Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI
Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI
复制标题
DOI：
10.1007/s00330-019-06205-9
复制
发表时间：
2019-07-01
影响因子：
5.9
通讯作者：
Letzen, Brian
中科院分区：
文献类型：
--
作者：
Hamm, Charlie A.;Wang, Clinton J.;Letzen, Brian
目的开发和验证一种基于概念验证卷积神经网络(CNN)的深度学习系统(DLS)，该系统可在多期MRI上对常见肝脏病变进行分类。方法通过迭代优化网络结构和训练病例，设计一种定制的CNN，最终由三个卷积层和相关的校正线性单元、两个最大汇聚层和两个完全连接的层组成。研究对象为6大类494个具有典型影像特征的肝脏病变，分为训练组和测试组。使用已建立的增强技术来生成43,400个训练样本。使用ADAM优化器进行培训。进行蒙特卡罗交叉验证。模型设计完成后，在相同的不可见测试集上，将最终CNN的分类准确性与两名委员会认证的放射科医生进行比较。结果DLS显示出92%的准确性，92%的敏感性(Sn)和98%的特异性(Sp)。测试集在随机未见案例的单次运行中的性能显示，平均有90%的Sn和98%的Sp。放射科医生对这些病例的平均Sn/Sp为82.5%/96.5%。结果显示，与放射科医生的60%/70%相比，90%的SN值用于肝细胞癌(HCC)的分类。对于肝细胞癌的分类，真阳性率为93.5%，假阳性率为1.6%，受试者操作特征面积在曲线下0.992。每个病灶的计算时间为5.6ms。结论这项初步的深度学习研究证明了从六种常见的肝脏病变类型中对具有典型成像特征的病变进行分类的可行性，并推动了未来更大的多机构数据集和更复杂的成像表现的研究。关键点中心点深度学习在体积多相MRI上对肝脏病变的分类表现出很高的性能，显示出作为放射科医生最终决策支持工具的潜力。中心点显示每个病变的分类时间为几毫秒，深度学习系统可以以及时高效的方式被结合到临床工作流程中。
ObjectivesTo develop and validate a proof-of-concept convolutional neural network (CNN)-based deep learning system (DLS) that classifies common hepatic lesions on multi-phasic MRI.MethodsA custom CNN was engineered by iteratively optimizing the network architecture and training cases, finally consisting of three convolutional layers with associated rectified linear units, two maximum pooling layers, and two fully connected layers. Four hundred ninety-four hepatic lesions with typical imaging features from six categories were utilized, divided into training (n=434) and test (n=60) sets. Established augmentation techniques were used to generate 43,400 training samples. An Adam optimizer was used for training. Monte Carlo cross-validation was performed. After model engineering was finalized, classification accuracy for the final CNN was compared with two board-certified radiologists on an identical unseen test set.ResultsThe DLS demonstrated a 92% accuracy, a 92% sensitivity (Sn), and a 98% specificity (Sp). Test set performance in a single run of random unseen cases showed an average 90% Sn and 98% Sp. The average Sn/Sp on these same cases for radiologists was 82.5%/96.5%. Results showed a 90% Sn for classifying hepatocellular carcinoma (HCC) compared to 60%/70% for radiologists. For HCC classification, the true positive and false positive rates were 93.5% and 1.6%, respectively, with a receiver operating characteristic area under the curve of 0.992. Computation time per lesion was 5.6ms.ConclusionThis preliminary deep learning study demonstrated feasibility for classifying lesions with typical imaging features from six common hepatic lesion types, motivating future studies with larger multi-institutional datasets and more complex imaging appearances.Key Points center dot Deep learning demonstrates high performance in the classification of liver lesions on volumetric multi-phasic MRI, showingpotential as an eventual decision-support tool for radiologists.center dot Demonstrating a classification runtime of a few milliseconds per lesion, a deep learning system could be incorporated into the clinical workflow in a time-efficient manner.