancillary testing methods, new treatment options, research enrollment opportunities, and tissue archival processes create additional complexity in handling these unique specimens. Pathologists are at the heart of this critical decision-making, balancing responsibilities to consider expediency, accessibility, and cost-effectiveness of ancillary testing during pathologic examination and reporting. OBJECTIVE.­: To provide a practical approach to handling pediatric soft tissue tumor specimens, including volume considerations, immunohistochemical staining panel recommendations, genetic and molecular testing approaches, and other processes that impact the quality and efficiency of tumor tissue triage. DATA SOURCES.­: The World Health Organization Classification of Soft Tissue and Bone Tumors, 5th edition, other recent literature investigating tissue handling, and the collective clinical experience of the group are used in this manuscript. CONCLUSIONS.­: Pediatric soft tissue tumors can be difficult to diagnose, and evaluation can be improved by adopting a thoughtful, algorithmic approach to maximize available tissue and minimize time to diagnosis.

Rhabdomyosarcoma: Updates on classification and the necessity of molecular testing beyond immunohistochemistry.

Rhabdomyosarcoma (RMS) is the most common soft tissue sarcoma in children and adolescents under the age of 20. The current World Health Organization (WHO) classification for soft tissue and bone tumors recognizes 4 distinct subtypes of RMS based on clinicopathological and molecular genetic features: embryonal, alveolar, spindle cell/sclerosing and pleomorphic subtypes. However, with the increased use of molecular techniques, the classification of rhabdomyosarcoma has been evolving rapidly. New subtypes such as osseus RMS harboring TFCP2/NCOA2 fusions or RMS arising in inflammatory rhabdomyoblastic tumor have been emerging within the last decade, adding to the complexity of diagnosing skeletal muscle tumors. This review article provides an overview of classically recognized distinctive subtypes as well as new, evolving subtypes and discusses important morphologic, immunophenotypic and molecular genetic features of each subtype including recommendations for a diagnostic approach of malignant skeletal muscle neoplasms.

Children's Oncology Group's 2023 blueprint for research: Soft tissue sarcomas.

In the United States, approximately 850-900 children and adolescents each year are diagnosed with soft tissue sarcomas (STS). STS are divided into rhabdomyosarcoma (RMS) and non-rhabdomyosarcoma STS (NRSTS). RMS and NRSTS are risk stratified into low-, intermediate-, and high-risk categories, with 5-year survival rates of approximately 90%, 50%-70%, and 20%, respectively. Recent key achievements from the Children's Oncology Group (COG) STS Committee include the identification of new molecular prognostic factors for RMS, development and validation of a novel risk stratification system for NRSTS, successful completion of a collaborative NRSTS clinical trial with adult oncology consortia, and collaborative development of the INternational Soft Tissue SaRcoma ConsorTium (INSTRuCT). Current COG trials for RMS are prospectively evaluating a new risk stratification system that incorporates molecular findings, de-intensification of therapy for a very low-risk subgroup, and augmented therapy approaches for intermediate- and high-risk RMS. Trials for NRSTS exploring novel targets and local control modalities are in development.

Cancer-Associated Fibroblast-Like Tumor Cells Remodel the Ewing Sarcoma Tumor Microenvironment.

PURPOSE: Despite limited genetic and histologic heterogeneity, Ewing sarcoma (EwS) tumor cells are transcriptionally heterogeneous and display varying degrees of mesenchymal lineage specification in vitro. In this study, we investigated if and how transcriptional heterogeneity of EwS cells contributes to heterogeneity of tumor phenotypes in vivo. EXPERIMENTAL DESIGN: Single-cell proteogenomic-sequencing of EwS cell lines was performed and integrated with patient tumor transcriptomic data. Cell subpopulations were isolated by FACS for assessment of gene expression and phenotype. Digital spatial profiling and human whole transcriptome analysis interrogated transcriptomic heterogeneity in EwS xenografts. Tumor cell subpopulations and matrix protein deposition were evaluated in xenografts and patient tumors using multiplex immunofluorescence staining. RESULTS: We identified CD73 as a biomarker of highly mesenchymal EwS cell subpopulations in tumor models and patient biopsies. CD73+ tumor cells displayed distinct transcriptional and phenotypic properties, including selective upregulation of genes that are repressed by EWS::FLI1, and increased migratory potential. CD73+ cells were distinguished in vitro and in vivo by increased expression of matrisomal genes and abundant deposition of extracellular matrix (ECM) proteins. In epithelial-derived malignancies, ECM is largely deposited by cancer-associated fibroblasts (CAF), and we thus labeled CD73+ EwS cells, CAF-like tumor cells. Marked heterogeneity of CD73+ EwS cell frequency and distribution was detected in tumors in situ, and CAF-like tumor cells and associated ECM were observed in peri-necrotic regions and invasive foci. CONCLUSIONS: EwS tumor cells can adopt CAF-like properties, and these distinct cell subpopulations contribute to tumor heterogeneity by remodeling the tumor microenvironment. See related commentary by Kuo and Amatruda, p. 5002.

