Multimodal Deep Learning for Lymph Node Metastasis in Thyroid Cancer

A Multicenter Study on Developing a Multimodal Deep Learning Model Based on Color Doppler Ultrasound for Predicting Lymph Node Metastasis and Cancer Staging in Papillary Thyroid Carcinoma

Papillary thyroid carcinoma (PTC) is the most common endocrine malignancy in clinical practice, accounting for approximately 85% of all thyroid malignancies. The occurrence of cervical lymph node metastasis further increases the risk of local tumor recurrence and distant metastasis, thereby reducing patient survival rates. Pathological examinations reveal that approximately 30-80% of PTC patients have lymph node metastasis. Early detection of metastatic lymph nodes and the development of individualized treatment plans are crucial for improving patient prognosis. Currently, the primary method for diagnosing lymph node metastasis is ultrasound-guided fine-needle aspiration, but its accuracy is limited by sample quality and carries a risk of false-negative results. In recent years, deep learning technology has demonstrated significant potential in the field of medical image analysis. Therefore, the investigators aim to develop a deep learning model based on neck ultrasound to more accurately predict lymph node metastasis.

Inclusion Criteria:

Cases aged 18-80 years who underwent thyroid ultrasound examination and postoperative pathological examination of the thyroid.

Cases with a first-time diagnosis of papillary thyroid carcinoma. Cases who underwent lymph node dissection

Exclusion Criteria:

Cases aged <18 years or >80 years. Cases with poor-quality ultrasound images. Cases with incompletely visualized nodules. Cases with images showing multiple distinct lesions. Cases belonging to special populations. Cases with concurrent other tumors. Cases with a history of thyroid cancer resection