摘要

BACKGROUND:Magnetic resonance imaging (MRI) of the knee is the preferred method for diagnosing knee injuries. However, interpretation of knee MRI is time-intensive and subject to diagnostic error and variability. An automated system for interpreting knee MRI could prioritize high-risk patients and assist clinicians in making diagnoses. Deep learning methods, in being able to automatically learn layers of features, are well suited for modeling the complex relationships between medical images and their interpretations. In this study we developed a deep learning model for detecting general abnormalities and specific diagnoses (anterior cruciate ligament [ACL] tears and meniscal tears) on knee MRI exams. We then measured the effect of providing the model's predictions to clinical experts during interpretation. METHODS AND FINDINGS:Our dataset consisted of 1,370 knee MRI exams performed at Stanford University Medical Center between January 1, 2001, and December 31, 2012 (mean age 38.0 years; 569 [41.5%] female patients). The majority vote of 3 musculoskeletal radiologists established reference standard labels on an internal validation set of 120 exams. We developed MRNet, a convolutional neural network for classifying MRI series and combined predictions from 3 series per exam using logistic regression. In detecting abnormalities, ACL tears, and meniscal tears, this model achieved area under the receiver operating characteristic curve (AUC) values of 0.937 (95% CI 0.895, 0.980), 0.965 (95% CI 0.938, 0.993), and 0.847 (95% CI 0.780, 0.914), respectively, on the internal validation set. We also obtained a public dataset of 917 exams with sagittal T1-weighted series and labels for ACL injury from Clinical Hospital Centre Rijeka, Croatia. On the external validation set of 183 exams, the MRNet trained on Stanford sagittal T2-weighted series achieved an AUC of 0.824 (95% CI 0.757, 0.892) in the detection of ACL injuries with no additional training, while an MRNet trained on the rest of the external data achieved an AUC of 0.911 (95% CI 0.864, 0.958). We additionally measured the specificity, sensitivity, and accuracy of 9 clinical experts (7 board-certified general radiologists and 2 orthopedic surgeons) on the internal validation set both with and without model assistance. Using a 2-sided Pearson's chi-squared test with adjustment for multiple comparisons, we found no significant differences between the performance of the model and that of unassisted general radiologists in detecting abnormalities. General radiologists achieved significantly higher sensitivity in detecting ACL tears (p-value = 0.002; q-value = 0.019) and significantly higher specificity in detecting meniscal tears (p-value = 0.003; q-value = 0.019). Using a 1-tailed t test on the change in performance metrics, we found that providing model predictions significantly increased clinical experts' specificity in identifying ACL tears (p-value < 0.001; q-value = 0.006). The primary limitations of our study include lack of surgical ground truth and the small size of the panel of clinical experts. CONCLUSIONS:Our deep learning model can rapidly generate accurate clinical pathology classifications of knee MRI exams from both internal and external datasets. Moreover, our results support the assertion that deep learning models can improve the performance of clinical experts during medical imaging interpretation. Further research is needed to validate the model prospectively and to determine its utility in the clinical setting.

