Biology subjects

Zigiotto, L.

Publications and source records attributed to Zigiotto, L..

3 recordsLinked to original sources

bioRxiv2025

Supervised white matter bundle segmentation in glioma patients with transfer learning

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

neuroscience↗

bioRxiv2023

Supervised White Matter Bundle Segmentation in Glioma Patients with Transfer Learning

In clinical neuroscience, the segmentation of the main white matter bundles is propaedeutic for many tasks such as preoperative neurosurgical planning and monitoring of neuro-related diseases. Automating bundle segmentation with data-driven approaches and deep learning models has shown promising accuracy in the context of healthy individuals. The lack of large clinical datasets is preventing the translation of these results to patients. Inference on patients data with models trained on healthy population is not effective because of domain shift. This study aims to carry out an empirical analysis to investigate how transfer learning might be beneficial to overcome these limitations. For our analysis, we consider a public dataset with hundreds of individuals and a clinical dataset of glioma patients. We focus our preliminary investigation on the corticospinal tract. The results show that transfer learning might be effective in partially overcoming the domain shift.

neuroscience↗

bioRxiv2020

Classifyber, a robust streamline-based linear classifier for white matter bundle segmentation

Virtual delineation of white matter bundles in the human brain is of paramount importance for multiple applications, such as pre-surgical planning and connectomics. A substantial body of literature is related to methods that automatically segment bundles from diffusion Magnetic Resonance Imaging (dMRI) data indirectly, by exploiting either the idea of connectivity between regions or the geometry of fiber paths obtained with tractography techniques, or, directly, through the information in volumetric data. Despite the remarkable improvement in automatic segmentation methods over the years, their segmentation quality is not yet satisfactory, especially when dealing with datasets with very diverse characteristics, such as different tracking methods, bundle sizes or data quality. In this work, we propose a novel, supervised streamline-based segmentation method, called Classifyber, which combines information from atlases, connectivity patterns, and the geometry of fiber paths into a simple linear model. With a wide range of experiments on multiple datasets that span from research to clinical domains, we show that Classifyber substantially improves the quality of segmentation as compared to other state-of-the-art methods and, more importantly, that it is robust across very diverse settings. We provide an implementation of the proposed method as open source code, as well as web service.

neuroscience↗