Researchers have created a new microscope that can visualize relatively large pieces of cell-resolved tissue to help surgeons examine tumor margins within minutes from removal.

Removable tissue is typically sent to a hospital laboratory where specialists either freeze it or treat it with chemical agents until they make extremely thin slices to be mounted on a slide. This careful selection and mounting is a time-consuming procedure that involves advanced machinery and a bench of professionals.

"Current methods to prepare tissue for margin status evaluation during surgery have not changed significantly since first introduced over 100 years ago," said study co-author Ann Gillenwater, M.D., a professor of head and neck surgery at MD Anderson. "By bringing the ability to accurately assess margin status to more treatment sites, the DeepDOF has potential to improve outcomes for cancer patients treated with surgery."

Researchers at Rice University and the University of Texas MD Anderson Cancer Center developed the modern microscope which can easily view relatively thick tissue with cell-level resolution. It was developed by Rice engineers and Applied Physicists and was presented in a study published in the Proceedings of the National Academy of Science this week.

The microscope uses a cheap conventional optic lens for photographing entire tissues. The tool provides depths of field up to five times the existing state-of-the-art microscope. Using an AI technique dubbed "DeepDOF", the microscope software employs a deep learning network that can analyze vast volumes of data.

To train the dataset, Investigators showed 1,200 photographs from a database of histological (cell) slides to the system. The system would then capture and process photographs in less than two minutes.

"Traditionally, imaging equipment like cameras and microscopes are designed separately from imaging processing software and algorithms," said study co-lead author Yubo Tang, a postdoctoral research associate in the lab of co-corresponding author Rebecca Richards-Kortum. "DeepDOF is one of the first microscopes that's designed with the post-processing algorithm in mind."

According to the authors, data developed from the device provides a profound learning histopathology of intact specimens with comprehensive depth of field in real time. In the long term, the DeepDOF microscope may contribute considerably to the evaluation of intact biopsy specimens and surgical organisms, in particular for intra-operative assessment and in restricted tools.