End-to-End Deep Learning for Structural Brain Imaging: A Unified Framework

TL;DR

UniBrain is an innovative end-to-end deep learning framework that unifies multiple neuroimaging analysis steps, reducing annotation needs and improving accuracy and efficiency in brain image processing.

Contribution

It introduces a minimally supervised, integrated approach that jointly optimizes all key neuroimaging tasks within a single framework, surpassing traditional sequential methods.

Findings

Outperforms existing methods across multiple neuroimaging tasks.

Reduces annotation effort significantly compared to traditional workflows.

Enhances computational efficiency and accuracy in brain image analysis.

Abstract

Brain imaging analysis is fundamental in neuroscience, providing valuable insights into brain structure and function. Traditional workflows follow a sequential pipeline-brain extraction, registration, segmentation, parcellation, network generation, and classification-treating each step as an independent task. These methods rely heavily on task-specific training data and expert intervention to correct intermediate errors, making them particularly burdensome for high-dimensional neuroimaging data, where annotations and quality control are costly and time-consuming. We introduce UniBrain, a unified end-to-end framework that integrates all processing steps into a single optimization process, allowing tasks to interact and refine each other. Unlike traditional approaches that require extensive task-specific annotations, UniBrain operates with minimal supervision, leveraging only low-cost labels (i.e., classification and extraction) and a single labeled atlas. By jointly optimizing extraction, registration, segmentation, parcellation, network generation, and classification, UniBrain enhances both accuracy and computational efficiency while significantly reducing annotation effort. Experimental results demonstrate its superiority over existing methods across multiple tasks, offering a more scalable and reliable solution for neuroimaging analysis. Our code and data can be found at https://github.com/Anonymous7852/UniBrain