Related Experiment Video
Updated: Jun 29, 2025
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
Published on: January 7, 2019
Automated Classification of Body MRI Sequence Type Using Convolutional Neural Networks
Kimberly Helm1, Tejas Sudharshan Mathai1, Boah Kim1
1Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA.
Abstract:
Multi-parametric MRI of the body is routinely acquired for the identification of abnormalities and diagnosis of diseases. However, a standard naming convention for the MRI protocols and associated sequences does not exist due to wide variations in imaging practice at institutions and myriad MRI scanners from various manufacturers being used for imaging. The intensity distributions of MRI sequences differ widely as a result, and there also exists information conflicts related to the sequence type in the DICOM headers. At present, clinician oversight is necessary to ensure that the correct sequence is being read and used for diagnosis. This poses a challenge when specific series need to be considered for building a cohort for a large clinical study or for developing AI algorithms. In order to reduce clinician oversight and ensure the validity of the DICOM headers, we propose an automated method to classify the 3D MRI sequence acquired at the levels of the chest, abdomen, and pelvis. In our pilot work, our 3D DenseNet-121 model achieved an F1 score of 99.5% at differentiating 5 common MRI sequences obtained by three Siemens scanners (Aera, Verio, Biograph mMR). To the best of our knowledge, we are the first to develop an automated method for the 3D classification of MRI sequences in the chest, abdomen, and pelvis, and our work has outperformed the previous state-of-the-art MRI series classifiers.
Insights
This study introduces an automated method to classify 3D Magnetic Resonance Imaging (MRI) sequences in the chest, abdomen, and pelvis. Our AI model accurately identifies MRI sequences, reducing the need for manual review in clinical studies and AI development.
Area of Science:
- Radiology and Medical Imaging
- Artificial Intelligence in Healthcare
- Medical Informatics
Background:
- Multi-parametric MRI is crucial for disease diagnosis, but lacks standardized naming conventions for protocols and sequences.
- Variations in imaging practices and MRI scanner manufacturers lead to differing intensity distributions and conflicting DICOM header information.
- Current reliance on clinician oversight for accurate sequence identification hinders large-scale clinical studies and AI algorithm development.
Approach:
- Developed an automated 3D DenseNet-121 model for classifying MRI sequences in the chest, abdomen, and pelvis.
- The model was trained and validated on data from three Siemens MRI scanners.
- Evaluated the model's performance in differentiating five common MRI sequences.
Key Points:
- Achieved a 99.5% F1 score in differentiating common MRI sequences.
- Demonstrated the model's effectiveness across different Siemens scanner models.
- Established a novel automated method for 3D MRI sequence classification.
Conclusions:
- The proposed automated method significantly reduces the need for manual clinician oversight in MRI sequence identification.
- This approach ensures the validity of DICOM headers, crucial for clinical research and AI applications.
- Outperformed previous state-of-the-art methods for MRI series classification.
