Improved inter-scanner MS lesion segmentation by adversarial training on longitudinal data
This work addresses variability in automated lesion segmentation for MS patients, which is crucial for treatment decisions, but it is incremental as it builds on existing methods to improve consistency.
The paper tackles the problem of inconsistent MS lesion segmentation across different MRI scanners by proposing an adversarial training model on longitudinal data, which reduces inter-scanner variability and outperforms an FDA-approved solution in test-retest evaluations.
The evaluation of white matter lesion progression is an important biomarker in the follow-up of MS patients and plays a crucial role when deciding the course of treatment. Current automated lesion segmentation algorithms are susceptible to variability in image characteristics related to MRI scanner or protocol differences. We propose a model that improves the consistency of MS lesion segmentations in inter-scanner studies. First, we train a CNN base model to approximate the performance of icobrain, an FDA-approved clinically available lesion segmentation software. A discriminator model is then trained to predict if two lesion segmentations are based on scans acquired using the same scanner type or not, achieving a 78% accuracy in this task. Finally, the base model and the discriminator are trained adversarially on multi-scanner longitudinal data to improve the inter-scanner consistency of the base model. The performance of the models is evaluated on an unseen dataset containing manual delineations. The inter-scanner variability is evaluated on test-retest data, where the adversarial network produces improved results over the base model and the FDA-approved solution.