FGFR1 gene fusions in a subset of pediatric mesenchymal tumors: Expanding the genetic spectrum of tumors sharing histologic overlap with infantile fibrosarcoma and "NTRK-rearranged" spindle cell neoplasms.

As the classification of kinase-driven spindle cell tumors continues to evolve, we describe the first series of pediatric mesenchymal tumors harboring FGFR1 gene fusions that share histologic overlap with infantile fibrosarcoma and "NTRK-rearranged" spindle cell neoplasms. Herein, we present three cases of FGFR1-rearranged pediatric mesenchymal tumors, including one case with FGFR1::PARD6B gene fusion and two cases with FGFR1::EBF2 gene fusion. The tumors involved infants ranging from 3 to 9 months in age with a male-to-female ratio of 2:1. All tumors involved the deep soft tissue of the gluteal, pelvic, or perirectal region. Histologically, the tumors comprised a cellular spindle cell neoplasm with primitive stellate cells, focal myxoid stroma, focal epithelioid features, no necrosis, and occasional mitotic figures (2-6 per 10 high-power field). By immunohistochemistry, the neoplastic cells focally expressed CD34 but lacked expression of S100 protein, SMA, desmin, myogenin, MyoD1, pan-TRK, and ALK. These three cases, including a case with long-term clinical follow-up, demonstrate that FGFR1 fusions occur in a subset of newly described pediatric kinase-driven mesenchymal tumors with locally aggressive behavior. Importantly, knowledge of these genetic alterations in this spectrum of pediatric tumors is key for diagnostic and targeted therapeutic purposes.

Feasibility of combining temsirolimus to vincristine, dactinomycin, cyclophosphamide, and vincristine and irinotecan chemotherapy for children with intermediate-risk rhabdomyosarcoma: A report from Children's Oncology Group.

BACKGROUND: Temsirolimus has shown in vivo activity against rhabdomyosarcoma (RMS). We aimed to determine the feasibility of incorporating temsirolimus within the standard Children's Oncology Group (COG) chemotherapy backbone of vincristine, actinomycin-D, and cyclophosphamide (VAC) alternating with vincristine and irinotecan (VI) in children with intermediate-risk (IR) RMS. METHODS: The feasibility phase of the COG IR-RMS trial, ARST1431 (NCT02567435), assigned 10 patients to receive 15 mg/m2 /dose (dose level 1) of temsirolimus on days 1, 8, and 15 of each of three weekly VAC and VI cycles for the first 12 weeks of induction chemotherapy. The primary endpoint of the feasibility phase was to establish the safe dose and safety of combining temsirolimus with VAC/VI. The combination regimen was deemed feasible if less than 40% of patients developed a priori defined nonhematological dose-limiting toxicities (DLTs). RESULTS: Ten patients (seven males and three females; median age = 4.5 years [range: 0.2-14.4 years]) with IR-RMS were enrolled and received dose level 1 of temsirolimus. Eight patients had FOXO1-negative disease, while two had FOXO1-positive disease. Two patients had metastatic disease. Of 10 patients, two developed DLTs: grade 3 oral mucositis and pneumonitis. Four patients (40%) had grade 4 neutropenia. No treatment-related mortality occurred. The median duration of the completion of the feasibility phase was 12.1 weeks (range: 11.7-15 weeks). CONCLUSIONS: Weekly temsirolimus at 15 mg/m2 /dose during VAC/VI chemotherapy was feasible and well tolerated. The efficacy of this regimen is currently being tested in a phase III randomized trial against VAC/VI chemotherapy alone in the ARST1431 trial.

Carcinoma-associated fibroblast-like tumor cells remodel the Ewing sarcoma tumor microenvironment.

