Classification of Multi-Parametric Body MRI Series Using Deep Learning

2024-08-23

IEEE journal of biomedical and health informatics

AI Summary

Inhomogeneous DICOM header annotations across multi-parametric body MRI (mpMRI) protocols—caused by vendor-specific conventions and human error—impede radiologist workflow efficiency. Method: We propose an end-to-end DenseNet-121–based image classification model for automatic, accurate identification of eight common clinical mpMRI sequences directly from raw DICOM images. Contribution/Results: This is the first systematic evaluation of ResNet, EfficientNet, and DenseNet generalizability across multi-institutional, multi-vendor mpMRI data. The model achieves an F1-score of 0.966 and accuracy of 0.972 (p < 0.05) on multi-center DICOM data; accuracy exceeds 0.95 with ≥729 training cases. It demonstrates strong out-of-distribution robustness, attaining accuracies of 0.872 on the DLDS and 0.810 on the CPTAC-UCEC external datasets—substantially improving sequence identification reliability and clinical deployability.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Security and Privacy: Data transparency and provenance

Abstract

Multi-parametric magnetic resonance imaging (mpMRI) exams have various series types acquired with different imaging protocols. The DICOM headers of these series often have incorrect information due to the sheer diversity of protocols and occasional technologist errors. To address this, we present a deep learning-based classification model to classify 8 different body mpMRI series types so that radiologists read the exams efficiently. Using mpMRI data from various institutions, multiple deep learning-based classifiers of ResNet, EfficientNet, and DenseNet are trained to classify 8 different MRI series, and their performance is compared. Then, the best-performing classifier is identified, and its classification capability under the setting of different training data quantities is studied. Also, the model is evaluated on the out-of-training-distribution datasets. Moreover, the model is trained using mpMRI exams obtained from different scanners in two training strategies, and its performance is tested. Experimental results show that the DenseNet-121 model achieves the highest F1-score and accuracy of 0.966 and 0.972 over the other classification models with p-value $< $ 0.05. The model shows greater than 0.95 accuracy when trained with over 729 studies of the training data, whose performance improves as the training data quantities grow larger. On the external data with the DLDS and CPTAC-UCEC datasets, the model yields 0.872 and 0.810 accuracy for each. These results indicate that in both the internal and external datasets, the DenseNet-121 model attains high accuracy for the task of classifying 8 body MRI series types.

Problem

• Classify 8 body MRI series types accurately
• Handle incorrect DICOM headers in mpMRI exams
• Evaluate model performance across diverse datasets

Innovation

• Deep learning classifies 8 body MRI series types
• DenseNet-121 achieves highest F1-score and accuracy
• Model tested on internal and external datasets