Using Artificial Intelligence to Examine Biopsied Tissue Samples

University of Los Angeles (UCLA) engineers developed a method to improve diagnostic tools that examine biopsied tissue samples using artificial intelligence. The AI system uses virtual re-staining of tissue images, which is faster and as accurate as human-performed special stains.

Under a microscope, pathologists examine the tissue samples from biopsies that have been stained with special dyes to enhance the color and contrast. Hematoxylin and eosin (H&E) are the most used stains. However, often in clinical cases, additional special stains are necessary to increase contrast and color to different tissue components, allowing pathologists to get a clearer diagnostic picture.

While the special stains provide a better diagnostic picture, they often require much longer tissue preparations, increased monitoring, and a more expensive price tag. To speed up the process, UCLA researchers created a computation technique using artificial intelligence to transform images of tissue previously stained with H&E into new ones with added special stains.

According to the researchers, this process takes less than one minute per tissue sample compared to the several hours when performed by human experts. The system’s efficiency allows for faster preliminary diagnoses, leading to quicker development of treatment options.

“We developed a deep learning-based technique that eliminates the need for special stains to be performed by histotechnologists,” research lead Aydogan Ozcan said in a press release.

“The enhanced speed and accuracy are particularly important when diagnosing medical conditions such as organ transplant rejection cases, where a fast and accurate diagnosis enables rapid treatment, which may lead to greatly improved clinical outcomes.” 

Ozcan and the team demonstrated the AI-based technique by generating a full panel of special stains used for kidney tissue. By using specialized deep neural networks trained on images of H&E-stained tissue biopsies, the research team virtually generated the special stains on several clinical samples, covering a broad range of kidney diseases.

“A multi-institution team of board-certified renal pathologists then performed a clinical evaluation to ascertain the efficacy of the virtual, stain-to-stain transformation technique. They found a statistically significant improvement in the diagnoses achieved by using the virtually generated special stains over the use of only the H&E-stained images of biopsies,” the press release stated.

Additionally, another study indicated that the quality of the virtually re-stained images is statistically equivalent to those produced with special stains by human experts.

According to the researcher team, this method would be easily adoptable since the technique is applied to already existing H&E-stained images. The researcher was supported by the National Science Foundations’ Biophotonics Program.