Tumor heterogeneity is a major driver of cancer progression. In epithelial-derived malignancies, carcinoma-associated fibroblasts (CAFs) contribute to tumor heterogeneity by depositing extracellular matrix (ECM) proteins that dynamically remodel the tumor microenvironment (TME). Ewing sarcomas (EwS) are histologically monomorphous, mesenchyme-derived tumors that are devoid of CAFs. Here we identify a previously uncharacterized subpopulation of transcriptionally distinct EwS tumor cells that deposit pro-tumorigenic ECM. Single cell analyses revealed that these CAF-like cells differ from bulk EwS cells by their upregulation of a matrisome-rich gene signature that is normally repressed by EWS::FLI1, the oncogenic fusion transcription factor that underlies EwS pathogenesis. Further, our studies showed that ECM-depositing tumor cells express the cell surface marker CD73, allowing for their isolation ex vivo and detection in situ. Spatial profiling of tumor xenografts and patient biopsies demonstrated that CD73 + EwS cells and tumor cell-derived ECM are prevalent along tumor borders and invasive fronts. Importantly, despite loss of EWS::FLI1-mediated gene repression, CD73 + EwS cells retain expression of EWS::FLI1 and the fusion-activated gene signature, as well as tumorigenic and proliferative capacities. Thus, EwS tumor cells can be reprogrammed to adopt CAF-like properties and these transcriptionally and phenotypically distinct cell subpopulations contribute to tumor heterogeneity by remodeling the TME.

CD43-positive, EWSR1::FLI1 -rearranged Soft Tissue Sarcoma in a Pediatric Patient With History of B-Cell Acute Lymphoblastic Leukemia.

Ewing sarcoma is a small round blue cell tumor typically characterized by an EWSR1 rearrangement and expression of CD99 and NKX2.2, without expression of hematopoietic markers such as CD45. CD43 is an alternative hematopoietic immunohistochemical marker often utilized in the workup of these tumors and its expression typically argues against Ewing sarcoma. We report a 10-year-old with history of B-cell acute lymphoblastic leukemia presenting with an unusual malignant shoulder mass with variable CD43 positivity, but with an EWSR1::FLI1 fusion detected by RNA sequencing. Her challenging workup highlights the utility of next-generation DNA-based and RNA-based sequencing methods in cases with unclear or conflicting immunohistochemical results.

Functional genomics of human clear cell sarcoma: genomic, transcriptomic and chemical biology landscape for clear cell sarcoma.

BACKGROUND: Systemic therapy for metastatic clear cell sarcoma (CCS) bearing EWSR1-CREB1/ATF1 fusions remains an unmet clinical need in children, adolescents, and young adults. METHODS: To identify key signaling pathway vulnerabilities in CCS, a multi-pronged approach was taken: (i) genomic and transcriptomic landscape analysis, (ii) integrated chemical biology interrogations, (iii) development of CREB1/ATF1 inhibitors, and (iv) antibody-drug conjugate testing (ADC). The first approach encompassed DNA exome and RNA deep sequencing of the largest human CCS cohort yet reported consisting of 47 patient tumor samples and 8 cell lines. RESULTS: Sequencing revealed recurrent mutations in cell cycle checkpoint, DNA double-strand break repair or DNA mismatch repair genes, with a correspondingly low to intermediate tumor mutational burden. DNA multi-copy gains with corresponding high RNA expression were observed in CCS tumor subsets. CCS cell lines responded to the HER3 ADC patritumab deruxtecan in a dose-dependent manner in vitro, with impaired long term cell viability. CONCLUSION: These studies of the genomic, transcriptomic and chemical biology landscape represent a resource 'atlas' for the field of CCS investigation and drug development. CHK inhibitors are identified as having potential relevance, CREB1 inhibitors non-dependence of CCS on CREB1 activity was established, and the potential utility of HER3 ADC being used in CCS is found.

Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group.

PURPOSE: Rhabdomyosarcoma (RMS) is an aggressive soft-tissue sarcoma, which primarily occurs in children and young adults. We previously reported specific genomic alterations in RMS, which strongly correlated with survival; however, predicting these mutations or high-risk disease at diagnosis remains a significant challenge. In this study, we utilized convolutional neural networks (CNN) to learn histologic features associated with driver mutations and outcome using hematoxylin and eosin (H&E) images of RMS. EXPERIMENTAL DESIGN: Digital whole slide H&E images were collected from clinically annotated diagnostic tumor samples from 321 patients with RMS enrolled in Children's Oncology Group (COG) trials (1998-2017). Patches were extracted and fed into deep learning CNNs to learn features associated with mutations and relative event-free survival risk. The performance of the trained models was evaluated against independent test sample data (n = 136) or holdout test data. RESULTS: The trained CNN could accurately classify alveolar RMS, a high-risk subtype associated with PAX3/7-FOXO1 fusion genes, with an ROC of 0.85 on an independent test dataset. CNN models trained on mutationally-annotated samples identified tumors with RAS pathway with a ROC of 0.67, and high-risk mutations in MYOD1 or TP53 with a ROC of 0.97 and 0.63, respectively. Remarkably, CNN models were superior in predicting event-free and overall survival compared with current molecular-clinical risk stratification. CONCLUSIONS: This study demonstrates that high-risk features, including those associated with certain mutations, can be readily identified at diagnosis using deep learning. CNNs are a powerful tool for diagnostic and prognostic prediction of rhabdomyosarcoma, which will be tested in prospective COG clinical trials.

