SEMPAI: a Self-Enhancing Multi-Photon Artificial Intelligence for prior-informed assessment of muscle function and pathology

TL;DR

SEMPAI is a novel AI framework that combines hypothesis-driven priors with deep learning and meta-learning to analyze multiphoton microscopy images of muscle fibers, enabling interpretable, accurate predictions even with limited data.

Contribution

The paper introduces SEMPAI, a self-enhancing multi-photon AI that integrates priors into deep learning for muscle analysis, improving interpretability and performance on small datasets.

Findings

SEMPAI outperforms existing biomarkers in six of seven tasks.

Models with integrated priors outperform those without priors.

The method enables analysis of large, multi-study datasets for muscle pathology.

Abstract

Deep learning (DL) shows notable success in biomedical studies. However, most DL algorithms work as a black box, exclude biomedical experts, and need extensive data. We introduce the Self-Enhancing Multi-Photon Artificial Intelligence (SEMPAI), that integrates hypothesis-driven priors in a data-driven DL approach for research on multiphoton microscopy (MPM) of muscle fibers. SEMPAI utilizes meta-learning to optimize prior integration, data representation, and neural network architecture simultaneously. This allows hypothesis testing and provides interpretable feedback about the origin of biological information in MPM images. SEMPAI performs joint learning of several tasks to enable prediction for small datasets. The method is applied on an extensive multi-study dataset resulting in the largest joint analysis of pathologies and function for single muscle fibers. SEMPAI outperforms state-of-the-art biomarkers in six of seven predictive tasks, including those with scarce data. SEMPAI's DL models with integrated priors are superior to those without priors and to prior-only machine learning approaches.