Review examines multi-omics approaches to enhance diagnostic precision and treatment decisions in pediatric neuroblastoma.

Neuroblastoma is the most common extracranial solid tumor in children, presenting significant challenges in diagnosis and treatment due to its highly heterogeneous clinical manifestations and complex genetic background. In recent years, advances in transcriptomics have played a pivotal role in this field, not only aiding in the identification of molecular subtypes of tumors but also revealing potential mechanisms of drug resistance. Through comprehensive gene expression profiling and single-cell sequencing technology, researchers have deeply analyzed key interaction nodes within the metabolic-immune microenvironment, providing a theoretical basis for developing targeted therapeutic strategies. Concurrently, radiomics, leveraging imaging techniques such as MRI, PET-CT, and CT, quantitatively assesses the morphological and metabolic characteristics of tumors. This enables non-invasive prediction of MYCN amplification status, evaluation of bone marrow metastasis risk, and prognostic stratification, thereby supporting dynamic disease monitoring. In pathology, artificial intelligence technology is widely applied in the analysis of digital pathology images. It effectively identifies cellular diversity and immune microenvironment features in tissues, enhancing diagnostic accuracy and assisting in predicting potential gene mutations. More importantly, integrating transcriptomics, radiology, and pathology data through multi-omics approaches overcomes the limitations of single data types. This integration constructs more precise disease classification models and facilitates the development of personalized treatment plans. This review emphasizes the critical roles of transcriptomics, radiomics, digital pathology analysis, and multi-omics fusion strategies in enhancing diagnostic precision for neuroblastoma and optimizing treatment decisions.