Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 25;15(1):27044.
doi: 10.1038/s41598-025-11985-w.

Automated characterization of abdominal MRI exams using deep learning

Joonghyun Kim  1 , Allison Chae  2 , Jeffrey Duda  2 , Arijitt Borthakur  2   3 , Daniel J Rader  4   5 , James C Gee  2 , Charles E Kahn Jr  2   3 ; Penn Medicine BioBank; Walter R Witschey  2 , Hersh Sagreiya  6
Collaborators, Affiliations

Automated characterization of abdominal MRI exams using deep learning

Joonghyun Kim et al. Sci Rep. .

Abstract

Advances in magnetic resonance imaging (MRI) have revolutionized disease detection and treatment planning. However, the growing volume and complexity of MRI data-along with heterogeneity in imaging protocols, scanner technology, and labeling practices-creates a need for standardized tools to automatically identify and characterize key imaging attributes. Such tools are essential for large-scale, multi-institutional studies that rely on harmonized data to train robust machine learning models. In this study, we developed convolutional neural networks (CNNs) to automatically classify three core attributes of abdominal MRI: pulse sequence type, imaging orientation, and contrast enhancement status. Three distinct CNNs with similar backbone architectures were trained to classify single image slices into one of 12 pulse sequences, 4 orientations, or 2 contrast classes. The models achieved high classification accuracies of 99.51%, 99.87%, and 99.99% for pulse sequence, orientation, and contrast, respectively. We applied Grad-CAM to visualize image regions influencing pulse sequence predictions and highlight relevant anatomical features. To enhance performance, we implemented a majority voting approach to aggregate slice-level predictions, achieving 100% accuracy at the volume level for all tasks. External validation using the Duke Liver Dataset demonstrated strong generalizability; after adjusting for class label mismatch, volume-level accuracies exceeded 96.9% across all classification tasks.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Sample pulse sequence (A), orientation (B), and contrast (C) labeling of nine MRI image slices.
Fig. 2
Fig. 2
Convolutional neural network model architecture.
Fig. 3
Fig. 3
Representative MRCP images from the external validation dataset. (A) Excluded due to motion artifact and low image quality; (B) Excluded due to off-center anatomy; (C) Accepted image showing centered biliary system with diagnostic clarity.
Fig. 4
Fig. 4
Training and validation accuracy and loss curves across epochs for each classification task.
Fig. 5
Fig. 5
Confusion matrices for the slice-level classification of pulse sequence, orientation, and contrast.
Fig. 6
Fig. 6
Confusion matrices for the volume-level classification of pulse sequence, orientation, and contrast.
Fig. 7
Fig. 7
Sample Grad-CAM visualizations for pulse sequence classification. Top two rows: Correctly classified T1-weighted MRI slices. Bottom row: Misclassified Localizer image incorrectly predicted as T1.
Fig. 8
Fig. 8
Confusion matrices for the volume-level classification of pulse sequence, orientation, and contrast on the duke liver dataset.
See this image and copyright information in PMC

Update of

References

    1. Sim, A. J., Kaza, E., Singer, L. & Rosenberg, S. A. A review of the role of MRI in diagnosis and treatment of early stage lung cancer. Clin. Transl Radiat. Oncol.24, 16–22 (2020). - PMC - PubMed
    1. Sindhu, T. S., Kumaratharan, N. & Anandan, P. A review of magnetic resonance imaging and its clinical applications. In 2022 6th International Conference on Devices, Circuits and Systems (ICDCS) 38–42 (2022).
    1. Nitz, W. R. MR imaging: acronyms and clinical applications. Eur. Radiol.9, 979–997 (1999). - PubMed
    1. Chan, R. W., Lau, J. Y. C., Lam, W. W. & Lau, A. Z. Magnetic resonance imaging. Encycl. Biomed. Eng. 574–587 (2019).
    1. Plewes, D. B. & Kucharczyk, W. Physics of MRI: a primer. J. Magn. Reson. Imaging. 35, 1038–1054 (2012). - PubMed

MeSH terms

LinkOut - more resources