Transfer Learning by Asymmetric Image Weighting for Segmentation across Scanners
This work addresses the challenge of scanner variability in medical image segmentation, which is crucial for clinical applications, though it is incremental as it builds on existing transfer learning and similarity measure concepts.
The paper tackled the problem of performance deterioration in image segmentation when classifiers trained on one scanner are applied to images from different scanners, proposing a transfer learning classifier that uses asymmetric image weighting based on similarity measures and achieved excellent results across multiple brain tissue and white matter lesion segmentation datasets.
Supervised learning has been very successful for automatic segmentation of images from a single scanner. However, several papers report deteriorated performances when using classifiers trained on images from one scanner to segment images from other scanners. We propose a transfer learning classifier that adapts to differences between training and test images. This method uses a weighted ensemble of classifiers trained on individual images. The weight of each classifier is determined by the similarity between its training image and the test image. We examine three unsupervised similarity measures, which can be used in scenarios where no labeled data from a newly introduced scanner or scanning protocol is available. The measures are based on a divergence, a bag distance, and on estimating the labels with a clustering procedure. These measures are asymmetric. We study whether the asymmetry can improve classification. Out of the three similarity measures, the bag similarity measure is the most robust across different studies and achieves excellent results on four brain tissue segmentation datasets and three white matter lesion segmentation datasets, acquired at different centers and with different scanners and scanning protocols. We show that the asymmetry can indeed be informative, and that computing the similarity from the test image to the training images is more appropriate than the opposite direction.