'A net for everyone': fully personalized and unsupervised neural networks trained with longitudinal data from a single patient
This work addresses personalized medicine for glioblastoma patients by enabling unsupervised tumor monitoring without manual annotations, though it is incremental as it adapts existing GAN methods to a specific medical application.
The researchers tackled the problem of detecting tumor progression in glioblastoma patients by training personalized neural networks using only two longitudinal MRI scans per patient, achieving an AUC of 0.87 for tumor change detection and 66% accuracy with modified RANO criteria.
With the rise in importance of personalized medicine, we trained personalized neural networks to detect tumor progression in longitudinal datasets. The model was evaluated on two datasets with a total of 64 scans from 32 patients diagnosed with glioblastoma multiforme (GBM). Contrast-enhanced T1w sequences of brain magnetic resonance imaging (MRI) images were used in this study. For each patient, we trained their own neural network using just two images from different timepoints. Our approach uses a Wasserstein-GAN (generative adversarial network), an unsupervised network architecture, to map the differences between the two images. Using this map, the change in tumor volume can be evaluated. Due to the combination of data augmentation and the network architecture, co-registration of the two images is not needed. Furthermore, we do not rely on any additional training data, (manual) annotations or pre-training neural networks. The model received an AUC-score of 0.87 for tumor change. We also introduced a modified RANO criteria, for which an accuracy of 66% can be achieved. We show that using data from just one patient can be used to train deep neural networks to monitor tumor change.