AutoMO-Mixer: An automated multi-objective Mixer model for balanced, safe and robust prediction in medicine

TL;DR

AutoMO-Mixer is a new AI model for medical image diagnosis that balances sensitivity and specificity while ensuring safety and robustness, demonstrated on OCT data.

Contribution

It introduces a unified multi-objective framework combining MLP-Mixer with evidential reasoning for safer and more balanced medical predictions.

Findings

AutoMO-Mixer outperforms existing models in safety and robustness.

The model achieves balanced sensitivity and specificity.

Experimental results validate improved performance on OCT data.

Abstract

Accurately identifying patient's status through medical images plays an important role in diagnosis and treatment. Artificial intelligence (AI), especially the deep learning, has achieved great success in many fields. However, more reliable AI model is needed in image guided diagnosis and therapy. To achieve this goal, developing a balanced, safe and robust model with a unified framework is desirable. In this study, a new unified model termed as automated multi-objective Mixer (AutoMO-Mixer) model was developed, which utilized a recent developed multiple layer perceptron Mixer (MLP-Mixer) as base. To build a balanced model, sensitivity and specificity were considered as the objective functions simultaneously in training stage. Meanwhile, a new evidential reasoning based on entropy was developed to achieve a safe and robust model in testing stage. The experiment on an optical coherence tomography dataset demonstrated that AutoMO-Mixer can obtain safer, more balanced, and robust results compared with MLP-Mixer and other available models.