Multi-view Attention for gestational age at birth prediction
This work addresses a domain-specific problem in clinical neuroimaging for predicting gestational age, presenting an incremental improvement with competitive results on a new benchmark.
The paper tackles gestational age at birth prediction using a multi-view shape analysis method that renders 3D brain features into 2D images, achieving a mean absolute error (MAE) of 1.637 ± 1.3 in Native space and 1.38 ± 1.14 in template space.
We present our method for gestational age at birth prediction for the SLCN (surface learning for clinical neuroimaging) challenge. Our method is based on a multi-view shape analysis technique that captures 2D renderings of a 3D object from different viewpoints. We render the brain features on the surface of the sphere and then the 2D images are analyzed via 2D CNNs and an attention layer for the regression task. The regression task achieves a MAE of 1.637 +- 1.3 on the Native space and MAE of 1.38 +- 1.14 on the template space. The source code for this project is available in our github repository https://github.com/MathieuLeclercq/SLCN_challenge_UNC