Application of one-dimensional hierarchical network assisted screening for cervical cancer based on Raman spectroscopy combined with attention mechanism
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Early cervical cancer detection is crucial. Raman spectroscopy combined with an attention-based convolutional neural network accurately classifies seven cervical tissue types, improving diagnostic performance for early screening.
Area Of Science
- Biomedical Optics
- Oncology
- Machine Learning
Background
- Cervical cancer is a leading cause of mortality in women, underscoring the critical need for early detection and screening.
- Pathological changes in cervical cancer progress slowly, making timely diagnosis paramount for effective treatment and reduced mortality rates.
Purpose Of The Study
- To develop and evaluate a novel classification model for early cervical cancer detection using Raman spectroscopy.
- To enhance diagnostic accuracy by integrating attention mechanisms into a hierarchical convolutional neural network for cervical tissue sample analysis.
Main Methods
- Raman spectroscopy was employed to collect data from seven distinct cervical tissue types, including normal, pre-cancerous, and cancerous lesions.
- A one-dimensional hierarchical convolutional neural network incorporating Efficient Channel Attention Networks (ECAN) and Squeeze-and-Excitation Networks (SEN) was developed for tissue classification.
- Principal Component Analysis (PCA) was utilized in conjunction with the attention-based models for dimensionality reduction and feature enhancement.
Main Results
- The PCA-SEN-hierarchical network model achieved an average accuracy of 96.49%±2.12%, F1 score of 0.97±0.03, and AUC of 0.98±0.02 after 5-fold cross-validation.
- The PCA-ECAN-hierarchical network model demonstrated a high recall rate of 96.78%±2.85%.
- The proposed models significantly outperformed traditional Convolutional Neural Network (CNN) and ResNet, with accuracy improvements of 3.33% and 11.05%, respectively.
Conclusions
- The developed Raman spectroscopy-based model with attention mechanisms offers a highly accurate and user-friendly approach for rapid cervical cancer screening.
- This study provides a strong foundation for the clinical application of Raman spectroscopy as a diagnostic tool for cervical cancer.
- The integration of attention mechanisms significantly improves the diagnostic performance of hierarchical convolutional neural networks in classifying cervical tissue types.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
Related Concept Videos
A conventional Raman spectrophotometer includes a laser source, a sample holding system, a wavelength selector, and a detector.
The monochromatic laser source, typically using visible or near-infrared radiation, generates a highly focused beam of light. This light interacts with the molecules of the sample, scattering some of the light. Liquid and gaseous samples are usually tested in ordinary glass capillaries, while solids can be analyzed as powders packed in capillaries or as potassium...
The underlying principle of Raman spectroscopy is based on the interaction between light and matter, specifically molecules' inelastic scattering of photons. When a monochromatic beam of light, typically from a laser source, interacts with a sample, most scattered light has the same frequency as the incident light. This is known as Rayleigh scattering.
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and...