AI-Based Multimodal Multi-tasks Analysis Reveals Tumor Molecular Heterogeneity, Predicts Preoperative Lymph Node Metastasis and Prognosis in Papillary Thyroid Carcinoma

Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University256 enrolled

Overview

This study involved a comprehensive analysis of 256 PTC patients from Sun Yat-sen Memorial Hospital of Sun Yat-sen University (SYSMH) and 499 patients from The Cancer Genome Atlas. DNA-based next-generation sequencing (NGS) and single-cell RNA sequencing (scRNA-seq) were employed to capture genetic alterations and TME heterogeneity. A deep learning multimodal model was developed by incorporating matched histopathology slide images, genomic, transcriptomic, immune cells data to predict LNM and disease-free survival (DFS).

Study Type

OBSERVATIONAL

Enrollment

256

Conditions

Papillary Thyroid Carcinoma; Molecular Heterogeneity; Multi-model Analysis; Artificial Intelligence; Lymph Node Metastases; Disease-free Survival

Interventions

OTHER

Eligibility

Medical Language ↔ Plain English

Inclusion Criteria: ≥ 18 years of age Diagnosis of Papillary thyroid carcinoma at least one months before trial Willing to return for required follow-up (posttest) visits Exclusion Criteria: The patient requires valve or other likely surgery The patient is unable to carry out any physical activity without discomfort The patient had thyroid ache within three months prior to enrollment The patient refuses to give informed consent The patient is a candidate for coronary bypass surgery or something similar

Outcomes

Primary Outcomes

Lymph node metastasis

Lymph node metastasis is frequently influenced by a myriad of factors, and tumor heterogeneity stands out as a significant contributing element.

Time frame: 2021.10.1

Secondary Outcomes

Disease-free survival

Disease-free survival is defined as the time from randomization to the first occurrence of a relapse, progression, or death from any cause, commonly used in clinical trials of adjuvant therapy after curative surgery or radiation therapy. It is also used as a primary endpoint in studies of neoadjuvant therapy and a useful endpoint for evaluating the efficacy of treatments that aim to prevent cancer recurrence research