Fig. 3: Live and dead classification results. | npj Biosensing

Fig. 3: Live and dead classification results.

From: Realtime bacteria detection and analysis in sterile liquid products using deep learning holographic imaging

Fig. 3

a A sample of experimentally derived synthetic hologram showing our deep learning model detects and classifies live and dead E. coli (EC), as well as the detections below our confidence threshold (unknown). The figure also includes in-focused hologram samples for live and dead bacteria showing distinct diffraction patterns between them. b Receiver operator characteristic (ROC) curves and corresponding area under curve (AUC) values of our deep learning model for live and dead EC with vertical dashed line marking 0.1% false positive rate (FPR). c The confusion matrix showing the accuracy and prediction errors of our classification for live and dead EC evaluated at 0.1% FPR.

Back to article page