基于语言模型的德国胸部放射学报告的标签
Alessandro Wollek1,2, Philip Haitzer1,2, Thomas Sedlmeyr1,2
1Munich Institute of Biomedical Engineering, Technical University of Munich, Garching near Munich, Germany.
RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin
|April 25, 2024
概括
这项研究引入了一种深度学习模型,用于从德国放射学报告中提取标签,优于基于规则的方法,并使用有限的手动数据实现有效的胸部X射线分类.
科学领域:
- 医疗信息学 医疗信息学
- 放射学中的人工智能
- 自然语言处理自然语言处理.
背景情况:
- 胸部放射学报告的准确标签对于训练诊断模型至关重要.
- 手动注释是耗时和昂贵的,需要自动化解决方案.
- 软弱的监督为提高标签提取效率提供了一个有希望的途径.
研究的目的:
- 为德国自由文本胸部放射学报告开发和评估基于深度学习的标签预测模型.
- 评估模型在提取CheXpert标签方面的性能及其在训练胸部X射线分类模型中的实用性.
- 为了比较手册注释,基于规则的标签和基于深度学习的标签的有效性,用于训练诊断模型.
主要方法:
- 德国BERT编码器被用于标签提取模型,对手动注释,基于规则的标签和它们的组合进行了培训.
- 使用F1分数来量化标签提取性能,用于提取提取,否定检测和不确定性检测.
- 胸部X射线分类模型 (DenseNet-121) 使用不同的标签来源进行训练,以评估它们对肺胸检测的影响.
主要成果:
- 深度学习标记器 (DL) 在手动标记数据上的所有标签提取任务 (提及,否定,不确定性) 中显著优于基于规则的标记器 (RB).
- 在较大的数据集 (DS 0) 上预训练的模型,并在较小的标记集 (DS 1) 上进行了微调,显示出更高的性能.
- 胸部X射线肺胸部分类在使用DL预测标签训练时获得了最高的性能 (AUC 0.939),超过RB标签 (AUC 0.858) 和与手册标签 (AUC 0.934) 密切匹配.
结论:
- 监督的薄弱,特别是基于规则的报告标签,提高了深度学习模型的标签性能.
- 拟议的基于深度学习的标签提取模型可以作为广泛的手动标签的有效替代品,需要最小的注释数据.
- 使用预测标签训练诊断模型的表现与使用手动注释数据的表现相当,突出显示了医疗成像中自动标签的潜力.
更多相关视频
07:53Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
1.4K
02:09Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
Published on: April 12, 2024
583
相关概念视频
01:13Radiological Investigation III: Pulmonary Angiogram and PET Scan
91
Radiological investigations are paramount in the diagnosis and management of various pulmonary diseases. Two essential investigations are the Pulmonary Angiogram and the Positron Emission Tomography (PET) Scan.
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
91
01:30Radiological Investigation II: MRI and Ventilation Perfusion Scan
117
Description
Magnetic Resonance Imaging (MRI) and Ventilation Perfusion Scans are two radiological investigations that offer detailed diagnostic images of the body, particularly lung structures.
MRI
MRI uses magnetic fields and radiofrequency signals to distinguish between normal and abnormal tissues. This technology provides a more detailed diagnostic image than CT scans, enabling it to characterize pulmonary nodules, stage bronchogenic carcinoma, and evaluate inflammatory activity in...
Magnetic Resonance Imaging (MRI) and Ventilation Perfusion Scans are two radiological investigations that offer detailed diagnostic images of the body, particularly lung structures.
MRI
MRI uses magnetic fields and radiofrequency signals to distinguish between normal and abnormal tissues. This technology provides a more detailed diagnostic image than CT scans, enabling it to characterize pulmonary nodules, stage bronchogenic carcinoma, and evaluate inflammatory activity in...
117
01:29Positron Emission Tomography
4.2K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
4.2K