ASCHOPLEX encounters Dafne: a federated continuous learning project for the generalizability of the Choroid Plexus automatic segmentation

TL;DR

This paper introduces a federated incremental learning approach within the ASCHOPLEX toolbox, enhancing the generalizability of Choroid Plexus segmentation across diverse MRI datasets compared to traditional fine-tuning methods.

Contribution

It presents the first federated incremental learning framework for ChP segmentation, improving model robustness across heterogeneous imaging conditions.

Findings

Federated learning outperforms fine-tuning in diverse datasets

Model generalizability is significantly improved with federated approach

Stable performance across multiple MRI sequences and cohorts

Abstract

The Choroid Plexus (ChP) is a highly vascularized brain structure that plays a critical role in several physiological processes. ASCHOPLEX, a deep learning-based segmentation toolbox with an integrated fine-tuning stage, provides accurate ChP delineations on non-contrast-enhanced T1-weighted MRI scans; however, its performance is hindered by inter-dataset variability. This study introduces the first federated incremental learning approach for automated ChP segmentation from 3D T1-weighted brain MRI, by integrating an enhanced version of ASCHOPLEX within the Dafne (Deep Anatomical Federated Network) framework. A comparative evaluation is conducted to assess whether federated incremental learning through Dafne improves model generalizability across heterogeneous imaging conditions, relative to the conventional fine-tuning strategy employed by standalone ASCHOPLEX. The experimental cohort comprises 2,284 subjects, including individuals with Multiple Sclerosis as well as healthy controls, collected from five independent MRI datasets. Results indicate that the fine-tuning strategy provides high performance on homogeneous data (e.g., same MRI sequence, same cohort of subjects), but limited generalizability when the data variability is high (e.g., multiple MRI sequences, multiple and new cohorts of subjects). By contrast, the federated incremental learning variant of ASCHOPLEX constitutes a robust alternative consistently achieving higher generalizability and more stable performance across diverse acquisition settings.