期刊
EGYPTIAN JOURNAL OF RADIOLOGY AND NUCLEAR MEDICINE
卷 52, 期 1, 页码 -出版社
SPRINGER
DOI: 10.1186/s43055-021-00499-w
关键词
Computer-assisted diagnosis [E01.158]; Radiography [E01.370.350.700]; Neural networks [G17.485]; Machine learning [G17.035.250.500]; Cloud computing [L01.224.097]; Deep learning [G17.035.250.500.250]
This study demonstrates the feasibility of using a general purpose automated machine learning platform to train a CNN for classifying chest radiographs, although the accuracy achieved is slightly lower than a traditionally developed neural network model.
Background Widespread implementation of machine learning models in diagnostic imaging is restricted by dearth of expertise and resources. General purpose automated machine learning offers a possible solution. This study aims to provide a proof of concept that a general purpose automated machine learning platform can be utilized to train a CNN to classify chest radiographs. In a retrospective study, more than 2000 postero-anterior chest radiographs were assessed for quality, contrast, position, and pathology. A selected dataset of 637 radiographs were used to train a CNN using reinforcement learning based automated machine learning platform. Accuracy metrics of each label was calculated and model performance was compared to previous studies. Results The auPRC (area under precision-recall curve) was 0.616. The model achieved precision of 70.8% and recall of 60.7% (P > 0.05) for detection of Normal radiographs. Detection of Pathology by the model had a precision of 75.6% and recall of 75.6% (P > 0.05). The F1 scores were 0.65 and 0.75 respectively. Conclusion Automated machine learning platforms may provide viable alternatives to developing custom CNN models for classification of chest radiographs. However, the accuracy achieved is lower than a comparable traditionally developed neural network model.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据