文献速递神经技术与安全MR

基于深度多任务学习与随机森林的脉冲序列类型及方向系列分类

Deep multi-task learning and random forest for series classification by pulse sequence type and orientation.
PubMed 文献 · Neuroradiology · 2022-07-30

研究构建卷积神经网络与随机森林的集成模型,对25种脑部MRI序列和4种方向进行系列分类;在自建数据集A上集成模型序列准确率98%,在外部医院数据集B上达99%,所有模型方向准确率均>99%。

要点

  • 集成模型在数据集A上序列分类准确率98%,数据集B上99%,方向分类所有模型均>99%。
  • 随机森林基于DICOM元数据,神经网络基于图像内容,二者互补提升系列识别。
  • 该方法可辅助后处理与PACS阅片时的图像路由,适应多设备多站点复杂命名。

核心结论

  • 集成模型能应对当代临床实践中脑部MRI研究的复杂性,较既往概念验证工作覆盖更广的序列多样性与方向分类。

研究设计与样本

  • 研究论文;数据集A来自本院,训练集16828项检查/48512个系列/112028幅图像,验证集4746项检查/16612个系列/26222幅图像,测试集6348项检查/58705个系列/3314018幅图像;数据集B来自另一家医院用于域外外部验证,含1252项检查/2150个系列/234944幅图像。

诊断标准与关键数值

  • 序列分类总体准确率:数据集A上神经网络95%、随机森林97%、集成模型98%;数据集B上神经网络98%、随机森林99%、集成模型99%;方向分类准确率所有模型在两个数据集上均>99%。

临床应用与阅片要点

  • 作者提出集成模型可用于系列识别,以协助后处理与PACS查看时的图像路由,适应多扫描仪和多站点的复杂命名。

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

PURPOSE: Increasingly complex MRI studies and variable series naming conventions reveal limitations of rule-based image routing, especially in health systems with multiple scanners and sites. Accurate methods to identify series based on image content would aid post-processing and PACS viewing. Recent deep/machine learning efforts classify 5-8 basic brain MR sequences. We present an ensemble model combining a convolutional neural network and a random forest classifier to differentiate 25 brain sequences and image orientation.

METHODS: Series were grouped by descriptions into 25 sequences and 4 orientations. Dataset A, obtained from our institution, was divided into training (16,828 studies; 48,512 series; 112,028 images), validation (4746 studies; 16,612 series; 26,222 images) and test sets (6348 studies; 58,705 series; 3,314,018 images). Dataset B, obtained from a separate hospital, was used for out-of-domain external validation (1252 studies; 2150 series; 234,944 images). We developed an ensemble model combining a 2D convolutional neural network with a custom multi-task learning architecture and random forest classifier trained on DICOM metadata to classify sequence and orientation by series.

RESULTS: The neural network, random forest, and ensemble achieved 95%, 97%, and 98% overall sequence accuracy on dataset A, and 98%, 99%, and 99% accuracy on dataset B, respectively. All models achieved > 99% orientation accuracy on both datasets.

CONCLUSION: The ensemble model for series identification accommodates the complexity of brain MRI studies in state-of-the-art clinical practice. Expanding on previous work demonstrating proof-of-concept, our approach is more comprehensive with greater sequence diversity and orientation classification.

来源:Neuroradiology,查看原文。版权归原作者所有。

引用

  1. Kasmanoff, Lee, Razavian, et al. Deep multi-task learning and random forest for series classification by pulse sequence type and orientation. Neuroradiology. 2022. PMID: 35906437. doi:10.1007/s00234-022-03023-7

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。