Sarcoma classification by DNA methylation profiling in clinical everyday life: the Charité experience

General Applicability of Existing College of American Pathologists Accreditation Requirements to Clinical Implementation of Machine Learning-Based Methods in Molecular Oncology Testing

CONTEXT.—

The College of American Pathologists (CAP) accreditation requirements for clinical laboratory testing help ensure laboratories implement and maintain systems and processes that are associated with quality. Machine learning (ML)-based models share some features of conventional laboratory testing methods. Accreditation requirements that specifically address clinical laboratories' use of ML remain in the early stages of development.

OBJECTIVE.—

To identify relevant CAP accreditation requirements that may be applied to the clinical adoption of ML-based molecular oncology assays, and to provide examples of current and emerging ML applications in molecular oncology testing.

DESIGN.—

CAP accreditation checklists related to molecular pathology and general laboratory practices (Molecular Pathology, All Common and Laboratory General) were reviewed. Examples of checklist requirements that are generally applicable to validation, revalidation, quality management, infrastructure, and analytical procedures of ML-based molecular oncology assays were summarized. Instances of ML use in molecular oncology testing were assessed from literature review.

RESULTS.—

Components of the general CAP accreditation framework that exist for traditional molecular oncology assay validation and maintenance are also relevant for implementing ML-based tests in a clinical laboratory. Current and emerging applications of ML in molecular oncology testing include DNA methylation profiling for central nervous system tumor classification, variant calling, microsatellite instability testing, mutational signature analysis, and variant prediction from histopathology images.

CONCLUSIONS.—

Currently, much of the ML activity in molecular oncology is within early clinical implementation. Despite specific considerations that apply to the adoption of ML-based methods, existing CAP requirements can serve as general guidelines for the clinical implementation of ML-based assays in molecular oncology testing.

Classification of Fibro-Osseous Tumors in the Craniofacial Bones Using DNA Methylation and Copy Number Alterations

Fibro-osseous tumors of the craniofacial bones are a heterogeneous group of lesions comprising cemento-osseous dysplasia (COD), cemento-ossifying fibroma (COF), juvenile trabecular ossifying fibroma (JTOF), psammomatoid ossifying fibroma (PsOF), fibrous dysplasia (FD), and low-grade osteosarcoma (LGOS) with overlapping clinicopathological features. However, their clinical behavior and treatment differ significantly, underlining the need for accurate diagnosis. Molecular diagnostic markers exist for subsets of these tumors, including GNAS mutations in FD, SATB2 fusions in PsOF, mutations involving the RAS-MAPK signaling pathway in COD, and MDM2 amplification in LGOS. Because DNA methylation and copy number profiling are well established for the classification of central nervous system tumors, we aimed to investigate whether this tool might be used as well for classifying fibro-osseous tumors in the craniofacial bones. We collected a well-characterized, multicenter cohort with available molecular data, including COD (n = 20), COF (n = 13), JTOF (n = 10), PsOF (n = 25), FD (n = 23), LGOS (n = 4), and high-grade osteosarcoma (HGOS; n = 11). Genome-wide DNA methylation and copy number variation data were generated using the Illumina Infinium Methylation EPIC array interrogating >850 000 CpG sites. DNA methylation profiling yielded evaluable results in 73/106 tumors, including 6 CODs, 12 COFs, 6 JTOFs, 19 PsOFs, 18 FDs, 2 LGOSs, and 10 HGOSs. Unsupervised clustering and dimensionality reduction (Uniform Manifold Approximation and Projection) revealed that FD, extragnatic PsOF, and HGOS formed distinct clusters. Surprisingly, COD, COF, JTOF, and mandibular PsOF clustered together, apart from other craniofacial bone tumors. LGOS did not form a distinct cluster, likely due to the low number of cases. Copy number analysis revealed that FD, COD, COF, JTOF, and PsOF were typically characterized by flat copy number profiles compared with LGOS with gains of chromosome 12 and HGOS with multiple heterogeneous copy number alterations. In conclusion, using DNA methylation and copy number profiles, benign fibro-osseous tumors can be separated from low-grade and HGOSs in the craniofacial bones, which is of diagnostic value in challenging cases with overlapping clinicopathological features.

cIMPACT-NOW update 9: Recommendations on utilization of genome-wide DNA methylation profiling for central nervous system tumor diagnostics

