Related Experiment Video
Updated: Jan 15, 2026
05:41
Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
Published on: February 9, 2024
1.0K
Detection of Lymph Node Metastasis in Thyroid Cancer Using Deep Learning and Second Harmonic Generation Imaging
Han Wu1,2, Qiuyan He3, Zhiyan Luo1
1School of Science, Jimei University, Xiamen, China.
Microscopy Research and Technique
|October 6, 2025
Summary
A new AI tool, AutoThyroLNMNet, uses SHG imaging and deep learning to accurately detect lymph node metastasis in papillary thyroid cancer, improving diagnosis and treatment planning.
Area of Science:
- Oncology
- Medical Imaging
- Artificial Intelligence
Background:
- Papillary thyroid carcinoma (PTC) is the most common thyroid cancer.
- Lymph node metastasis (LNM) in PTC accelerates tumor progression.
- Current diagnostic methods for LNM have limited sensitivity, impacting treatment.
Purpose of the Study:
- To introduce AutoThyroLNMNet, an automated system for classifying LNM in thyroid cancer.
- To integrate Second-harmonic generation (SHG) imaging with deep learning for LNM detection.
- To develop a precise diagnostic tool for LNM in PTC.
Main Methods:
- Developed AutoThyroLNMNet, an automated quantitative histological classification framework.
- Utilized Pyramid Vision Transformer v2 (PVTv2) as the deep learning backbone.
- Fused deep learning outputs, pathological data, and collagen features using a multi-layer perceptron.
Main Results:
- The combined model demonstrated strong performance on training datasets.
- The model incorporating 3D texture features achieved the highest efficacy.
- Achieved an area under the receiver operating characteristic (ROC) curve of 0.99 for LNM classification.
Conclusions:
- AutoThyroLNMNet enables automatic and quantitative classification of LNM in thyroid cancer.
- The system offers a novel and effective approach for precise LNM detection.
- This tool can aid in improved treatment planning for PTC patients with LNM.
