使用新型AUROC损失函数改进卷积神经网络对儿童低级别神经上皮肿瘤分子亚型的识别
Improving Pediatric Low-Grade Neuroepithelial Tumors Molecular Subtype Identification Using a Novel AUROC Loss Function for Convolutional Neural Networks
AI总结：
本研究提出一种新型AUROC损失函数，用于改进CNN在MRI上识别儿童低级别神经上皮肿瘤分子亚型的性能，显著提升了分类准确率，为非侵入性诊断提供了新方法。
摘要：
儿童低级别神经上皮肿瘤（PLGNT）是最常见的儿童癌症类型，占儿童脑肿瘤的40%，识别PLGNT分子亚型对于治疗规划至关重要。然而，确定PLGNT亚型的金标准是活检，这对患者来说可能不切实际或存在危险。本研究通过引入一种专门提高模型受试者工作特征曲线下面积（AUROC）的损失函数，改进了卷积神经网络（CNN）通过MRI扫描对PLGNT亚型进行分类的性能，提供了一种非侵入性的诊断替代方案。本研究整理了一个包含339名PLGNT儿童（143例BRAF融合，71例BRAF V600E突变，125例非BRAF）的回顾性数据集。我们采用了带有蒙特卡洛随机数据分割的CNN模型。基线模型使用二元交叉熵（BCE）进行训练，在区分BRAF融合和BRAF V600E突变方面达到了86.11%的AUROC，使用我们提出的AUROC损失函数后提高到87.71%（p值0.045）。在多分类中，AUROC从74.42%提高到76.59%（p值0.0016）。
英文摘要：
Pediatric Low-Grade Neuroepithelial Tumors (PLGNT) are the most common pediatric cancer type, accounting for 40% of brain tumors in children, and identifying PLGNT molecular subtype is crucial for treatment planning. However, the gold standard to determine the PLGNT subtype is biopsy, which can be impractical or dangerous for patients. This research improves the performance of Convolutional Neural Networks (CNNs) in classifying PLGNT subtypes through MRI scans by introducing a loss function that specifically improves the model's Area Under the Receiver Operating Characteristic (ROC) Curve (AUROC), offering a non-invasive diagnostic alternative. In this study, a retrospective dataset of 339 children with PLGNT (143 BRAF fusion, 71 with BRAF V600E mutation, and 125 non-BRAF) was curated. We employed a CNN model with Monte Carlo random data splitting. The baseline model was trained using binary cross entropy (BCE), and achieved an AUROC of 86.11% for differentiating BRAF fusion and BRAF V600E mutations, which was improved to 87.71% using our proposed AUROC loss function (p-value 0.045). With multiclass classification, the AUROC improved from 74.42% to 76. 59% (p-value 0.0016).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