Functional genomic analysis of epithelioid sarcoma reveals distinct proximal and distal subtype biology.

BACKGROUND: Metastatic epithelioid sarcoma (EPS) remains a largely unmet clinical need in children, adolescents and young adults despite the advent of EZH2 inhibitor tazemetostat. METHODS: In order to realise consistently effective drug therapies, a functional genomics approach was used to identify key signalling pathway vulnerabilities in a spectrum of EPS patient samples. EPS biopsies/surgical resections and cell lines were studied by next-generation DNA exome and RNA deep sequencing, then EPS cell cultures were tested against a panel of chemical probes to discover signalling pathway targets with the most significant contributions to EPS tumour cell maintenance. RESULTS: Other biologically inspired functional interrogations of EPS cultures using gene knockdown or chemical probes demonstrated only limited to modest efficacy in vitro. However, our molecular studies uncovered distinguishing features (including retained dysfunctional SMARCB1 expression and elevated GLI3, FYN and CXCL12 expression) of distal, paediatric/young adult-associated EPS versus proximal, adult-associated EPS. CONCLUSIONS: Overall results highlight the complexity of the disease and a limited chemical space for therapeutic advancement. However, subtle differences between the two EPS subtypes highlight the biological disparities between younger and older EPS patients and emphasise the need to approach the two subtypes as molecularly and clinically distinct diseases.

Molecular testing of rhabdomyosarcoma in clinical trials to improve risk stratification and outcome: A consensus view from European paediatric Soft tissue sarcoma Study Group, Children's Oncology Group and Cooperative Weichteilsarkom-Studiengruppe.

Rhabdomyosarcomas (RMSs) are the most common soft tissue sarcomas in children/adolescents less than 18 years of age with an annual incidence of 1-2/million. Inter/intra-tumour heterogeneity raise challenges in clinical, pathological and biological research studies. Risk stratification in European and North American clinical trials previously relied on clinico-pathological features, but now, incorporates PAX3/7-FOXO1-fusion gene status in the place of alveolar histology. International working groups propose a coordinated approach through the INternational Soft Tissue SaRcoma ConsorTium to evaluate the specific genetic abnormalities and generate and integrate molecular and clinical data related to patients with RMS across different trial settings. We review relevant data and present a consensus view on what molecular features should be assessed. In particular, we recommend the assessment of the MYOD1-LR122R mutation for risk escalation, as it has been associated with poor outcomes in spindle/sclerosing RMS and rare RMS with classic embryonal histopathology. The prospective analyses of rare fusion genes beyond PAX3/7-FOXO1 will generate new data linked to outcomes and assessment of TP53 mutations and CDK4 amplification may confirm their prognostic value. Pathogenic/likely pathogenic germline variants in TP53 and other cancer predisposition genes should also be assessed. DNA/RNA profiling of tumours at diagnosis/relapse and serial analyses of plasma samples is recommended where possible to validate potential molecular biomarkers, identify new biomarkers and assess how liquid biopsy analyses can have the greatest benefit. Together with the development of new molecularly-derived therapeutic strategies that we review, a synchronised international approach is expected to enhance progress towards improved treatment assignment, management and outcomes for patients with RMS.

Rationale and design of ON-TRK: a novel prospective non-interventional study in patients with TRK fusion cancer treated with larotrectinib.

