Cargando…

Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging

IMPORTANCE: Accurate pre-treatment prediction of distant metastasis in patients with Nasopharyngeal Carcinoma (NPC) enables the implementation of appropriate treatment strategies for high-risk individuals. PURPOSE: To develop and assess a Convolutional Neural Network (CNN) model using pre-therapy Ma...

Descripción completa

Detalles Bibliográficos
Autores principales: Hua, Hong-Li, Deng, Yu-Qin, Li, Song, Li, Si-Te, Li, Fen, Xiao, Bai-Kui, Huang, Jin, Tao, Ze-Zhang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Bentham Science Publishers 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10236565/
https://www.ncbi.nlm.nih.gov/pubmed/36121078
http://dx.doi.org/10.2174/1386207325666220919091210
_version_ 1785052964982882304
author Hua, Hong-Li
Deng, Yu-Qin
Li, Song
Li, Si-Te
Li, Fen
Xiao, Bai-Kui
Huang, Jin
Tao, Ze-Zhang
author_facet Hua, Hong-Li
Deng, Yu-Qin
Li, Song
Li, Si-Te
Li, Fen
Xiao, Bai-Kui
Huang, Jin
Tao, Ze-Zhang
author_sort Hua, Hong-Li
collection PubMed
description IMPORTANCE: Accurate pre-treatment prediction of distant metastasis in patients with Nasopharyngeal Carcinoma (NPC) enables the implementation of appropriate treatment strategies for high-risk individuals. PURPOSE: To develop and assess a Convolutional Neural Network (CNN) model using pre-therapy Magnetic Resonance (MR) imaging to predict distant metastasis in NPC patients. METHODS: We retrospectively reviewed data of 441 pathologically diagnosed NPC patients who underwent complete radiotherapy and chemotherapy at Renmin Hospital of Wuhan University (Hubei, China) between February 2012 and March 2018. Using Adobe Photoshop, an experienced radiologist segmented MR images with rectangular regions of interest. To develop an accurate model according to the primary tumour, Cervical Metastatic Lymph Node (CMLN), the largest area of invasion of the primary tumour, and image segmentation methods, we constructed intratumoural and intra-peritumoural datasets that were used for training and test of the transfer learning models. Each model’s precision was assessed according to its receiver operating characteristic curve and accuracy. Generated high-risk-related Grad-Cams demonstrated how the model captured the image features and further verified its reliability. RESULTS: Among the four models, all intra-peritumoural datasets performed better than the corresponding intratumoural datasets, with the CMLN intra-peritumoural dataset exhibiting the best performance (average area under the curves (AUCs) = 0.88). There was no significant difference between average AUCs of the Max and NPC tumour datasets. AUCs of the eight datasets for the four models were higher than those of the Tumour-Node-Metastasis staging system (AUC=0.67). In most datasets, the xception model had higher AUCs than other models. The efficientnet-b0 and xception models efficiently extracted high-risk features. CONCLUSION: The CNN model predicted distant metastasis in NPC patients with high accuracy. Compared to the primary tumour, the CMLN better predicted distant metastasis. In addition to intratumoural data, peritumoural information can facilitate the prediction of distant metastasis. With a larger sample size, datasets of the largest areas of tumour invasion may achieve meaningful accuracy. Among the models, xception had the best overall performance.
format Online
Article
Text
id pubmed-10236565
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Bentham Science Publishers
record_format MEDLINE/PubMed
spelling pubmed-102365652023-06-03 Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging Hua, Hong-Li Deng, Yu-Qin Li, Song Li, Si-Te Li, Fen Xiao, Bai-Kui Huang, Jin Tao, Ze-Zhang Comb Chem High Throughput Screen Chemistry, Combinatorial Chemistry and High Throughput Screening, Biochemical Research Methods, Applied Chemistry, Pharmacology IMPORTANCE: Accurate pre-treatment prediction of distant metastasis in patients with Nasopharyngeal Carcinoma (NPC) enables the implementation of appropriate treatment strategies for high-risk individuals. PURPOSE: To develop and assess a Convolutional Neural Network (CNN) model using pre-therapy Magnetic Resonance (MR) imaging to predict distant metastasis in NPC patients. METHODS: We retrospectively reviewed data of 441 pathologically diagnosed NPC patients who underwent