Dynamic-Contrast Digital Holography with Deep Learning for Cancer Chemotherapy Selection

2021 
Coherence-gated digital holography captures intracellular dynamics in living tumor biopsies through depth-resolved dynamic speckle and fluctuation spectroscopy. Changes in intracellular dynamics have specific Doppler signatures that depend on the applied cancer drugs and the sensitivity of the patient to treatment. A Twin Deep Network (TDN) identifies these signatures in the presence of strong sample-to-sample variance to predict patient response to therapy. Clinical trials of dynamic-contrast digital holography have provided phenotypic profiles for ovarian cancer, for HER2neg breast cancer, and for esophageal cancer. This work provides insight into the value of Deep Learning for advanced data analytics as the volume and variety of data from optics-based assays grows.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    4
    References
    0
    Citations
    NaN
    KQI
    []