Preoperative prediction of clinical and pathological stages for patients with esophageal cancer using PET/CT radiomics
Abstract Background Preoperative stratification is critical for the management of patients with esophageal cancer (EC). To investigate the feasibility and accuracy of PET-CT-based radiomics in preoperative prediction of clinical and pathological stages for patients with EC. Methods Histologically co...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2023-10-01
|
Series: | Insights into Imaging |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13244-023-01528-0 |
_version_ | 1797452402706612224 |
---|---|
author | Xiyao Lei Zhuo Cao Yibo Wu Jie Lin Zhenhua Zhang Juebin Jin Yao Ai Ji Zhang Dexi Du Zhifeng Tian Congying Xie Weiwei Yin Xiance Jin |
author_facet | Xiyao Lei Zhuo Cao Yibo Wu Jie Lin Zhenhua Zhang Juebin Jin Yao Ai Ji Zhang Dexi Du Zhifeng Tian Congying Xie Weiwei Yin Xiance Jin |
author_sort | Xiyao Lei |
collection | DOAJ |
description | Abstract Background Preoperative stratification is critical for the management of patients with esophageal cancer (EC). To investigate the feasibility and accuracy of PET-CT-based radiomics in preoperative prediction of clinical and pathological stages for patients with EC. Methods Histologically confirmed 100 EC patients with preoperative PET-CT images were enrolled retrospectively and randomly divided into training and validation cohorts at a ratio of 7:3. The maximum relevance minimum redundancy (mRMR) was applied to select optimal radiomics features from PET, CT, and fused PET-CT images, respectively. Logistic regression (LR) was applied to classify the T stage (T1,2 vs. T3,4), lymph node metastasis (LNM) (LNM(−) vs. LNM(+)), and pathological state (pstage) (I–II vs. III–IV) with features from CT (CT_LR_Score), PET (PET_LR_Score), fused PET/CT (Fused_LR_Score), and combined CT and PET features (CT + PET_LR_Score), respectively. Results Seven, 10, and 7 CT features; 7, 8, and 7 PET features; and 3, 6, and 3 fused PET/CT features were selected using mRMR for the prediction of T stage, LNM, and pstage, respectively. The area under curves (AUCs) for T stage, LNM, and pstage prediction in the validation cohorts were 0.846, 0.756, 0.665, and 0.815; 0.769, 0.760, 0.665, and 0.824; and 0.727, 0.785, 0.689, and 0.837 for models of CT_LR_Score, PET_ LR_Score, Fused_ LR_Score, and CT + PET_ LR_Score, respectively. Conclusions Accurate prediction ability was observed with combined PET and CT radiomics in the prediction of T stage, LNM, and pstage for EC patients. Critical relevance statement PET/CT radiomics is feasible and promising to stratify stages for esophageal cancer preoperatively. Key points • PET-CT radiomics achieved the best performance for Node and pathological stage prediction. • CT radiomics achieved the best AUC for T stage prediction. • PET-CT radiomics is feasible and promising to stratify stages for EC preoperatively. Graphical Abstract |
first_indexed | 2024-03-09T15:08:05Z |
format | Article |
id | doaj.art-a8ad5c2bf1bb4643ad149e86f502f218 |
institution | Directory Open Access Journal |
issn | 1869-4101 |
language | English |
last_indexed | 2024-03-09T15:08:05Z |
publishDate | 2023-10-01 |
publisher | SpringerOpen |
record_format | Article |
series | Insights into Imaging |
spelling | doaj.art-a8ad5c2bf1bb4643ad149e86f502f2182023-11-26T13:32:46ZengSpringerOpenInsights into Imaging1869-41012023-10-0114111010.1186/s13244-023-01528-0Preoperative prediction of clinical and pathological stages for patients with esophageal cancer using PET/CT radiomicsXiyao Lei0Zhuo Cao1Yibo Wu2Jie Lin3Zhenhua Zhang4Juebin Jin5Yao Ai6Ji Zhang7Dexi Du8Zhifeng Tian9Congying Xie10Weiwei Yin11Xiance Jin12Department of Radiation Oncology, Lishui Municipal Central HospitalDepartment of Respiratory, Lishui People’s HospitalDepartment of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical UniversityDepartment of Nuclear Medicine, 1st Affiliated Hospital of Wenzhou Medical UniversityDepartment of Radiology, 1st Affiliated Hospital of Wenzhou Medical UniversityDepartment of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical UniversityDepartment of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical UniversityDepartment of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical UniversityDepartment of Radiation Oncology, Lishui Municipal Central HospitalDepartment of Radiation Oncology, Lishui Municipal Central HospitalDepartment of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical