A deep learning method for multi-task intelligent detection of oral cancer based on optical fiber Raman spectroscopy

Abstract

In the fight against oral cancer, innovative methods like Raman spectroscopy and deep learning have become powerful tools, particularly in integral tasks encompassing tumor staging, lymph node staging, and histological grading. These aspects are essential for the development of effective treatment strategies and prognostic assessment. However, it is important to note that most research so far has focused on solutions to one of these problems and has not taken full advantage of the potential wealth of information in the data. To compensate for this shortfall, we conceived a method that combines Raman spectroscopy with deep learning for simultaneous processing of multiple classification tasks, including tumor staging, lymph node staging, and histological grading. To achieve this innovative approach, we collected 1750 Raman spectra from 70 tissue samples, including normal and cancerous tissue samples from 35 patients with oral cancer. In addition, we used a deep neural network architecture to design four distinct multi-task network (MTN) models for intelligent oral cancer diagnosis, named MTN-Alexnet, MTN-Googlenet, MTN-Resnet50, and MTN-Transformer. To determine their effectiveness, we compared these multitask models to each other and to single-task models and traditional machine learning methods. The preliminary experimental results show that our multi-task network model has good performance, among which MTN-Transformer performs best. Specifically, MTN-Transformer has an accuracy of 81.5%, a precision of 82.1%, a sensitivity of 80.2%, and an F1_score of 81.1% in terms of tumor staging. In the field of lymph node staging, the accuracy, precision, sensitivity, and F1_score of MTN-Transformer are 81.3%, 83.0%, 80.1%, and 81.5% respectively. Similarly, for the histological grading classification tasks, the accuracy was 83.0%, the precision 84.3%, the sensitivity 76.7%, and the F1_score 80.2%. This code is available at https://github.com/ISCLab-Bistu/MultiTask-OralRamanSystem.