Radiomics-based lymph nodes prognostic models from three MRI regions in nasopharyngeal carcinoma

Hui Xie ¹, Wenjie Huang ¹, Shaolong Li ¹

⁰Department of Radiology, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China.

Heliyon +

|

May 28, 2024

View abstract on PubMed

Summary

Radiomics analysis of magnetic resonance imaging (MRI) data from nasopharyngeal carcinoma (NPC) lymph nodes can predict patient survival. The largest slice of the largest lymph node (LSLN) radiomics signature, combined with clinical factors, offers accurate prognosis for NPC patients.

Area Of Science

Oncology
Radiology
Medical Imaging Analysis

Background

Accurate prognosis for nasopharyngeal carcinoma (NPC) is crucial for effective treatment planning.
Lymph node metastasis is a key indicator of treatment failure and recurrence in NPC patients.
Traditional radiological evaluation of lymph nodes can be subjective and inconsistent.

Purpose Of The Study

To evaluate the predictive performance of radiomics models based on pretreatment magnetic resonance imaging (MRI)-determined metastatic lymph nodes for NPC prognosis.
To compare three different lymph node delineation methods for radiomics feature extraction.

Main Methods

A retrospective analysis of 729 newly diagnosed NPC patients without distant metastases was performed.
Radiomics features were extracted from all lymph nodes (ALN), the largest lymph node (LLN), and the largest slice of the largest lymph node (LSLN).
Three radiomics signatures were generated and combined with clinical factors to predict overall survival (OS).

Main Results

The LSLN radiomics signature, integrated with clinical factors, demonstrated high accuracy and robustness in predicting OS.
The combined model achieved a C-index of 0.762 (95% CI: 0.760-0.763) for overall survival prediction.
Pretreatment MRI-based radiomics offers a quantitative and objective approach to NPC prognosis.

Conclusions

Radiomics analysis using pretreatment MRI-determined metastatic lymph nodes can accurately predict NPC prognosis.
The LSLN radiomics signature combined with clinical factors provides a valuable tool for improving treatment planning in NPC.
This quantitative approach overcomes the limitations of subjective radiological assessments.

Keywords:

Lymph node Magnetic resonance imaging Nasopharyngeal carcinoma Radiomics