首页|Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine Re ports Findings in Machine Learning (Raman fiberoptic probe for rapid diagnosis of gastric and esophageal tumors with machine learning analysis or similarity .. .)
Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine Re ports Findings in Machine Learning (Raman fiberoptic probe for rapid diagnosis of gastric and esophageal tumors with machine learning analysis or similarity .. .)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
New research on Machine Learning is th e subject of a report. According to news reporting out of Shanghai, People's Rep ublic of China, by NewsRx editors, research stated, "Gastric and esophageal canc ers, the predominant forms of upper gastrointestinal malignancies, contribute si gnificantly to global cancer mortality. Routine detection methods, including med ical imaging, endoscopic examination, and pathological biopsy, often suffer from drawbacks such as low sensitivity and laborious and complex procedures." Our news journalists obtained a quote from the research from the Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine, "Raman spectrosc opy is a non-invasive and label-free optical technique that provides highly sens itive biomolecular information to facilitate effective tumor identification. In this work, we report the use of fiber-optic Raman spectroscopy for the accurate and rapid diagnosis of gastric and esophageal cancers. Using a database of 14,00 0 spectra from 140 ex vivo tissue pieces of both tumor and normal tissue samples , we compare the random forest (RF) and our established Euclidean distance Raman spectroscopy (EDRS) model. The RF analysis achieves a sensitivity of 85.23% and an accuracy of 83.05% in diagnosing gastric tumors. The EDRS a lgorithm with improved diagnostic transparency further increases the sensitivity to 92.86% and accuracy to 89.29%. When these diagnos tic protocols are extended to esophageal tumors, the RF and EDRS models achieve accuracies of 71.27 % and 93.18%, respectively. Finall y, we demonstrate that fewer than 20 spectra are sufficient to achieve good Rama n diagnostic accuracy for both tumor tissues. This optimizes the balance between acquisition time and diagnostic performance. Our work, although conducted on ex vivo tissue models, offers valuable insights for in vivo in situ endoscopic Ram an diagnosis of gastric and esophageal cancer lesions in the future."
ShanghaiPeople's Republic of ChinaAsiaCyborgsDiagnostics and ScreeningEmerging TechnologiesHealth and Medici neMachine Learning
NETL
NSTL
