Supervised white matter bundle segmentation in glioma patients with transfer learning

Abstract

In clinical settings, the virtual dissection of white matter tracts represents an informative source of information for monitoring neurological conditions or to support the planning of a treatment. The automation of this task using data-driven approaches, and in particular deep learning models, provides promising evidence of good accuracy when carried out on healthy individuals. However, the lack of large clinical datasets and the profound differences between healthy and clinical populations hinder the translation of these results to patients. Here, we investigated for the first time the effectiveness of transfer learning in adapting a deep learning architecture trained on a healthy population to glioma patients. Importantly, we provided the first thorough characterization of domain shift and its complexity, distinguishing systematic (i.e. measurement and pre-processing related) from tumor specific components. Our results suggest that (i) models trained on a large normative healthy population have a significant performance drop when the inference is carried out on patients; (ii) transfer learning can be an effective strategy to overcome the shortage of clinical data and to manage the systematic shift; (iii) fine tuning of the learning model cannot accommodate large white matter deformations induced by the tumor. The results were coherent across the five white matter bundles and three different input modalities tested, highlighting their robustness and generalizability. Our work provides valuable insights for advancing automated white matter segmentation in clinical populations and enhancing clinical transfer learning applications. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=72 SRC="FIGDIR/small/659452v1_ufig1.gif" ALT="Figure 1"> View larger version (16K): org.highwire.dtl.DTLVardef@1c2bbbcorg.highwire.dtl.DTLVardef@1b3555eorg.highwire.dtl.DTLVardef@a9bb4dorg.highwire.dtl.DTLVardef@147dc5e_HPS_FORMAT_FIGEXP M_FIG C_FIG HighlightsO_LIWhite matter bundle segmentation is essential for planning glioma tumor resection. C_LIO_LIWe trained a deep learning model on a healthy dataset to segment white matter bundles. C_LIO_LIWe observed a sub-optimal performance on glioma patients due to domain shift. C_LIO_LITransfer learning mitigated domain shift between healthy and clinical populations. C_LIO_LIWe highlighted domain shift domains solved/not solved by transfer learning. C_LI