Erik Hallström

This paper develops a vision transformer model for rapid bacterial species identification from time-lapse images without fluorescent labels, achieving high accuracy on clinical isolates.

This study uses microfluidics, time-lapse microscopy, and deep learning to rapidly identify seven bacterial species with high accuracy in one hour.

This paper develops a method to rapidly detect bacteria in blood using smart centrifugation, microfluidic trapping, and deep learning for sepsis diagnostics.

The paper uses deep learning to classify bacteria species from phase-contrast microscopy images without staining or fixation, achieving over 98% accuracy.

The paper generates fluorescent labels from bright-field images using deep learning to enable virtual staining of adipocyte cells, improving feature extraction for downstream analysis.