注意力引导深度学习分析化学交换饱和转移MRI鉴别脑转移瘤进展与放射性坏死
本研究纳入93例接受立体定向放射外科治疗的脑转移患者共230个病灶,开发带两种新注意力机制的三维Transformer模型,用多模态化学交换饱和转移MRI区分肿瘤进展与放射性坏死。六模态联合时AUC最高达0.87±0.01,提示多模态MRI输入对SRS后病灶评估有重要价值。
要点
- 六模态联合的注意力引导深度学习模型鉴别肿瘤进展与放射性坏死的AUC达0.87±0.01。
- 化学交换饱和转移MRI与T1/T2图或常规结构MRI联合可显著提升鉴别性能。
- 多模态MRI输入对SRS后脑转移病灶评估具有重要价值。
核心结论
- 注意力引导深度学习分析化学交换饱和转移MRI在准确区分放射性坏死与肿瘤进展方面显示出较强潜力。
研究设计与样本
- 研究纳入93例接受SRS数月后的患者共230个脑转移病灶,采集3D酰胺质子转移磁化转移率、 relayed nuclear Overhauser效应磁化转移率、T1/T2参数图及增强T1加权和T2-FLAIR图像。
- 病灶结局经组织病理学和/或至少6个月随访的系列临床影像(含灌注成像)确认,数据分为训练集(47例患者、184个病灶)和独立测试集(46例患者、46个病灶)。
- 开发了带两种新注意力机制的三维Transformer模型,用不同多模态MRI输入组合对病灶进行分类。
主要发现
- 双通道模型中,增强T1加权与T2-FLAIR的AUC为0.78±0.01,酰胺质子转移磁化转移率与relayed nuclear Overhauser效应磁化转移率的AUC为0.76±0.01。
- 将酰胺质子转移磁化转移率和relayed nuclear Overhauser效应磁化转移率与T1/T2图或增强T1加权/T2-FLAIR联合后性能大幅提升,AUC分别为0.84±0.02和0.85±0.02。
- 使用全部6种模态时性能最高,AUC为0.87±0.01。
临床怎么用
- SRS后脑转移病灶出现难以鉴别的影像学改变时,可考虑采用多模态化学交换饱和转移MRI联合常规结构MRI辅助区分肿瘤进展与放射性坏死。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: Stereotactic radiosurgery (SRS) is a standard treatment for brain metastases; however, it may lead to radiation necrosis (RN). RN can be virtually indistinguishable from tumor progression (TP), which can have significant clinical implications on appropriate, time-sensitive treatment. This study investigated the effectiveness of multimodal chemical exchange saturation transfer magnetic resonance imaging (MRI), combined with T1/T2 mapping and/or conventional structural MRI, in addressing this diagnostic challenge, when analyzed through attention-guided deep learning. METHODS AND MATERIALS: MRI data (3-dimensional amide proton transfer magnetization transfer ratio [AmideMTR], relayed nuclear Overhauser effect magnetization transfer ratio [rNOEMTR], T1 and T2 parametric maps, and postcontrast T1-weighted [T1c] and T2-weighted fluid-attenuated inversion recovery [T2-FLAIR] images) were acquired from 93 patients (230 brain metastases lesions) treated with SRS a few months prior. Lesion outcomes (TP/RN) were confirmed via histopathology and/or serial clinical imaging, including the use of perfusion imaging, over a follow-up period of at least 6 months. Data were split into training (47 patients; 184 lesions) and independent testing (46 patients; 46 lesions) sets. A 3-dimensional transformer model with 2 new attention mechanisms was developed to classify lesions using various combinations of multimodal MRI inputs. RESULTS: Among dual-channel models, T1c and T2-FLAIR yielded an area under the receiver operating characteristic curve (AUC) of 0.78 ± 0.01, whereas AmideMTR and rNOEMTR maps achieved 0.76 ± 0.01. Integrating AmideMTR and rNOEMTR with either T1/T2 maps or T1c/T2-FLAIR substantially improved performance (AUC = 0.84 ± 0.02 and 0.85 ± 0.02, respectively). The highest performance (AUC = 0.87 ± 0.01) was achieved using all 6 modalities. CONCLUSIONS: Attention-guided deep-learning analysis of chemical exchange saturation transfer MRI shows strong potential for accurately distinguishing RN from TP, underscoring the significance of multimodal MRI inputs for post-SRS lesion evaluation.
引用
- Bhatti NB, Young D, Lam WW, et al. Attention-Guided Deep Learning of Chemical Exchange Saturation Transfer Magnetic Resonance Imaging to Differentiate Between Tumor Progression and Radiation Necrosis in Brain Metastasis. Int J Radiat Oncol Biol Phys. 2025. PMID: 41348074. doi:10.1016/j.ijrobp.2025.10.040
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。