New Imaging Technology Developed By UCLA Research Team May Reduce Need For Skin Biopsies

Instead of surgically taking a skin sample, sending it to a lab, and waiting several days for the results, your dermatologist takes photos of a suspicious-looking lesion and quickly produces a detailed microscopic image of the skin.

This could become routine in clinics, the result of a new “virtual histology” technology developed by researchers at UCLA Samueli School of Engineering and UCLA’s David Geffen School of Medicine, according to today’s article in Light: Science & Applications, a journal of the Springer Nature Group. Histology is the study of the microscopic structure of tissue.

Aydogan Ozcan

“This process bypasses several standard steps commonly used for diagnosis, including skin biopsy, tissue fixation, processing, sectioning and histochemical staining. The images look like biopsied and histochemically stained sections of skin imaged on microscope slides, ”said lead author of the study, Aydogan Ozcan, Professor to the Chancellor and Volgenau Chair for Engineering Innovation in the Department of Electrical and Computer Engineering at UCLA Samueli.

The technology, which has been in research and development for more than three years, could offer a new avenue for the rapid diagnosis of malignant skin tumors, reducing the number of unnecessary invasive skin biopsies and allowing earlier diagnosis of skin cancer. . Previously, this technology was only applied to microscopy slides containing unstained tissue, acquired by biopsy. This report is the first to apply virtual histology to intact, non-biopsied tissue.

Philippe Sumpia
Philippe Sumpia

“The current standard for the diagnosis of skin diseases, including skin cancer, is based on invasive biopsy and histopathological evaluation. For patients, this often leads to unnecessary biopsies and scarring as well as multiple visits to the doctor. It can also be costly for patients and the healthcare system, ”said Dr Philip Scumpia, Assistant Professor of Dermatology and Dermatopathology at the David Geffen School of Medicine at UCLA and West Los Angeles Veterans Affairs Hospital and Member of the UCLA Jonsson Comprehensive Cancer Center. “Our approach potentially offers a biopsy-free solution, providing images of skin structure with resolution at the cellular level.”

The research team, led by Ozcan, Scumpia and Dr. Gennady Rubinstein, a dermatologist at the Dermatology & Laser Center in Los Angeles, created a deep learning framework to transform images of intact skin acquired through non-invasive optical technology. emerging, confocal reflectance microscopy. (RCM), in a friendly format for dermatologists and pathologists. Analysis of RCM images requires special training because they are black and white and, unlike standard histology, they lack nuclear characteristics of cells.

“I was surprised at how easy it is for this virtual staining technology to transform the images into the ones I typically see from skin biopsies processed using traditional chemical fixation and tissue staining with the aid of traditional chemical fixation. microscope, ”Sumpia said.

The researchers formed a “convolutional neural network” to quickly transform RCM images of unstained skin into virtually stained 3D images like the H&E (hematoxylin and eosin) images familiar to dermatologists and dermatopathologists. Deep learning, a form of machine learning, builds artificial neural networks that, like the human brain, can “learn” from large amounts of data.

“This framework can perform virtual histology on a variety of skin conditions, including basal cell carcinoma. It also provides detailed 3D images of multiple layers of the skin, ”said Ozcan, who also has faculty positions at UCLA in bioengineering and surgery and is associate director of the California NanoSystems Institute. “In our studies, the virtually stained images showed color contrast and spatial characteristics similar to those of traditionally stained microscopic images of biopsied tissue. This approach can allow diagnosticians to see the overall histological features of intact skin without invasive skin biopsies or the tedious work of chemical processing and tissue labeling.

According to Rubinstein, this is an exciting proof-of-concept study. “The only tool currently used in clinics to help a dermatologist is the dermatoscope, which magnifies the skin and polarizes light. At best, they can help a dermatologist spot patterns, ”said Rubinstein, who also uses confocal reflectance microscopes in the clinic.

The authors said there are several steps to take to translate this technology for clinical use, but their goal is to provide virtual histology technology that can be integrated into any device – large, small, or combined with others. optical imaging systems. Once the neural network is “trained”, with numerous tissue samples and the use of powerful graphics processing units (GPUs), it will be able to run on a computer or a network, allowing rapid transformation of a standard image into an image. a virtual histological image.

Future studies will determine whether this digital biopsy-free approach can interface with whole body imaging and electronic medical records to usher in a new era of “digital dermatology” and change the way dermatology is practiced. Additionally, the research team will determine whether this artificial intelligence platform can work with other AI technologies to research patterns and further aid in clinical diagnosis.

Other authors of this work include Assistant Assistant Professor of Electrical and Computer Engineering Yair rivenson graduate engineering students from UCLA Samueli and Ozcan: Jingxi Li, Jason Garfinkel, Xiaoran Zhang, Di Wu, Yijie Zhang, Kevin de Haan, Hongda Wang, Tairan Liu, and Bijie Bai.

The research is funded by the National Science Foundation, Biophotonics Program (PI: Ozcan). Scumpia, in collaboration with Ozcan, received a VA Merit Award for further studying non-biopsy virtual histology in non-melanoma skin cancer in veterans.

About Perry Perrie

Check Also

Lunar water could come from Earth’s atmosphere

Not all of the moon’s water comes from its own surface; part of it is …