译文

背景: 膝关节磁共振成像 (MRI) 是诊断膝关节损伤的首选方法。然而,膝关节 MRI 的解释是时间密集型的,并且容易出现诊断错误和变异。一个解释膝盖核磁共振成像的自动化系统可以优先考虑高危患者,并帮助临床医生做出诊断。深度学习方法能够自动学习特征层,非常适合建模医学图像及其解释之间的复杂关系。在这项研究中,我们开发了一个深度学习模型,用于检测膝关节 MRI 检查的一般异常和特定诊断 (前交叉韧带 [前交叉韧带] 撕裂和半月板撕裂)。然后我们测量了在解释过程中向临床专家提供模型预测的效果。方法和结果: 我们的数据集包括 2001年1月1日至 2012年12月31日间在斯坦福大学医学中心进行的 1,370 次膝关节 MRI 检查 (平均年龄 38.0 岁; 569 [41.5%] 名女性患者)。3 名肌肉骨骼放射学家的多数票在 120 次检查的内部验证集中建立了参考标准标签。我们开发了 MRNet,这是一种卷积神经网络,用于对每次检查的 3 个序列的 MRI 序列和组合预测进行分类,使用逻辑回归。在检测异常、前交叉韧带撕裂和半月板撕裂时,该模型在受试者操作特征曲线 (AUC) 值下的面积为 0.937 (95% CI 0.895,0.980), 内部验证集中分别为 0.965 (95% CI 0.938,0.993) 和 0.847 (95% CI 0.780,0.914)。我们还从克罗地亚里耶卡的临床医院中心获得了 917 项具有矢状面 T1-weighted 系列和 ACL 损伤标签的公共数据集。在 183 项检查的外部验证组中,在没有额外训练的情况下,经斯坦福矢状面 T2-weighted 系列训练的 MRNet 在检测前交叉韧带损伤方面的 AUC 达到了 0.824 (95% CI 0.757,0.892), 而对其余外部数据进行 MRNet 训练的 AUC 为 0.911(95% CI 0.864,0.958)。我们还测量了 9 名临床专家 (7 名董事会认证的普通放射科医生和 2 名整形外科医生) 在内部验证集中的特异性、敏感性和准确性,无论是否有模型辅助。使用双面皮尔逊卡方检验,并对多重比较进行调整,我们发现模型的性能和未经辅助的普通放射科医生在检测异常方面没有显著差异。普通放射科医生在检测前交叉韧带撕裂方面取得了显著更高的灵敏度 (p值 = 0.002; q值 = 0.019),在检测半月板撕裂方面取得了显著更高的特异性 (p值 = 0.003; q 值 = 0.019)。通过对性能指标变化的单尾 t检验,我们发现提供模型预测显著提高了临床专家识别 ACL 撕裂的特异性 (p值 <0.001; q 值 = 0.006)。我们研究的主要局限性包括缺乏手术依据和临床专家小组规模小。结论: 我们的深度学习模型可以从内部和外部数据集快速生成准确的膝关节 MRI 检查的临床病理学分类。此外,我们的结果支持深度学习模型可以提高临床专家在医学成像解释中的表现的断言。需要进一步的研究来前瞻性地验证该模型,并确定其在临床环境中的效用。

Magnetic Resonance Imaging

肿瘤 影像 诊断方式
概述  :  

磁共振成像(MRI)是根据生物体磁性核(氢核)在磁场中的表现特性成像的高新技术。二十余年来,随着超导技术、低温技术、磁体技术、电子技术、成像技术和计算机等相关技术的进步,磁共振成像技术得到了飞速发展。如今,其已广泛应用于临床,成为现代医学影像领域中不可缺少的一员。MRI的物理基础是核磁共振(NMR)理论。所谓NMR,是指与物质磁性核磁场有关的共振现象,也可以说是低能量电磁波,即射频波与既有角动量又有磁矩的核系统在外界磁场中相互作用所表现出来的共振特性。NMR的本质是

Magnetic   英 /mæɡˈnetɪk/   美 /mæɡˈnetɪk/

释    义   adj. 地磁的;有磁性的;有吸引力的

同根词   magnetized adj. 已磁化的

               magnetically adv. 有磁力地;有吸引力地

               magnetism n. 磁性,磁力;磁学;吸引力

               magnetized v. 磁化(magnetize的过去分词);吸引

               magnetize vi. 磁化;受磁

               magnetize vt. 吸引;使磁化

               magnetise vt. 使……磁化;使……有磁力

例    句   Due to the magnetic effects, the occurrence rate of the instability is not symmetric in longitudes even at the magnetic equator. 由于地磁位型的不同,发生率的分布并不具有经度对称性,即使在磁赤道附近也如此。

 

Resonance   英 /ˈrezənəns/   美 /ˈrezənəns/

释    义   n. [力] 共振;共鸣;反响

同根词   resonant adj. 洪亮的,共振的;共鸣的

               resonating adj. 产生共鸣的

               resonator n. [声] 共鸣器,共鸣体;共振器

               resonating n. 感通

               resonating v. 产生共鸣;回响(resonate 的ing形式)

               resonate vi. 共鸣;共振

               resonate vt. 共鸣;共振

例    句   Resonance would occur again, but not so strong as before. 共振会再次发生,但不如先前那么强。

 

Imaging   英 /ˈɪmɪdʒɪŋ/   美 /ˈɪmɪdʒɪŋ/

释    义   n. 成像;v. 想像(image的ing形式);画…的像

同根词   imaginary adj. 虚构的,假想的;想像的;虚数的

               imaginative adj. 虚构的;富于想像的;有创造力的

               imaginable adj. 可能的;可想像的

               image n. 影像;想象;肖像;偶像

               imagine vi. 想像;猜想;想像起来

               image vt. 想象;反映;象征;作…的像

               imagine vt. 想像;猜想;臆断

例    句   So using brain imaging, she focused on the white matter, or nerve tissue, of the brain. 因此,观察大脑成像时,她将注意力放在大脑的白质或神经组织上。

请扫描右侧二维码,免费查看词汇专业知识背景