BACKGROUND: Tropomyosin receptor kinase (TRK) fusion proteins resulting from neurotrophic tyrosine receptor kinase (NTRK) gene fusions are rare primary oncogenic drivers in a wide array of tumors. Larotrectinib is a first-in-class, highly selective, central nervous system-active TRK inhibitor approved by the US Food and Drug Administration (FDA), European Medicines Agency (EMA), and over 40 countries for the treatment of TRK fusion solid tumors in adult and pediatric patients. Due to the rarity of TRK fusion cancer, larotrectinib was granted accelerated approval based on a relatively small number of patients enrolled in three early phase trials. ON-TRK aims to evaluate the safety profile of larotrectinib in a broader population and over extended time periods. METHODS: ON-TRK is a prospective, non-interventional, open-label, multicenter, multi-cohort, post-approval study in adult and pediatric patients with locally advanced or metastatic TRK fusion cancer treated with larotrectinib that will describe the safety and effectiveness of larotrectinib in real-world practice conditions. Adult patients will be grouped by tumor type and followed for at least 2 years. Patients < 18 years old will be enrolled under a 'pediatric' cohort regardless of tumor type and will be followed for 5 years to evaluate the risk of potential long-term adverse effects of larotrectinib on their growth and development. The effectiveness of larotrectinib in the overall study population as well as in patient subgroups will also be evaluated. Procedures avoided in patients with infantile fibrosarcoma (e.g., amputation) and the number of patients who were able to undergo surgery with a curative intent (excluding amputation) because of the use of larotrectinib will be described. Larotrectinib treatment patterns in real-world practice, including dosing and duration of treatment, will be described. DISCUSSION: The FDA Accelerated Approval Program allows for earlier approval of and patient access to drugs that treat serious conditions and fill an unmet medical need. This study is designed to fulfill post-approval requirements set by the FDA as well as post-marketing requirements set forth by local regulatory bodies and is part of the risk management plan for the EMA. STUDY REGISTRATION: This study is registered at ClinicalTrials.gov ( NCT04142437 ). PROTOCOL VERSION: v2.5, 25 March 2021.

Tyrosine kinase-altered spindle cell neoplasms with EGFR internal tandem duplications.

In this study, we present two extra-renal pediatric spindle cell neoplasms with epidermal growth factor receptor (EGFR) internal tandem duplications (ITD). Histologically, these tumors demonstrated the same histologic features seen in other tyrosine kinase-altered spindle cell neoplasms, with one case showing abundant adipose tissue with cellular fibrous septae resembling lipofibromatosis and the other case showing fascicles of spindled cells resembling infantile fibrosarcoma. There was variable expression of CD34, S100, and SMA, and all cases were negative for panTRK. This case series adds to our molecular understanding of the spectrum of tyrosine kinase-altered spindle cell neoplasms and represents the first reported examples of EGFR ITDs in extra-renal tumors. The presence of EGFR alterations in the absence of gene fusions represents a potential therapeutic target and necessitates a broader testing panel for this group of tumors.

Congenital spindle cell rhabdomyosarcoma: An international cooperative analysis.

BACKGROUND: Spindle cell rhabdomyosarcoma (RMS) is a rare variant of RMS accounting for up to 10% of cases in infants. In older children and adults, spindle cell RMS is associated with MYOD1 mutations and a poor prognosis. In infants, it is associated with recurring fusions involving NCOA2 and VGLL2. Reports in the literature suggest a favorable prognosis for this subset, however, little is known about treatment and outcome data of infants with spindle cell RMS. METHODS: Characteristics, treatment, and outcome of an international cohort of 40 patients aged ≤ 12 months with spindle cell RMS treated from 1997 to 2018 were evaluated. RESULTS: Localized disease (LD) was diagnosed in 39 patients. The median age at diagnosis was 2.5 months (range 0-12 months). Expert pathologic review confirmed the diagnosis of spindle cell RMS in all patients. Among 26 tumors that had molecular evaluation, 13 had rearrangements of NCOA and/or VGLL. Multimodal treatment of infants with LD included conventional (age adjusted) chemotherapy (n = 37), resection (n = 31) and radiotherapy (RT) (n = 5, brachytherapy in 3). Complete remission was achieved in 37/39 patients. Progressive disease occurred in two infants, relapsed disease in three. Microscopically complete surgical resection was associated with five-year event-free survival (EFS) and overall survival (OS) of 100%. Two patients with tumors ≤ 5 cm were treated with microscopically complete resection only and were alive 1 and 4.2 years after diagnosis. The 5-year EFS and OS for infants with LD were 86% (±11; CI 95%) and 91% (±9; CI 95%), respectively. One patient had metastatic disease (NCOA fusion positive) with primary tumor in head and neck and brain metastases. This patient died despite chemotherapy and delayed resection of the primary tumor due to respiratory failure secondary to cytomegalovirus infection 1.2 years after diagnosis. CONCLUSION: Infants with spindle cell RMS have an excellent prognosis. Multimodal treatment including microscopically complete resection of the tumor is strongly recommended.

