Feasibility Study of the Prediction of Radiologist’s Instructions with the Bi-LSTM Model Trained with Descriptions of MR Imaging Order-statement

• Published in: Japanese Journal of Radiological Technology Vol. 79; no. 6; pp. 565 - 576
• Main Authors: Shimizu, Kozo, Tachiiri, Tetsuya, Yamatani, Yuya, Mai, Yoshimasa, Marugami, Nagaaki
• Format: Journal Article
• Language: Japanese
• Published: Japan Japanese Society of Radiological Technology 20.06.2023; Japan Science and Technology Agency
• Subjects: classification; Feasibility studies; Language; machine learning; Magnetic resonance imaging; Medical imaging; MRI protocol; Natural language processing; Optimization; prediction; Predictions; Quality assurance; Recall; prediction; natural language processing; classification; machine learning; MRI protocol
• ISSN: 0369-4305; 1881-4883
• DOI: 10.6009/jjrt.2023-1328

Purpose: Magnetic resonance (MR) images provide essential diagnostic information; however, it is also a very burdensome examination for patients. At our hospital, radiologists make imaging instructions for all MR examination orders, but this is a time-consuming task. If a natural language processing model can predict the imaging instructions, it will be possible to reduce the burden on radiologists and the instruction quality can be assured. The purpose of this study was to investigate the feasibility of using natural language processing to predict MR imaging instructions with the aim of assisting radiologists. Methods: Considering the uniqueness of the MR imaging protocols at each facility and the particularity of the test order text, we considered that the use of large datasets and pre-training models would be unsuitable. We focused on LSTM, which has been used for natural language processing, and built a 4-layer bi-LSTM model in combination with our own morphological preprocessing to predict MR imaging instructions. Results: The proposed method achieved macro-average precision, recall, and F1-score of 70.6%, 69.5%, and 68.9%, respectively. Compared to the previous studies, the proposed method achieved satisfactory performance in the natural language analysis task for Japanese. It is considered that the proposed method improved the prediction accuracy of the minority class through direct and indirect effects of vocabulary reduction, optimization, and similarity learning. Conclusion: It is suggested that the proposed method is effective and that the prediction of MR imaging instructions using natural language analysis in combination with the proposed method is feasible.