DOI 10.1016/j.radi.2025.103113
Predicting EGFR mutation status in non-small cell lung cancer patients with brain metastases based on MRI radiomics: A systematic review and meta-analysis.
Аннотация
INTRODUCTION
This study evaluates the quality and diagnostic accuracy of Magnetic Resonance Imaging (MRI) radiomics-based prediction of epidermal growth factor receptor (EGFR) mutation status in non-small cell lung cancer (NSCLC) patients with brain metastasis.
METHODS
Six databases (PubMed, Embase, Web of Science, Cochrane Library, Scopus, and IEEE Xplore) were systematically searched up to June 2025. Quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool and Radiomics Quality Score (RQS). The predictive performance of MRI radiomics was quantitatively analyzed by pooling sensitivity (SEN), specificity (SPE), positive/negative likelihood ratios (PLR/NLR), diagnostic odds ratio (DOR), and area under the curve (AUC).
RESULTS
15 studies were included in the systematic review, of which 11 reported sufficient data for meta-analysis (10 training cohorts and 7 validation cohorts). QUADAS-2 indicated that the overall quality of the studies was considered acceptable. The mean RQS score of the included studies was 14.47 (40.19 % of the maximum). Training cohorts achieved the pooled sensitivity, specificity, PLR, NLR, DOR and AUC of MRI-based radiomics for predicting EGFR mutation status were 0.82 [95 % CI: 0.75-0.87], 0.85 [95 % CI: 0.77-0.90], 6.69 [95 % CI: 3.53-12.69], 0.13 [95 % CI: 0.06-0.18], 52.79 [95 % CI: 14.90-187.03], and 0.94 [95 % CI: 0.92-0.96], respectively. For the validation cohorts, these values were 0.77 [95 % CI: 0.69-0.84], 0.83 [95 % CI: 0.78-0.88], 4.64 [95 % CI: 3.45-6.25], 0.27 [95 % CI: 0.20-0.38], 16.69 [95 % CI: 9.85-29.19], and 0.85 [95 % CI: 0.81-0.88].
CONCLUSION
MRI radiomics-based models may be useful in predicting the EGFR mutation status in patients with brain metastases from NSCLC. However, the analysis revealed limitations including the retrospective design of most studies, geographic bias, and relatively low methodological quality.
IMPLICATIONS FOR PRACTICE: MRI radiomics may offer a promising non-invasive diagnostic approach for clinical use, providing valuable insights to guide clinical decision-making before obtaining pathological results.
Предметные рубрики MeSH
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.