Abedi Masoud, Shekarchizadeh Navid, Bazin Pierre-Louis, Scherf Nico, Lier Julia, Bergner Christa-Caroline, Köhler Wolfgang, Kirsten Toralf
Faculty Applied Computer and Bio Sciences, Mittweida University of Applied Sciences, 09648 Mittweida, Germany.
Department for Medical Data Science, Leipzig University Medical Center, 04103 Leipzig, Germany.
Gigascience. 2025 Jan 6;14. doi: 10.1093/gigascience/giaf092.
Magnetic resonance imaging (MRI) is commonly used for analyzing white matter abnormalities in the human brain. Integrating machine learning into MRI analysis can enhance diagnostic processes. However, the application of such techniques for white matter analysis in clinical practice is often limited when MRI data are multi-scanner (i.e., heterogeneous), particularly in scenarios with limited data, as seen in rare diseases. Therefore, it is crucial to develop methods that are highly independent of the MRI scanner and acquisition protocol.
This study introduces HeteroMRI, a deep learning method for classifying MRIs based on white matter abnormalities. Most importantly, HeteroMRI mitigates the effects of data heterogeneity on classification performance. Herein, HeteroMRI is employed to detect brain MRIs with white matter abnormalities. This method utilizes intensity clustering of the white matter tissue to reduce the effects of the heterogeneity of MRIs. MRI data from 11 public datasets with 40 MRI protocols are included. By using 200 MRIs for training the model, the binary classifier achieves an average accuracy of 93% ± 4%. Furthermore, the method is evaluated in limited data scenarios, simulating conditions of rare diseases. By reducing the data by 64% and 75%, the model's accuracy has a 4% and 12% decrease, respectively.
The presented method opens new avenues for white matter abnormality-related classification of heterogeneous MRI data without additional machine learning methods to reduce MRI heterogeneity. This classification approach demonstrates a high degree of independence from the MRI scanner and protocol, while also proving to be relatively generalizable to unseen MRI protocols.
磁共振成像（MRI）常用于分析人脑白质异常。将机器学习集成到MRI分析中可增强诊断过程。然而，当MRI数据来自多台扫描仪（即异质性）时，尤其是在数据有限的情况下，如罕见疾病中所见，此类技术在临床实践中用于白质分析的应用往往受到限制。因此，开发高度独立于MRI扫描仪和采集协议的方法至关重要。
本研究引入了HeteroMRI，一种基于白质异常对MRI进行分类的深度学习方法。最重要的是，HeteroMRI减轻了数据异质性对分类性能的影响。在此，HeteroMRI用于检测有白质异常的脑部MRI。该方法利用白质组织的强度聚类来减少MRI异质性的影响。纳入了来自11个公共数据集、具有40种MRI协议的MRI数据。通过使用200幅MRI图像训练模型，二元分类器的平均准确率达到93%±4%。此外，该方法在有限数据场景中进行评估，模拟罕见疾病的情况。通过将数据减少64%和75%，模型的准确率分别下降了4%和12%。
所提出的方法为异质性MRI数据的白质异常相关分类开辟了新途径，无需额外的机器学习方法来减少MRI异质性。这种分类方法显示出高度独立于MRI扫描仪和协议，同时也证明对未见的MRI协议具有相对的通用性。
