Siamese LSTM-based fiber structural similarity network (FS2NET) for rotation invariant brain tractography segmentation
- Streamline classification usually requires registration of subject data to a common space.
- Contribution: The main goal of this work is to provide a rotationally invariant approach for streamline segmentation based on a set of reference streamlines.
- Learn the probability of two streamlines to belong to the same bundle.
- Recognise a streamline by assigning the label of the fiber with the highest similarity in a given set of reference fibers.
Assumption: Similarity between fibers is learned. This is supposed to generalise to
Therefore, applying data augmentation to the reference set is sufficient for achieving rotation invariance. (I.e. augmentation independent of the training stage.)
- stacked LSTMs to arrive at a 32-entry feature vector
“L1-distance” between feature vectors
Comment: Probably, the authors mean the difference vector.
- classification network: ‘similar’ vs ‘dissimilar’
Comparison to two of their own works: ANN and BrainSegNet
- Comment: Doubtful if this can be considered as ‘state of the art’.
- BS: 11, 1000 batches per epoch -> only 11K training samples. # epochs: not clear.
macro classification - Gray matter fibres vs White matter fibres
- probably: U-shaped or short fibres vs long range fibres (?)
micro classification - Labelling WM fibres into 8 subclasses
Recall - fraction of correct WM labels in macro classification
- 3 subjects, 250K streamlines each
- preprocessing: keep only 75% of streamline points with the highest curvature (per fibre)
- each streamline: max of 100 points (zero padded)
- FS2Net achieves top performance compared to ANN and BrainSegNet in all experiments.
- FS2Net shows better recall hinting at a better robustness towards data imbalance of GM and WM classes (macro).
- FS2Net is quite robust to rotations of testing streamlines.
- Very nice idea. However, for the real value of their approach for streamline segmentation the evaluation is of limited power.