학술논문
Predicting slot lengths of MRI exams to decrease observed discrepancies between planning and execution.
Document Type
Academic Journal
Author
Wang X; Philips Research Europe, Philips GmbH Innovative Technologies, Röntgenstraße 24-26, Hamburg 22335, Germany. Electronic address: xinyu.wang@philips.com.; Aski SN; Department of Diagnostic Medical Physics, Karolinska University Hospital Solna, Stockholm, Sweden.; Uhlemann F; Philips Research Europe, Philips GmbH Innovative Technologies, Röntgenstraße 24-26, Hamburg 22335, Germany.; Gupta V; Philips Innovation & Strategy, Stockholm, Sweden.; Amthor T; Philips Research Europe, Philips GmbH Innovative Technologies, Röntgenstraße 24-26, Hamburg 22335, Germany.
Source
Publisher: Mosby Country of Publication: United States NLM ID: 7607123 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1535-6302 (Electronic) Linking ISSN: 03630188 NLM ISO Abbreviation: Curr Probl Diagn Radiol Subsets: MEDLINE
Subject
Language
English
Abstract
This retrospective study aimed to reveal discrepancies between planned (T plan ) and actual (T act ) slot lengths of abdomen MRI exams, and to improve T plan by predicting slot lengths via a machine learning algorithm. T plan and T act were retrieved from RIS and modality logfiles, respectively, covering 3038 MRI exams of 17 protocols performed at an abdomen department. Comparisons showed that 30% of exams exceeded planned slot lengths. On the other hand, exams completed within planning failed to manifest good adherence to schedule, as many of them were assigned with an unnecessarily long slot. While adjusting the planned exam duration by a fixed amount of time for each protocol could move T plan closer to the mean or median T act , the large spread of T act would still be unaffected. This is why this study goes one step further, introducing a method to predict the required slot length not only per protocol, but for each individual exam. A Random Forest Regression model was trained on historic data to predict individual slot lengths (T pred ) based on patient and exam context. The correlation between T pred and T act was found to be better than that of T plan and T act , with Pearson correlation factors of 0.66 and 0.50, respectively. The overall adherence to schedule was also improved by the prediction, as seen by a reduction of both the root mean squared error (-28%) and the standard deviation (-16%) of the differences between planned/predicted slot times and T act . To provide further insights into the discrepancies between planning and execution of MRI exams, nineteen exams from the Liver protocol with verified clinical information were selected. This case study showed that patient conditions, diagnostic purposes and the selection of sequences during exams could explain some variations of exam durations, but the potential for improving the exam time prediction by including this additional context is limited.
Competing Interests: Declaration of competing interest Xinyu Wang, Falk Uhlemann, Vikas Gupta, and Thomas Amthor are employees of Philips.
(Copyright © 2024 Elsevier Inc. All rights reserved.)
Competing Interests: Declaration of competing interest Xinyu Wang, Falk Uhlemann, Vikas Gupta, and Thomas Amthor are employees of Philips.
(Copyright © 2024 Elsevier Inc. All rights reserved.)