Genome-wide DNA methylation signatures correlate with and distinguish central nervous system (CNS) tumor types. Since the publication of the initial CNS tumor DNA methylation classifier in 2018, this platform has been increasingly used as a diagnostic tool for CNS tumors, with multiple studies showing the value and utility of DNA methylation-based classification of CNS tumors. A Consortium to Inform Molecular and Practical Approaches to CNS Tumor Taxonomy (cIMPACT-NOW) Working Group was therefore convened to describe the current state of the field and to provide advice based on lessons learned to date. Here, we provide recommendations for the use of DNA methylation-based classification in CNS tumor diagnostics, emphasizing the attributes and limitations of the modality. We emphasize that the methylation classifier is one diagnostic tool to be used alongside previously established diagnostic tools in a fully integrated fashion. In addition, we provide examples of the inclusion of DNA methylation data within the layered diagnostic reporting format endorsed by the World Health Organization (WHO) and the International Collaboration on Cancer Reporting. We emphasize the need for backward compatibility of future platforms to enable accumulated data to be compatible with new versions of the array. Finally, we outline the specific connections between methylation classes and CNS WHO tumor types to aid in the interpretation of classifier results. It is hoped that this update will assist the neuro-oncology community in the interpretation of DNA methylation classifier results to facilitate the accurate diagnosis of CNS tumors and thereby help guide patient management.

Classification of pediatric soft and bone sarcomas using DNA methylation-based profiling

Pediatric sarcomas present heterogeneous morphology, genetics and clinical behavior posing a challenge for an accurate diagnosis. DNA methylation is an epigenetic modification that coordinates chromatin structure and regulates gene expression, determining cell type and function. DNA methylation-based tumor profiling classifier for sarcomas (known as sarcoma classifier) from the German Cancer Research Center (Deutsches Krebsforschungszentrum) was applied to 122 pediatric sarcomas referred to a reference pediatric oncology hospital. The classifiers reported 88.5% of agreement between histopathological and molecular classification confirming the initial diagnosis of all osteosarcomas and Ewing sarcomas. The Ewing-like sarcomas were reclassified into sarcomas with BCOR or CIC alterations, later confirmed by orthogonal diagnostic techniques. Regarding the CNAs profile, osteosarcomas had several chromosomal gains and losses as well as chromothripsis, whereas Ewing sarcomas had few large events, such as amplifications of chromosomes 8 and 12. The molecular classification together with clinical and histopathological assessment could improve the diagnosis of pediatric sarcomas although there are limitations to deal with more rare classes. This study provides an increase in the number of sarcomas evaluated for DNA methylation profiling in the pediatric population.

Sarcoma diagnosis by DNA methylation classifier: A systematic review, current status and future prospects

Sarcomas, a diverse group of malignant tumors originating from connective tissues, present substantial diagnostic challenges due to their histological heterogeneity. Traditional diagnostic methods include histomorphology along with immunohistochemistry is necessary for primary evaluation. Fluorescence in situ hybridization (FISH) is a supplementary tool that helps with additional findings. However it is very difficult sometimes to accurately classify sarcoma subtypes despite all these tools. Recent advancements in DNA methylation profiling have emerged as a promising approach to enhance the precision of sarcoma diagnosis. This paper delves into the role of DNA methylation classifiers in diagnosing sarcomas, emphasizing their potential to improve diagnostic accuracy, inform treatment decisions, and ultimately enhance patient outcomes.

Malignant Peripheral Nerve Sheath Tumor (MPNST) With Smooth Muscle Differentiation of the Uterus-A Case Report With Emphasis on Diagnostic Pitfalls and Value of DNA Methylation Analysis

With no more than two dozen cases reported in the literature, malignant peripheral nerve sheath tumor (MPNST) is a rare primary mesenchymal neoplasm arising in the female genital tract. Most cases occurred in middle-aged adults with high grade histology, unfavorable clinical outcome, and no history of neurofibromatosis type 1. Its extreme rarity in this site no doubt poses a diagnostic challenge during routine clinical practice. In the following, we report an additional case of uterine MPNST occurring in a 49-year-old Chinese woman, which was initially misdiagnosed as a leiomyosarcoma. The primary tumor showed two distinctive components-a high-grade poorly differentiated component with markedly pleomorphic spindle cells arranged in a peritheliomatous pattern; and a leiomyosarcoma-like (LMS-like) component with tumor cells displaying obvious myoid differentiation. The patient suffered a recurrence less than 2 years later with the recurrent tumor demonstrating similar features to the high-grade component of the primary tumor. The patient eventually succumbed 46 months later after developing another recurrence despite receiving targeted therapy and chemotherapy. On retrospective molecular analysis, no clinically relevant fusion transcript was detected on RNA sequencing. Interestingly instead, DNA methylation analysis showed the tumor clustered with the "MPNST" group in the German Cancer Research Center (DKFZ) sarcoma classifier. The tumor was also found to have EED gene homozygous deletion, multiple copy number alterations and loss of H3K27me3 expression in both high-grade and LMS-like components. Combining histology with all the ancillary tests results, the diagnosis was most consistent with MPNST. Our case highlights the diagnostic pitfalls for MPNST arising in the female genital tract and the potential clinical utility of DNA methylation analysis.

