Imaging Software Could Speed Breast Cancer Diagnosis

New software developed by Rice University bioengineers could speed up the diagnosis of breast cancer with 90 percent accuracy and without the need for a specialist.

Researchers said the software could improve breast cancer management, particularly in developing countries where pathologists are not routinely available.

“评估新鲜乳房组织的care could change the current practice of pathology,” said lead researcher Rebecca Richards-Kortum, Rice’s Malcolm Gillis University Professor and professor of bioengineering and of electrical and computer engineering. “We have developed a faster means to classify benign and malignant human breast tissues using fresh samples and thereby removing the need for time-consuming tissue preparation.”

Today, breast-cancer diagnosis is an intricate process. Tissue first must be obtained, typically by either a core needle biopsy or surgical excision. Next, pathologists must complete a complex process to prepare the tissue for analysis and histological assessment.

When examined under a microscope, cancerous and precancerous cells typically appear different from healthy cells. The study of cellular structures is known as histology, and a histological analysis is typically required for an accurate diagnosis of both the type and stage of a cancerous tumor.

The software developed in Richards-Kortum’s lab allows for an automated histological assessment of breast cancer from tissue samples without the need for complex tissue-sample preparation or assessment by a pathologist. The software uses high-speed optical microscopy of intact breast tissue specimens.

“We performed our analysis without tissue fixation, cutting and staining and achieved comparable classification with current methods,” Richards-Kortum said. “This cuts out the tissue-preparation process and allows for rapid diagnosis. It is also reliant on measurable criteria, which could reduce subjectivity in the evaluation of breast histology.”

The software uses images from a confocal fluorescence microscope to analyze freshly cut human breast tissue samples for certain histological parameters that are typically used in breast cancer diagnosis. The software uses the parameter data to classify the tissue in each image and make a determination whether the imaged tissue is benign or malignant.

Although the software could have substantial clinical relevance, Richards-Kortum said more research and refinement of the classification procedures are needed before the software can be used in a clinical setting.

Rice graduate student Jessica Dobbs, the study’s lead author, said, “We are excited about the possibility of using these imaging techniques to improve access to histologic diagnosis in developing regions that lack the human resources and equipment necessary to perform standard histologic assessment.”