UniCAD: Efficient and Extendable Architecture for Multi-Task Computer-Aided Diagnosis System

TL;DR

UniCAD presents an efficient, extendable multi-task CAD architecture leveraging pre-trained vision models with minimal task-specific parameters, enabling versatile medical image analysis and fostering open-source collaboration.

Contribution

The paper introduces UniCAD, a unified, modular CAD system that uses low-rank adaptation and plug-and-play experts for efficient multi-task medical imaging.

Findings

Outperforms existing methods in accuracy across 12 datasets.

Requires only 0.17% trainable parameters for adaptation.

Supports both 2D and 3D medical images efficiently.

Abstract

The growing complexity and scale of visual model pre-training have made developing and deploying multi-task computer-aided diagnosis (CAD) systems increasingly challenging and resource-intensive. Furthermore, the medical imaging community lacks an open-source CAD platform to enable the rapid creation of efficient and extendable diagnostic models. To address these issues, we propose UniCAD, a unified architecture that leverages the robust capabilities of pre-trained vision foundation models to seamlessly handle both 2D and 3D medical images while requiring only minimal task-specific parameters. UniCAD introduces two key innovations: (1) Efficiency: A low-rank adaptation strategy is employed to adapt a pre-trained visual model to the medical image domain, achieving performance on par with fully fine-tuned counterparts while introducing only 0.17% trainable parameters. (2) Plug-and-Play: A modular architecture that combines a frozen foundation model with multiple plug-and-play experts, enabling diverse tasks and seamless functionality expansion. Building on this unified CAD architecture, we establish an open-source platform where researchers can share and access lightweight CAD experts, fostering a more equitable and efficient research ecosystem. Comprehensive experiments across 12 diverse medical datasets demonstrate that UniCAD consistently outperforms existing methods in both accuracy and deployment efficiency. The source code and project page are available at https://mii-laboratory.github.io/UniCAD/.