Producing a faster, more accurate, less invasive instrument for detecting cancer
Producing a faster, more accurate, less invasive instrument for detecting cancer lead image
Gastric cancer is the 4th leading cause of cancer-related deaths. While prevention is the primary method for decreasing the number of gastric cancer cases, there are significant factors limiting prevention, such as geographic and ethnic dependencies, and unavoidable gene mutations which can drive cancer growth. As a result, secondary prevention, which focuses on detection, characterization, and confirmation, is of utmost importance for reducing the high mortality rates associated with gastrointestinal cancers.
In recent years, there have been notable advancements in endoscopic diagnostics. Stanciu et al. discuss the field’s progress and where future research is needed.
The authors focus on three primary areas: biomimetic cameras with the potential to augment endoscopic screening by allowing faster, sharper, and more specific imaging; non-linear optical microscopy techniques that allow for in-vivo imaging approaches; and artificial intelligence methods for automated, high-precision, biomedical image analysis.
“Artificial intelligence methods are highly capable of automatically classifying collected data so that a diagnostic result can be provided on-the-fly,” said Stefan Stanciu. “Identifying synergies between novel and emerging imaging techniques and artificial intelligence represents a promising avenue to pursue in the quest for next-generation diagnostic tools.”
However, the authors acknowledge that there is a great, still-unexplored, potential in endoscopic imaging and gastrointestinal cancer diagnostics.
“We hope our work will encourage stakeholders to invest in the fabrication of ground-breaking endoscopes featuring capabilities for biomimetic endoscopic vision, in-vivo histology based on non-linear optical microscopies, and automated diagnostics produced from latest-hour artificial intelligence methods,” said Stanciu.
Source: “Toward next-generation endoscopes integrating biomimetic video systems, nonlinear optical microscopy, and deep learning,” by Stefan G. Stanciu, Karsten König, Young Min Song, Lior Wolf, Costas A. Charitidis, Paolo Bianchini, and Martin Goetz, Biophysics Reviews (2023). The article can be accessed at https://doi.org/10.1063/5.0133027 .