UniversityDepartment of Nuclear Medicine, 1st Affiliated Hospital of Wenzhou Medical UniversityDepartment of Radiation Oncology, Lishui Municipal Central HospitalAbstract Background Preoperative stratification is critical for the management of patients with esophageal cancer (EC). To investigate the feasibility and accuracy of PET-CT-based radiomics in preoperative prediction of clinical and pathological stages for patients with EC. Methods Histologically confirmed 100 EC patients with preoperative PET-CT images were enrolled retrospectively and randomly divided into training and validation cohorts at a ratio of 7:3. The maximum relevance minimum redundancy (mRMR) was applied to select optimal radiomics features from PET, CT, and fused PET-CT images, respectively. Logistic regression (LR) was applied to classify the T stage (T1,2 vs. T3,4), lymph node metastasis (LNM) (LNM(−) vs. LNM(+)), and pathological state (pstage) (I–II vs. III–IV) with features from CT (CT_LR_Score), PET (PET_LR_Score), fused PET/CT (Fused_LR_Score), and combined CT and PET features (CT + PET_LR_Score), respectively. Results Seven, 10, and 7 CT features; 7, 8, and 7 PET features; and 3, 6, and 3 fused PET/CT features were selected using mRMR for the prediction of T stage, LNM, and pstage, respectively. The area under curves (AUCs) for T stage, LNM, and pstage prediction in the validation cohorts were 0.846, 0.756, 0.665, and 0.815; 0.769, 0.760, 0.665, and 0.824; and 0.727, 0.785, 0.689, and 0.837 for models of CT_LR_Score, PET_ LR_Score, Fused_ LR_Score, and CT + PET_ LR_Score, respectively. Conclusions Accurate prediction ability was observed with combined PET and CT radiomics in the prediction of T stage, LNM, and pstage for EC patients. Critical relevance statement PET/CT radiomics is feasible and promising to stratify stages for esophageal cancer preoperatively. Key points • PET-CT radiomics achieved the best performance for Node and pathological stage prediction. • CT radiomics achieved the best AUC for T stage prediction. • PET-CT radiomics is feasible and promising to stratify stages for EC preoperatively. Graphical Abstracthttps://doi.org/10.1186/s13244-023-01528-0Esophageal neoplasmsPET-CTLymphatic metastasisNeoplasm staging |
spellingShingle | Xiyao Lei Zhuo Cao Yibo Wu Jie Lin Zhenhua Zhang Juebin Jin Yao Ai Ji Zhang Dexi Du Zhifeng Tian Congying Xie Weiwei Yin Xiance Jin Preoperative prediction of clinical and pathological stages for patients with esophageal cancer using PET/CT radiomics Insights into Imaging Esophageal neoplasms PET-CT Lymphatic metastasis Neoplasm staging |
title | Preoperative prediction of clinical and pathological stages for patients with esophageal cancer using PET/CT radiomics |
title_full | Preoperative prediction of clinical and pathological stages for patients with esophageal cancer using PET/CT radiomics |
title_fullStr | Preoperative prediction of clinical and pathological stages for patients with esophageal cancer using PET/CT radiomics |
title_full_unstemmed | Preoperative prediction of clinical and pathological stages for patients with esophageal cancer using PET/CT radiomics |
title_short | Preoperative prediction of clinical and pathological stages for patients with esophageal cancer using PET/CT radiomics |
title_sort | preoperative prediction of clinical and pathological stages for patients with esophageal cancer using pet ct radiomics |
topic | Esophageal neoplasms PET-CT Lymphatic metastasis Neoplasm staging |
url | https://doi.org/10.1186/s13244-023-01528-0 |
work_keys_str_mv | AT xiyaolei preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT zhuocao preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT yibowu preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT jielin preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT zhenhuazhang preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT juebinjin preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT yaoai preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT jizhang preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT dexidu preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT zhifengtian preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT congyingxie preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT weiweiyin preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics AT xiancejin preoperativepredictionofclinicalandpathologicalstagesforpatientswithesophagealcancerusingpetctradiomics |