complete radiotherapy and chemotherapy at Renmin Hospital of Wuhan University (Hubei, China) between February 2012 and March 2018. Using Adobe Photoshop, an experienced radiologist segmented MR images with rectangular regions of interest. To develop an accurate model according to the primary tumour, Cervical Metastatic Lymph Node (CMLN), the largest area of invasion of the primary tumour, and image segmentation methods, we constructed intratumoural and intra-peritumoural datasets that were used for training and test of the transfer learning models. Each model’s precision was assessed according to its receiver operating characteristic curve and accuracy. Generated high-risk-related Grad-Cams demonstrated how the model captured the image features and further verified its reliability. RESULTS: Among the four models, all intra-peritumoural datasets performed better than the corresponding intratumoural datasets, with the CMLN intra-peritumoural dataset exhibiting the best performance (average area under the curves (AUCs) = 0.88). There was no significant difference between average AUCs of the Max and NPC tumour datasets. AUCs of the eight datasets for the four models were higher than those of the Tumour-Node-Metastasis staging system (AUC=0.67). In most datasets, the xception model had higher AUCs than other models. The efficientnet-b0 and xception models efficiently extracted high-risk features. CONCLUSION: The CNN model predicted distant metastasis in NPC patients with high accuracy. Compared to the primary tumour, the CMLN better predicted distant metastasis. In addition to intratumoural data, peritumoural information can facilitate the prediction of distant metastasis. With a larger sample size, datasets of the largest areas of tumour invasion may achieve meaningful accuracy. Among the models, xception had the best overall performance. Bentham Science Publishers 2023-03-24 2023-03-24 /pmc/articles/PMC10236565/ /pubmed/36121078 http://dx.doi.org/10.2174/1386207325666220919091210 Text en © 2023 Bentham Science Publishers https://creativecommons.org/licenses/by/4.0/This is an Open Access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode
spellingShingle Chemistry, Combinatorial Chemistry and High Throughput Screening, Biochemical Research Methods, Applied Chemistry, Pharmacology
Hua, Hong-Li
Deng, Yu-Qin
Li, Song
Li, Si-Te
Li, Fen
Xiao, Bai-Kui
Huang, Jin
Tao, Ze-Zhang
Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging
title Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging
title_full Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging
title_fullStr Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging
title_full_unstemmed Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging
title_short Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging
title_sort deep learning for predicting distant metastasis in patients with nasopharyngeal carcinoma based on pre-radiotherapy magnetic resonance imaging
topic Chemistry, Combinatorial Chemistry and High Throughput Screening, Biochemical Research Methods, Applied Chemistry, Pharmacology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10236565/
https://www.ncbi.nlm.nih.gov/pubmed/36121078
http://dx.doi.org/10.2174/1386207325666220919091210
work_keys_str_mv AT huahongli deeplearningforpredictingdistantmetastasisinpatientswithnasopharyngealcarcinomabasedonpreradiotherapymagneticresonanceimaging
AT dengyuqin deeplearningforpredictingdistantmetastasisinpatientswithnasopharyngealcarcinomabasedonpreradiotherapymagneticresonanceimaging
AT lisong deeplearningforpredictingdistantmetastasisinpatientswithnasopharyngealcarcinomabasedonpreradiotherapymagneticresonanceimaging
AT lisite deeplearningforpredictingdistantmetastasisinpatientswithnasopharyngealcarcinomabasedonpreradiotherapymagneticresonanceimaging
AT lifen deeplearningforpredictingdistantmetastasisinpatientswithnasopharyngealcarcinomabasedonpreradiotherapymagneticresonanceimaging
AT xiaobaikui deeplearningforpredictingdistantmetastasisinpatientswithnasopharyngealcarcinomabasedonpreradiotherapymagneticresonanceimaging
AT huangjin deeplearningforpredictingdistantmetastasisinpatientswithnasopharyngealcarcinomabasedonpreradiotherapymagneticresonanceimaging
AT taozezhang deeplearningforpredictingdistantmetastasisinpatientswithnasopharyngealcarcinomabasedonpreradiotherapymagneticresonanceimaging