European Radiology: How to predict early temporal lobe injury after radiotherapy for nasopharyngeal carcinoma?

Nasopharyngeal carcinoma (NPC) is the most common head and neck tumor in Southeast Asia, especially in southern China .
Radiotherapy remains the mainstay of treatment for NPC due to its sensitivity to radiotherapy .
Due to the aggressive growth of nasopharyngeal carcinoma, it is clinically difficult to design a radiation field that can avoid important organs such as the temporal lobe and brain stem for treatment , especially the bilateral anterior and lower temporal lobes that receive marginal irradiation are very easy Radiation-induced temporal lobe injury (RTLI), one of the most serious neurological complications, occurs .
RTLI may cause long-term neurocognitive dysfunction in patients and severely reduce the quality of life .
Therefore, early prediction of RTLI is of great significance for timely adjustment of treatment plans and early clinical intervention .

Nasopharyngeal carcinoma (NPC) is the most common head and neck tumor in Southeast Asia, especially in southern China .

Radiotherapy remains the mainstay of treatment for NPC due to its sensitivity to radiotherapy .
Due to the aggressive growth of nasopharyngeal carcinoma, it is clinically difficult to design a radiation field that can avoid important organs such as the temporal lobe and brain stem for treatment , especially the bilateral anterior and lower temporal lobes that receive marginal irradiation are very easy Radiation-induced temporal lobe injury (RTLI), one of the most serious neurological complications, occurs .
RTLI may cause long-term neurocognitive dysfunction in patients and severely reduce the quality of life .
Therefore, early prediction of RTLI is of great significance for timely adjustment of treatment plans and early clinical intervention .

Several structural and functional MRI studies have shown corresponding changes in microstructural, functional, and metabolic information of lobes after radiotherapy .

However, functional MRI has high equipment requirements and cannot be promoted as a routine scanning scheme .
Radiomics can further reflect the biological characteristics of tumors through high-throughput extraction of deep feature information hidden in medical images, which can be used for tumor prognosis and efficacy evaluation .
Currently, there are few reports of radiomics studies on the prediction of RTLI in nasopharyngeal carcinoma .

Several structural and functional MRI studies have shown corresponding changes in microstructural, functional, and metabolic information of lobes after radiotherapy .
However, functional MRI has high equipment requirements and cannot be promoted as a routine scanning scheme .
Radiomics can further reflect the biological characteristics of tumors through high-throughput extraction of deep feature information hidden in medical images, which can be used for tumor prognosis and efficacy evaluation .
Currently, there are few reports of radiomics studies on the prediction of RTLI in nasopharyngeal carcinoma .

Recently, a study published in the journal European Radiology explored the role of MRI - based radiomics nomogram combining radiomic features and clinical factors in predicting the occurrence of RTLI at the end of NPC radiotherapy .

An objective basis is provided for the development of an appropriate treatment plan .
 

Recently, a study published in the journal European Radiology explored the role of MRI - based radiomics nomogram combining radiomic features and clinical factors in predicting the occurrence of RTLI at the end of NPC radiotherapy .
An objective basis is provided for the development of an appropriate treatment plan .
 

This study retrospectively analyzed 128 RTLI-positive and 278 RTLI-negative patient images from 203 NPC cases who received radiotherapy

The radiomic signature consisted of 14 selected signatures that were significantly associated with RTLI

 

Figure ROC curves of radiomics model, clinical model and radiomics nomogram model in training (a) and validation (b) (numbers in parentheses represent 95% CI) .
 

Figure ROC curves of radiomics model, clinical model and radiomics nomogram model in training (a) and validation (b) (numbers in parentheses represent 95% CI) .

 

This study constructs and validates an MRI-based radiomics nomogram that combines radiomics features and clinical factors and can be used to predict RTLI in patients with nasopharyngeal carcinoma .
The nomogram model shows good predictive performance in both training and validation sets, indicating its potential as a potential tool for early prediction of RTLI .

Original source :

Original source :

Jing Hou , Handong Li , Biao Zeng , et al .

MRI-based radiomics nomogram for predicting temporal lobe injury after radiotherapy in nasopharyngeal carcinoma .
DOI : 10.

Jing Hou Handong Li Biao Zeng ,et al MRI-based radiomics nomogram for predicting temporal lobe injury after radiotherapy in nasopharyngeal carcinoma 10.
1007/s00330-021-08254-5 10.
1007/s00330-021-08254-5Leave a message here