Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 2 appraisals
Clinical & experimental metastasis
All-site radiotherapy for metastatic ewing's sarcoma: a short-term analysis of feasibility, response, and safety.
BACKGROUND: Metastatic Ewing sarcoma (EWS) has a poor prognosis. While metastasis-directed therapy benefits oligometastatic disease, the role of comprehensive all-site radiotherapy in widespread disease remains underexplored. This study aimed to preliminarily assess its short-term efficacy and safety. METHODS: This retrospective analysis included 21 consecutive metastatic EWS patients treated with helical tomotherapy (Aug 2024-Jun 2025). All known metastases and unresected primary tumors received radiotherapy (45-55 Gy in 20 fractions for most sites; 12-45 Gy for lung/pleural metastases). Concurrent systemic therapies included chemotherapy, tyrosine kinase inhibitors (TKIs), immune checkpoint inhibitors (ICIs), or combinations. Primary endpoints were local objective response rate (ORR, RECIST 1.1) at 2 months post-radiotherapy and acute toxicity (CTCAE 5.0). Systemic therapy subgroup analyses were exploratory. RESULTS: Median follow-up was 6 months (range 2-11). Among 77 target lesions, ORR was 61.0% (CR 48.1%), and disease control rate (DCR) was 97.4%. Soft tissue lesions had a significantly higher CR rate than bone metastases (78.3% vs 3.2%, p < 0.001), potentially influenced by RECIST 1.1 limitations and treatment heterogeneity. Median progression-free survival (PFS) was 6.0 months (95% CI: 2.30-9.70), and median overall survival (OS) was 8.0 months (95% CI: 6.69-9.31). Combination systemic therapy was associated with improved PFS (HR 3.94, 95%CI 1.32-11.78; p = 0.014), with chemotherapy-based regimens yielding the best PFS (8.5 months). TKI-containing regimens were linked to shorter PFS (4.0 vs 8.5 months, p = 0.048) due to selection bias. Acute toxicity was manageable, with grade 3 thrombocytopenia (19.0%) and pneumonitis (4.7%) resolving with treatment. CONCLUSION: All-site radiotherapy achieves promising short-term local control with manageable toxicity in metastatic EWS, demonstrating feasibility and a lesion site-specific response warranting further investigation. Systemic therapy, particularly chemotherapy, correlates with improved PFS. Given high systemic progression rates, long-term outcomes may benefit from integration with more effective systemic therapies, supporting future prospective trials.
2 May 2026
Read appraisal →Cancer research
Multicenter Histology Image Integration and Multiscale Deep Learning Support Machine Learning-Enabled Pediatric Sarcoma Classification
UNLABELLED: Pediatric sarcomas present diagnostic challenges due to their rarity and diverse subtypes, often requiring specialized pathology expertise and costly genetic tests. To overcome these barriers, we developed a computational pipeline leveraging deep learning methods to accurately classify pediatric sarcoma subtypes from digitized histology slides. To ensure classifier generalizability and minimize center-specific artifacts, a dataset comprising 867 whole-slide images (WSI) from three medical centers and the Children's Oncology Group was collected and harmonized. Multiple convolutional neural network and vision transformer (ViT) architectures were systematically evaluated as feature extractors for SAMPLER-based WSI representations, and input parameters, such as tile size combinations and resolutions, were tested and optimized. The analysis showed that advanced ViT foundation models (UNI and CONCH) significantly outperformed earlier approaches, and incorporating multiscale features enhanced classification accuracy. The optimized models achieved high performance, distinguishing rhabdomyosarcoma (RMS) from non-RMS soft-tissue sarcomas (NRSTS) with an AUC of 0.969 and differentiating RMS subtypes (alveolar vs. embryonal) with an AUC of 0.961. Additionally, a two-stage pipeline effectively identified scarce Ewing sarcoma images from other NRSTS (AUC = 0.929). Compared with conventional transformer-encoder architectures used for WSI representations, these SAMPLER-based classifiers were three orders of magnitude faster to train, despite operating entirely without a graphical processing unit. This study highlights that digital histopathology paired with rigorous image harmonization provides a powerful solution for pediatric sarcoma classification. SIGNIFICANCE: An approach pairing a multi-institutional dataset with a published pipeline extends imaging-based diagnostic capabilities and creates the potential for accurate, rapid cancer diagnoses across resource-limited and remote settings. This article is part of a special series: Driving Cancer Discoveries with Computational Research, Data Science, and Machine Learning/AI .
5 Apr 2026
Read appraisal →