Fast multiphoton microscopic imaging joint image super-resolution for
automated Gleason grading of prostate cancers
Abstract
Gleason grading system is dependable for quantifying prostate cancer.
This paper introduces a fast multiphoton microscopic imaging method via
deep learning for automatic Gleason grading. Due to the contradiction
between multiphoton microscopy (MPM) imaging speed and quality, a deep
learning architecture (SwinIR) is used for image super-resolution to
address this issue. The quality of low-resolution image is improved,
which increased the acquisition speed from 7.55s per frame to 0.24s per
frame. A classification network (Swin transformer) was introduced for
automated Gleason grading. The classification accuracy and F1-score
achieved by training on high-resolution images are respectively 90.9%
and 90.9%. For training on super-resolution images, the classification
accuracy and F1-score are respectively 89.9% and 89.9%. It shows
super-resolution image can provide a comparable performance to
high-resolution image. Our results suggested MPM joint image
super-resolution and automatic classification methods holds the
potential to be a real-time clinical diagnostic tool for prostate cancer
diagnosis.