Optimizing MRI sequence classification performance: insights from domain shift analysis.
Authors
Affiliations (11)
Affiliations (11)
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany.
- Department of Neuroradiology, Bonn University Hospital, Bonn, Germany.
- Division for Computational Radiology and Clinical AI, University Hospital Bonn, Bonn, Germany.
- Division for Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany.
- Hopp Children's Cancer Center (KiTZ), Heidelberg, Germany.
- Department of Neuropathology, Heidelberg University Hospital, Heidelberg, Germany.
- Clinical Cooperation Unit Neuropathology, German Cancer Research Center (DKFZ) and German Cancer Consortium (DKTK), Heidelberg, Germany.
- Division of Pediatric Neurooncology, German Cancer Research Center (DKFZ) and German Cancer Consortium (DKTK), Heidelberg, Germany.
- Division of Pediatric Glioma Research, German Cancer Research Center (DKFZ), Heidelberg, Germany.
- Department of Pediatric Oncology, Hematology & Immunology, Heidelberg University Hospital, Heidelberg, Germany.
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany. [email protected].
Abstract
MRI sequence classification becomes challenging in multicenter studies due to variability in imaging protocols, leading to unreliable metadata and requiring labor-intensive manual annotation. While numerous automated MRI sequence identification models are available, they frequently encounter the issue of domain shift, which detrimentally impacts their accuracy. This study addresses domain shift, particularly from adult to pediatric MRI data, by evaluating the effectiveness of pre-trained models under these conditions. This retrospective and multicentric study explored the efficiency of a pre-trained convolutional (ResNet) and CNN-Transformer hybrid model (MedViT) to handle domain shift. The study involved training ResNet-18 and MedVit models on an adult MRI dataset and testing them on a pediatric dataset, with expert domain knowledge adjustments applied to account for differences in sequence types. The MedViT model demonstrated superior performance compared to ResNet-18 and benchmark models, achieving an accuracy of 0.893 (95% CI 0.880-0.904). Expert domain knowledge adjustments further improved the MedViT model's accuracy to 0.905 (95% CI 0.893-0.916), showcasing its robustness in handling domain shift. Advanced neural network architectures like MedViT and expert domain knowledge on the target dataset significantly enhance the performance of MRI sequence classification models under domain shift conditions. By combining the strengths of CNNs and transformers, hybrid architectures offer enhanced robustness for reliable automated MRI sequence classification in diverse research and clinical settings. Question Domain shift between adult and pediatric MRI data limits deep learning model accuracy, requiring solutions for reliable sequence classification across diverse patient populations. Findings The MedViT model outperformed ResNet-18 in pediatric imaging; expert domain knowledge adjustment further improved accuracy, demonstrating robustness across diverse datasets. Clinical relevance This study enhances MRI sequence classification by leveraging advanced neural networks and expert domain knowledge to mitigate domain shift, boosting diagnostic precision and efficiency across diverse patient populations in multicenter environments.