This study is a retrospective exploratory trial conducted at a single center, aiming to develop and validate a preoperative lymphatic metastasis model for cervical cancer using artificial intelligence deep learning. The model is trained using preoperative imaging and postoperative pathological findings of cervical cancer patients, with the goal of enhancing the accuracy of lymphatic metastasis prediction through preoperative imaging and offering insights for treatment decisions.

Inclusion criteria:

1. patients with preoperative diagnosis of invasive cervical cancer stage I-III, with any type of pathology, and patients who underwent radical/modified radical cervical cancer surgery + pelvic lymph node dissection in our hospital.
2. Age ≥18 years old and ≤80 years old
3. patients with complete preoperative pelvic MRI images and postoperative pathology and clinical data in our hospital

Exclusion criteria:

1. Patients during pregnancy or breastfeeding, patients within 42 days of abortion
2. Patients who have received neoadjuvant chemotherapy or radiotherapy before surgery for this previous cervical cancer
3. Patients with other malignant tumors within 5 years
4. Combination of other underlying diseases that may lead to enlarged pelvic lymph nodes
5. Imaging report more than 1 month prior to surgery
6. Poor image quality and unrecognizable

All patient information and imaging data were collected from the Obstetrics and Gynecology Hospital of Fudan University. This hospital is a specialized tertiary care facility and is recognized as the leading Obstetrics and Gynecology hospital in China.