Learning Full Spine Segmentations without Training Examples
Rhydian Windsor, Amir Jamaludin, Timor Kadir, Andrew Zisserman
Labelled full spine scans are very difficult to get (time consuming, requires clinical expertise)
However, lots of labelled lumbar (lower back) scans available
DPMs model an object as a set of parts constrained by a set of spatial arrangements
e.g. Person = 2 legs + 2 arms + face connected in a star shape
Popular approach in pose estimation
In our network, predict heatmaps for each corner of vertebrae + centroids
Get individual detections by thresholding and finding locally connected parts
Now we have part detections, next goal is to group into individual vertebrae
Vertebrae vary in size and angle so simply assigning parts to closest centroid gives poor grouping:
Instead, we predict a vector field for each corner.
At the point of detections the vector field must point to the centroid of the vertebrate
At test time we can perform groupings by getting part detections and observing the corresponding vector field value. We group the part to the centroid it points closest to
L1 loss for heatmaps, L2 loss for vector fields
Applying the detector directly to the full spine images does not work very well
This is likely due to resampling the full spine images to squares results in much smaller vertebrae.
To fix this, split full spine scans into smaller images and then perform detections on this image
This results in much better segmentations
Initialise with bounding box around S1 (blue box)
Apply for a fixed number of iterations (6 in lumbar scans, 23 for full spine scans)
Train on lumbar, apply to full spine scans
Similar to induction; we use nth case to show (n+1)th case
Use previous algorithm to find the S1 vertebrate.
During training time use vertebrae pairs next to each other as training examples
At test time, apply for 23 iterations up the spine
Training set: ~6000 lumbar MRI
Test set: ~400 (badly) labelled full spine MRI
Previous state of the art for lumbar scans 99.6% accuracy (Forsberg, 2017)
Little drop in accuracy as we move to full spine images