Buscar en
Revista Española de Medicina Nuclear e Imagen Molecular (English Edition)
Toda la web
Inicio Revista Española de Medicina Nuclear e Imagen Molecular (English Edition) Evaluation of survival of the patients with metastatic rectal cancer by staging ...
Journal Information
Share
Share
Download PDF
More article options
Visits
7
Original Article
Evaluation of survival of the patients with metastatic rectal cancer by staging 18F-FDG PET/CT radiomic and volumetric parameters
Evaluación de la supervivencia de pacientes con cáncer de recto metastásico mediante parámetros radiómicos y volumétricos de la poner 18F-FDG PET/TC de estadificación
Visits
7
Nurşin Agüloğlua,
Corresponding author
aguloglunursin@gmail.com

Corresponding author.
, Ayşegül Aksub
a The University of Health Sciences, Dr. Suat Seren Chest Diseases and Surgery Training and Research Hospital, Department of Nuclear Medicine, İzmir, Turkey
b İzmir Katip Çelebi University, Atatürk Training and Research Hospital, Department of Nuclear Medicine, İzmir, Turkey
This item has received
Received 12 May 2022. Accepted 07 September 2022
Article information
Abstract
Full Text
Bibliography
Download PDF
Statistics
Figures (3)
Show moreShow less
Tables (4)
Table 1. Definition of parameters evaluated including conventional and advanced metabolic indices, shape features and radiomic texture features.
Table 2. Parameters with statistically significant difference between 2S-2NS groups.
Table 3. AUC, PRC, MCC and accuracy values of ML algorithms to predict 2-year survival.
Table 4. The results of ML algorithms to predict 2-year survival.
Show moreShow less
Abstract
Objective

The aim of this study is to predict the prognosis in patients with metastatic rectal cancer (mRC) by obtaining a model with machine learning (ML) algorithms through volumetric and radiomic data obtained from baseline 18-Fluorine Fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) images.

Methods

Sixty-two patients with mRC who underwent 18F-FDG PET/CT imaging for staging between January 2015 and January 2021 were evaluated using LIFEx software. The volume of interest (VOI) of the primary tumor was generated and volumetric and textural features were obtained from this VOI. In addition, metabolic tumor volume (tMTV) and total lesion glycolysis (tTLG) values of tumor foci in the whole body. Clinical and radiomic data were evaluated with ML algorithms to create a model that predicts survival. Significant associations between these features and 1-year and 2-year survival were investigated.

Results

Random forest algorithm was the most successful algorithm in predicting 2-year survival (AUC: 0.843, PRC: 0.822, and MCC: 0.583). The model obtained with this algorithm was able to predict 49 patients with 79.03% accuracy. While tMTV and tTLG values were successful in predicting 1-year survival (p: 0.002 and 0.007, respectively), texture characteristics from the primary tumor did not show a significant relationship with 1-year survival.

Conclusions

In addition to the important role of 18F-FDG PET/CT in staging patients with mRC, this study shows that it is possible to predict survival with ML methods, with parameters obtained using texture analysis from the primary tumor and whole body volumetric parameters.

Keywords:
18F-FDG PET/CT
Metastatic colorectal cancer
Texture analysis
Machine learning
Resumen
Objetivo

El objetivo de este estudio es predecir el pronóstico de pacientes con cáncer de recto metastásico (CRM) mediante la obtención de modelo con algoritmos de aprendizaje automático (AA) a través de datos volumétricos y radiómicos obtenidos de la PET/TC basal.

Métodos

Pacientes con CRM que se sometieron a imágenes PET/TC 18F-FDG para estadificación en nuestro hospital entre enero 2015 y enero de 2021 fueron evaluados mediante el software LIFEx. El volumen de interés (VOl) del tumor primario fue generado. Además, se calcularon los valores de volumen tumoral metabólico (tMTV) y glucólisis de lesión total (tTLG) de los todos los focos tumorales. Se evaluaron los datos clínicos y radiómicos con algoritmos de AA para crear un modelo que predijera la supervivencia. Se investigaron asociaciones significativas entre estas características y la supervivencia a 1 y 2 años.

Resultados

El algoritmo de bosque aleatorio fue el algoritmo más exitoso para predecir la supervivencia a 2 años (AUC: 0,843, PRC: 0,822 y MCC: 0,583). Los valores de tMTV y tTLG tuvieron éxito en la predicción de la supervivencia a 1 año (p: 0,002 y 0,007, respectivamente), las características de la textura del tumor primario no mostraron una relación significativa con la supervivencia a 1 año.

Conclusiones

Además del importante papel de la PET-TC 18F-FDG en la estadificación de pacientes con CRM, este estudio muestra que es posible predecir la supervivencia con métodos AA, con parámetros obtenidos mediante el análisis de textura a partir de el tumor primario y parámetros volumétricos de cuerpo completo.

Palabras clave:
18F-FDG PET/TC
Cáncer colorrectal metastásico
Análisis de textura
Aprendizaje automático

Article

These are the options to access the full texts of the publication Revista Española de Medicina Nuclear e Imagen Molecular (English Edition)
Subscriber
Subscriber

If you already have your login data, please click here .

If you have forgotten your password you can you can recover it by clicking here and selecting the option “I have forgotten my password”
Subscribe
Subscribe to

Revista Española de Medicina Nuclear e Imagen Molecular (English Edition)

Purchase
Purchase article

Purchasing article the PDF version will be downloaded

Price 19.34 €

Purchase now
Contact
Phone for subscriptions and reporting of errors
From Monday to Friday from 9 a.m. to 6 p.m. (GMT + 1) except for the months of July and August which will be from 9 a.m. to 3 p.m.
Calls from Spain
932 415 960
Calls from outside Spain
+34 932 415 960
E-mail
Article options
Tools
es en pt

¿Es usted profesional sanitario apto para prescribir o dispensar medicamentos?

Are you a health professional able to prescribe or dispense drugs?

Você é um profissional de saúde habilitado a prescrever ou dispensar medicamentos