Head and neck cancer of unknown primary: unveiling primary tumor sites through machine learning on DNA methylation profiles

BACKGROUND

The unknown tissue of origin in head and neck cancer of unknown primary (hnCUP) leads to invasive diagnostic procedures and unspecific and potentially inefficient treatment options for patients. The most common histologic subtype, squamous cell carcinoma, can stem from various tumor primary sites, including the oral cavity, oropharynx, larynx, head and neck skin, lungs, and esophagus. DNA methylation profiles are highly tissue-specific and have been successfully used to classify tissue origin. We therefore developed a support vector machine (SVM) classifier trained with publicly available DNA methylation profiles of commonly cervically metastasizing squamous cell carcinomas (n = 1103) in order to identify the primary tissue of origin of our own cohort of squamous cell hnCUP patient's samples (n = 28). Methylation analysis was performed with Infinium MethylationEPIC v1.0 BeadChip by Illumina.

RESULTS

The SVM algorithm achieved the highest overall accuracy of tested classifiers, with 87%. Squamous cell hnCUP samples on DNA methylation level resembled squamous cell carcinomas commonly metastasizing into cervical lymph nodes. The most frequently predicted cancer localization was the oral cavity in 11 cases (39%), followed by the oropharynx and larynx (both 7, 25%), skin (2, 7%), and esophagus (1, 4%). These frequencies concord with the expected distribution of lymph node metastases in epidemiological studies.

CONCLUSIONS

On DNA methylation level, hnCUP is comparable to primary tumor tissue cancer types that commonly metastasize to cervical lymph nodes. Our SVM-based classifier can accurately predict these cancers' tissues of origin and could significantly reduce the invasiveness of hnCUP diagnostics and enable a more precise therapy after clinical validation.

Brain Tumor Classification by Methylation Profile

The goal of the methylation classifier in brain tumor classification is to accurately classify tumors based on their methylation profiles. Accurate brain tumor diagnosis is the first step for healthcare professionals to predict tumor prognosis and establish personalized treatment plans for patients. The methylation classifier can be used to perform classification on tumor samples with diagnostic difficulties due to ambiguous histology or mismatch between histopathology and molecular signatures, i.e., not otherwise specified (NOS) cases or not elsewhere classified (NEC) cases, aiding in pathological decision-making. Here, the authors elucidate upon the application of a methylation classifier as a tool to mitigate the inherent complexities associated with the pathological evaluation of brain tumors, even when pathologists are experts in histopathological diagnosis and have access to enough molecular genetic information. Also, it should be emphasized that methylome cannot classify all types of brain tumors, and it often produces erroneous matches even with high matching scores, so, excessive trust is prohibited. The primary issue is the considerable difficulty in obtaining reference data regarding the methylation profile of each type of brain tumor. This challenge is further amplified when dealing with recently identified novel types or subtypes of brain tumors, as such data are not readily accessible through open databases or authors of publications. An additional obstacle arises from the fact that methylation classifiers are primarily research-based, leading to the unavailability of charging patients. It is important to note that the application of methylation classifiers may require specialized laboratory techniques and expertise in DNA methylation analysis.

Clear cell chondrosarcoma: a review of clinicopathologic characteristics, differential diagnoses, and patient management

Clear cell chondrosarcoma (CCC), an extremely rare primary bone tumor, is currently classified by the World Health Organization as a low-grade malignant cartilaginous neoplasm. Clinically, CCC occurs primarily in males with a peak incidence in the third to fifth decades of life, and occasionally, it presents in skeletally immature patients. Unlike conventional chondrosarcoma, CCC has a predilection for the epiphysis of long bones and often displays radiologic features reminiscent of chondroblastoma. The recommended treatment is wide operative resection. CCC has a local recurrence rate of approximately 30%, and nearly 20% cases metastasize mainly to bone and lung often a decade after surgical intervention. Incomplete excision or curettage is associated with a high rate of recurrence. Histologically, the process is characterized by infiltrative lobules and sheets of round to oval cells with abundant cleared cytoplasm and well-defined cell borders associated with trabecula of osteoid and woven bone, scattered osteoclasts, and foci of conventional low-grade chondrosarcoma in about one-half of cases. Correlation with clinical and radiologic characteristics, such as epiphyseal location and young patient age, assists in establishing a correct diagnosis. Pathologic diagnosis of CCC is complicated by the low diagnostic accuracy of core needle biopsy, overlapping histologic features with other matrix-rich primary bone tumors, and a lack of a specific immunohistochemical and molecular profile. DNA methylation-based profiling classifier (sarcoma classifier) is one recent technologic advancement that may help to confirm the histopathological diagnosis of CCC or indicate the need for thorough reassessment in cases where results contradict previous conventional findings.