Project 97: Machine-Learning Based Raman Spectroscopy for the Early Diagnosis of Gastric Cancer

Contact Information:

Prof. Jian Ye

Project Description and Objectives：

Gastric cancer is one of the most commonly occurring malignant tumors and seriously threatens human health. Early diagnosis and treatment are globally recognized as the most effective approach to improving survival, and early diagnosis is particularly crucial. Diseases initiate from changes in tissue and intracellular structure and chemical composition. Raman spectroscopy is a non-invasive technique that can specifically detect the chemical and structural information of molecules. The signature Raman spectra of genomic DNA, nuclei, and tissue of normal gastric mucosa and gastric cancer has been proven to be different. This project aims to investigate the spectral difference between normal gastric tissue and cancers. It involves the usage of machine learning algorithms for the clustering or classification of Raman spectra that collected from cancer patients. The goal is to develop a model that can be used to determine tumor boundary, stages, and types with high accuracy and specificity. This work will facilitate the application of Raman spectroscopy in the early clinical diagnosis of gastric cancers.

Eligibility Requirements：

Background in biomedical nanomaterials and clinical diagnosis

Prerequisite of biomedical statistics, algorithms and software (Python, Matlab, etc.) for data analysis

Enthusiasm for advancing the in vivo diagnostics techniques

Main Tasks：

Developing and optimizing machine learning algorithms for Raman analysis

Practicing the early diagnostics of cancer tissues with high accuracy

Writing final reports.

Website:

Lab: http://www.yelab.sjtu.edu.cn/

School: https://bme.sjtu.edu.cn/