提高星形细胞瘤动态对比增强MRI药代动力学参数可靠性的深度学习方法
本回顾性研究纳入386例经组织病理学诊断的星形细胞瘤患者,开发深度学习模型将DCE-MRI测得的动脉输入函数(AIF)转换为DSC-MRI来源的AIF,并验证改进后AIF所得药代动力学参数的可靠性和诊断性能。结果显示,使用神经网络生成的AIF后,Ktrans和Ve在星形细胞瘤分级中的AUC和组内相关系数均优于DCE-MRI直接测量的AIF。
要点
- 深度学习生成的AIF可提高DCE-MRI药代动力学参数在星形细胞瘤分级中的可靠性。
- 使用生成AIF时,平均Ktrans和Ve分级星形细胞瘤的AUC分别为0.88和0.87,高于DCE-AIF的0.72和0.70。
- 生成AIF的Ktrans和Ve组内相关系数分别为0.91和0.86,优于DCE-AIF的0.38和0.60。
核心结论
- 深度学习算法同时提高了MRI药代动力学参数在鉴别星形细胞瘤分级中的可靠性和诊断性能。
研究设计与样本
- 回顾性研究纳入386例经组织病理学诊断的星形细胞瘤患者,平均年龄52岁±16(标准差),其中男性226例。
- 患者于2010年4月至2018年1月术前接受DSC增强和DCE MRI检查。
- 从DSC增强MRI获得AIF(AIFDSC),从DCE MRI测得AIF(AIFDCE);模型训练将AIFDCE转换为AIFDSC,训练后以AIFDCE为输入输出神经网络生成的AIF(AIFgenerated DSC)。
- 使用三种不同AIF,从DCE MRI肿瘤区域平均计算容积转移常数(Ktrans)、血管外细胞外间隙分数体积(Ve)和血管血浆空间(Vp)。
诊断标准与关键数值
- 使用AIFgenerated DSC所得药代动力学参数在星形细胞瘤分级中的AUC高于AIFDCE:平均Ktrans为0.88(95%CI:0.81,0.93)vs 0.72(95%CI:0.63,0.79),P=0.04;平均Ve为0.87(95%CI:0.79,0.92)vs 0.70(95%CI:0.61,0.77),P=0.049。
- Ktrans和Ve使用AIFgenerated DSC的组内相关系数高于AIFDCE:分别为0.91 vs 0.38(P<0.001)和0.86 vs 0.60(P<0.001)。
- AIF分析中,基线信号强度(SI)、最大SI和流入斜率使用AIFgenerated DSC的组内相关系数高于AIFDCE:分别为0.77 vs 0.29(P<0.001)、0.68 vs 0.42(P=0.003)和0.66 vs 0.45(P=0.01)。
临床应用与阅片要点
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
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)。
英文原文(摘要)· 点击展开
Background Pharmacokinetic (PK) parameters obtained from dynamic contrast agent-enhanced (DCE) MRI evaluates the microcirculation permeability of astrocytomas, but the unreliability from arterial input function (AIF) remains a challenge. Purpose To develop a deep learning model that improves the reliability of AIF for DCE MRI and to validate the reliability and diagnostic performance of PK parameters by using improved AIF in grading astrocytomas. Materials and Methods This retrospective study included 386 patients (mean age, 52 years ± 16 [standard deviation]; 226 men) with astrocytomas diagnosed with histopathologic analysis who underwent dynamic susceptibility contrast (DSC)-enhanced and DCE MRI preoperatively from April 2010 to January 2018. The AIF was obtained from each sequence: AIF obtained from DSC-enhanced MRI (AIFDSC) and AIF measured at DCE MRI (AIFDCE). The model was trained to translate AIFDCE into AIFDSC, and after training, outputted neural-network-generated AIF (AIFgenerated DSC) with input AIFDCE. By using the three different AIFs, volume transfer constant (Ktrans), fractional volume of extravascular extracellular space (Ve), and vascular plasma space (Vp) were averaged from the tumor areas in the DCE MRI. To validate the model, intraclass correlation coefficients and areas under the receiver operating characteristic curve (AUCs) of the PK parameters in grading astrocytomas were compared by using different AIFs. Results The AIF-generated, DSC-derived PK parameters showed higher AUCs in grading astrocytomas than those derived from AIFDCE (mean Ktrans, 0.88 [95% confidence interval {CI}: 0.81, 0.93] vs 0.72 [95% CI: 0.63, 0.79], P = .04; mean Ve, 0.87 [95% CI: 0.79, 0.92] vs 0.70 [95% CI: 0.61, 0.77], P = .049, respectively). Ktrans and Ve showed higher intraclass correlation coefficients for AIFgenerated DSC than for AIFDCE (0.91 vs 0.38, P < .001; and 0.86 vs 0.60, P < .001, respectively). In AIF analysis, baseline signal intensity (SI), maximal SI, and wash-in slope showed higher intraclass correlation coefficients with AIFgenerated DSC than AIFDCE (0.77 vs 0.29, P < .001; 0.68 vs 0.42, P = .003; and 0.66 vs 0.45, P = .01, respectively. Conclusion A deep learning algorithm improved both reliability and diagnostic performance of MRI pharmacokinetic parameters for differentiating astrocytoma grades. © RSNA, 2020 Online supplemental material is available for this article.
引用
- Choi KS, You SH, Han Y, et al. Improving the Reliability of Pharmacokinetic Parameters at Dynamic Contrast-enhanced MRI in Astrocytomas: A Deep Learning Approach. Radiology. 2020. PMID: 32749203. doi:10.1148/radiol.2020192763
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。