Dual-Branch Efficient Net Architecture for ACL Tear Detection in Knee MRI
kota, T.; Garofalaki, K.; Whitely, F.; Evdokimenko, E.; Smartt, E.
Show abstract
We propose a deep learning approach for detecting anterior cruciate ligament (ACL) tears from knee MRI using a dual-branch convolutional architecture. The model independently processes sagittal and coronal MRI sequences using EfficientNet-B2 backbones with spatial attention modules, followed by a late fusion classifier for binary prediction. MRI volumes are standardized to a fixed number of slices, and domain-specific normalization and data augmentation are applied to enhance model robustness. Trained on a stratified 80/20 split of the MRNet dataset, our best model--using the Adam optimizer and a learning rate of 1e-4--achieved a validation AUC of 0.98 and a test AUC of 0.93. These results show strong predictive performance while maintaining computational efficiency. This work demonstrates that accurate diagnosis is achievable using only two anatomical planes and sets the stage for further improvements through architectural enhancements and broader data integration.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Necessity and Impact of Specialization of Large Foundation Model for Medical Segmentation Tasks 95%
- Phase Recognition in Contrast-Enhanced CT Scans based on Deep Learning and Random Sampling 94%
- Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography 93%
Similar papers in this journal
- MISPEL: A supervised deep learning harmonizationmethod for multi-scanner neuroimaging data 96%
- Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images 96%
- Triplanar ensemble U-Net model for white matter hyperintensities segmentation on MR images 96%
Similar papers in this journal
- Application of a convolutional neural network to the quality control of MRI defacing 97%
- Fusion of Electronic Health Records and Radiographic Images for a Multimodal Deep Learning Prediction Model of Atypical Femur Fractures 95%
- BenchXAI: Comprehensive Benchmarking of Post-hoc Explainable AI Methods on Multi-Modal Biomedical Data 92%
Similar papers in this journal
- Cross-modality image translation of 3 Tesla Magnetic Resonance Imaging to 7 Tesla using Generative Adversarial Networks 97%
- Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation 96%
- CEREBRUM-7T: Fast and Fully-volumetric Brain Segmentation of 7 Tesla MR Volumes 96%
Similar papers in this journal
- BrainQCNet: a Deep Learning attention-based model for the automated detection of artifacts in brain structural MRI scans. 97%
- EPISeg: Automated segmentation of the spinal cord on echo planar images using open-access multi-center data 97%
- FONDUE: Robust resolution-invariant denoising of MR Images using Nested UNets 96%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.