Interpretable cancer cell detection with phonon microscopy using multi-task conditional neural networks for inter-batch calibration
This work addresses the batch effect issue in AI-based cancer diagnostics using phonon microscopy, offering a practical solution for improving accuracy and interpretability in medical imaging.
The paper tackled the batch effect problem in phonon microscopy for cancer cell detection by developing a multi-task conditional neural network that simultaneously calibrates inter-batch variations and classifies cells, achieving a balanced precision of 89.22% and enabling classification in 0.5 seconds.
Advances in artificial intelligence (AI) show great potential in revealing underlying information from phonon microscopy (high-frequency ultrasound) data to identify cancerous cells. However, this technology suffers from the 'batch effect' that comes from unavoidable technical variations between each experiment, creating confounding variables that the AI model may inadvertently learn. We therefore present a multi-task conditional neural network framework to simultaneously achieve inter-batch calibration, by removing confounding variables, and accurate cell classification of time-resolved phonon-derived signals. We validate our approach by training and validating on different experimental batches, achieving a balanced precision of 89.22% and an average cross-validated precision of 89.07% for classifying background, healthy and cancerous regions. Classification can be performed in 0.5 seconds with only simple prior batch information required for multiple batch corrections. Further, we extend our model to reconstruct denoised signals, enabling physical interpretation of salient features indicating disease state including sound velocity, sound attenuation and cell-adhesion to substrate.