# A probabilistic deep learning approach for choroid plexus segmentation in autism spectrum disorder

## TL;DR

This paper introduces a deep learning tool called ASCHOPLEX that can automatically segment the choroid plexus in MRI scans of individuals with autism, improving analysis of brain-immune interactions.

## Contribution

The novel contribution is a probabilistic deep learning approach for choroid plexus segmentation in ASD, with uncertainty quantification and generalizability across age groups.

## Key findings

- ASCHOPLEX generalized well to adult ASD participants and produced accurate segmentations.
- The probabilistic approach provided confidence metrics for assessing model reliability.
- Performance declined in children, indicating the need for age-specific fine-tuning.

## Abstract

The choroid plexus serves as the primary barrier between the brain’s blood and cerebrospinal fluid and mediates neuroimmune function. A subset of individuals with autism spectrum disorder (ASD) may exhibit morphological alterations of the choroid plexus. However, to power larger population analyses, an automated tool capable of accurately segmenting the choroid plexus based on magnetic resonance imaging (MRI) is needed. Automated Segmentation of CHOroid PLEXus (ASCHOPLEX) is a deep learning tool that enables finetuning using new, patient-specific, training data, allowing its usage across cohorts for which the model was not originally trained. We evaluated ASCHOPLEX’s generalizability to individuals with ASD by performing finetuning on a local dataset of ASD and control (CON) participants. To assess generalizability, we implemented a probabilistic version of the algorithm, which allowed us to quantify the uncertainty in choroid plexus segmentation and evaluate the model’s confidence. ASCHOPLEX generalized well to our local dataset, in which all participants were adults. To further assess its performance, we tested the algorithm on the Autism Brain Imaging Data Exchange (ABIDE) dataset, which includes data from children and adults. While ASCHOPLEX performed well in adults, its accuracy declined in children, suggesting limited generalizability to different age groups without additional finetuning. Our findings show that the incorporation of a probabilistic approach during finetuning can strengthen the use of this deep learning tool by providing confidence metrics which allow assessing model reliability. Overall, our findings demonstrate that ASCHOPLEX can generate accurate choroid plexus segmentations in previously unseen data.

The choroid plexus plays an important role in brain health and immunity and may be altered in autism spectrum disorder (ASD). To analyze large imaging datasets, a method to automatically delineate this structure is needed. We adapted an existing artificial intelligence tool, ASCHOPLEX, for use in individuals with ASD and made it probabilistic to probe the confidence of its automated segmentations. The results show that ASCHOPLEX can generate accurate choroid plexus segmentations in ASD.