LED-Based Imaging System Could Transform Cancer Detection in Endoscopy

Gastrointestinal cancers remain one of the most common and challenging forms of cancer to diagnose accurately. Despite the widespread use of endoscopy for screening and diagnosis, the procedure still misses approximately 8 to 11 percent of tumors due to visibility limitations. The current method uses broad color channels in endoscopic imaging, which often fails to detect subtle biochemical changes in cancerous tissue. To address this diagnostic gap, researchers have developed an innovative imaging system that could significantly improve the detection of cancerous tissue during endoscopic procedures by using hyperspectral imaging technology combined with light-emitting diodes (LEDs).

The prototype system created by researchers from the University of Texas at Dallas (Dallas, TX, USA) utilizes an array of 18 LEDs emitting light at different wavelengths ranging from 405 nanometers to 910 nanometers. The system employs a monochrome camera to capture images of tissue as each LED illuminates the target sequentially, generating a complete hyperspectral dataset. This hyperspectral imaging approach captures data across narrow wavelength bands, including light beyond the visible spectrum, which allows for the detection of biochemical changes in cancerous tissue. The system is designed to improve the ability to visualize cancerous tissue during endoscopy by providing more detailed information compared to conventional methods.

The LED-based hyperspectral imaging system was tested on both normal and cancerous tissue samples removed during surgery. The prototype successfully captured hyperspectral signatures from various tissue types, and the results were comparable to those obtained from a reference hyperspectral camera system. The system demonstrated an imaging rate of over 10 hyperspectral datasets per second, nearing the real-time speeds required for practical endoscopic use. The findings, published in the Journal of Medical Imaging, suggest that this LED-based hyperspectral imaging system has the potential to reduce the number of missed tumors and enable faster, more accurate diagnoses. The researchers plan to further develop the system to make it ready for clinical applications.

“Our research shows the feasibility of employing a spectral LED array as the illumination source for high-speed and high-quality hyperspectral imaging,” said Naeeme Modir, PhD candidate at the University of Texas at Dallas and first author. “Our findings suggest that LED-based systems could open new possibilities for hyperspectral imaging applications.”