Deep Learning of Rhabdomyosarcoma Pathology Images for Classification and Survival Outcome Prediction.

Rhabdomyosarcoma (RMS), the most common malignant soft tissue tumor in children, has several histologic subtypes that influence treatment and predict patient outcomes. Assistance with histologic classification for pathologists as well as discovery of optimized predictive biomarkers is needed. A convolutional neural network for RMS histology subtype classification was developed using digitized pathology images from 80 patients collected at time of diagnosis. A subsequent embryonal rhabdomyosarcoma (eRMS) prognostic model was also developed in a cohort of 60 eRMS patients. The RMS classification model reached a performance of an area under the receiver operating curve of 0.94 for alveolar rhabdomyosarcoma and an area under the receiver operating curve of 0.92 for eRMS at slide level in the test data set (n = 192). The eRMS prognosis model separated the patients into predicted high- and low-risk groups with significantly different event-free survival outcome (likelihood ratio test; P = 0.02) in the test data set (n = 136). The predicted risk group is significantly associated with patient event-free survival outcome after adjusting for patient age and sex (predicted high- versus low-risk group hazard ratio, 4.64; 95% CI, 1.05-20.57; P = 0.04). This is the first comprehensive study to develop computational algorithms for subtype classification and prognosis prediction for RMS histopathology images. Such models can aid pathology evaluation and provide additional parameters for risk stratification.

Machine learning for rhabdomyosarcoma histopathology.

Correctly diagnosing a rare childhood cancer such as sarcoma can be critical to assigning the correct treatment regimen. With a finite number of pathologists worldwide specializing in pediatric/young adult sarcoma histopathology, access to expert differential diagnosis early in case assessment is limited for many global regions. The lack of highly-trained sarcoma pathologists is especially pronounced in low to middle-income countries, where pathology expertise may be limited despite a similar rate of sarcoma incidence. To address this issue in part, we developed a deep learning convolutional neural network (CNN)-based differential diagnosis system to act as a pre-pathologist screening tool that quantifies diagnosis likelihood amongst trained soft-tissue sarcoma subtypes based on whole histopathology tissue slides. The CNN model is trained on a cohort of 424 centrally-reviewed histopathology tissue slides of alveolar rhabdomyosarcoma, embryonal rhabdomyosarcoma and clear-cell sarcoma tumors, all initially diagnosed at the originating institution and subsequently validated by central review. This CNN model was able to accurately classify the withheld testing cohort with resulting receiver operating characteristic (ROC) area under curve (AUC) values above 0.889 for all tested sarcoma subtypes. We subsequently used the CNN model to classify an externally-sourced cohort of human alveolar and embryonal rhabdomyosarcoma samples and a cohort of 318 histopathology tissue sections from genetically engineered mouse models of rhabdomyosarcoma. Finally, we investigated the overall robustness of the trained CNN model with respect to histopathological variations such as anaplasia, and classification outcomes on histopathology slides from untrained disease models. Overall positive results from our validation studies coupled with the limited worldwide availability of sarcoma pathology expertise suggests the potential of machine learning to assist local pathologists in quickly narrowing the differential diagnosis of sarcoma subtype in children, adolescents, and young adults.

Somatic activating BRAF variants cause isolated lymphatic malformations.

Somatic activating variants in PIK3CA, the gene that encodes the p110α catalytic subunit of phosphatidylinositol 3-kinase (PI3K), have been previously detected in ∼80% of lymphatic malformations (LMs).1 , 2 We report the presence of somatic activating variants in BRAF in individuals with LMs that do not possess pathogenic PIK3CA variants. The BRAF substitution p.Val600Glu (c.1799T>A), one of the most common driver mutations in cancer, was detected in multiple individuals with LMs. Histology revealed abnormal lymphatic channels with immunopositivity for BRAFV600E in endothelial cells that was otherwise indistinguishable from PIK3CA-positive LM. The finding that BRAF variants contribute to low-flow LMs increases the complexity of prior models associating low-flow vascular malformations (LM and venous malformations) with mutations in the PI3K-AKT-MTOR and high-flow vascular malformations (arteriovenous malformations) with mutations in the RAS-mitogen-activated protein kinase (MAPK) pathway.3 In addition, this work highlights the importance of genetic diagnosis prior to initiating medical therapy as more studies examine therapeutics for individuals with vascular malformations.