haruspex
A knee MRI model for the RSNA Knee Abnormality Detection challenge, flagging 12 findings from ligament and meniscus tears to effusion, contusion and fracture.
Machine Learning
Medical Imaging
Solo Competitor
Python, PyTorch, EfficientNet
The model reads 2.5D windows of three slices from the sagittal and coronal planes, plus axial where it helps. A learned plane embedding tells it which view it is looking at, and attention pooling for each finding picks out the slices that matter for that label.
One network rarely wins on every finding. I trained EfficientNet B0 at 224 pixels and B2 at 256, with and without axial input, used mirrored coronal and axial augmentation, and combined them in an equal-weight rank-average ensemble.
Final scores of 0.919 on the public leaderboard and 0.909 on the private leaderboard. Findings covered include the ACL, MCL and menisci, osteoarthritis, effusion, synovitis, Baker's cyst, bone contusion and fracture, each scored separately.

