The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups
Abstract Background Manual delineation of volume of interest (VOI) is widely used in current radiomics analysis, suffering from high variability. The tolerance of delineation differences and possible influence on each step of radiomics analysis are not clear, requiring quantitative assessment. The p...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2019-12-01
|
Series: | Cancer Imaging |
Subjects: | |
Online Access: | https://doi.org/10.1186/s40644-019-0276-7 |
id |
doaj-03947633e94845569473807a406d5045 |
---|---|
record_format |
Article |
spelling |
doaj-03947633e94845569473807a406d50452021-04-02T18:41:53ZengBMCCancer Imaging1470-73302019-12-0119111210.1186/s40644-019-0276-7The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groupsXiao Zhang0Liming Zhong1Bin Zhang2Lu Zhang3Haiyan Du4Lijun Lu5Shuixing Zhang6Wei Yang7Qianjin Feng8School of Biomedical Engineering, Southern Medical UniversitySchool of Biomedical Engineering, Southern Medical UniversityDepartment of Radiology, The First Affiliated Hospital, Jinan UniversityDepartment of Radiology, Guangdong General Hospital/Guangdong Academy of Medical SciencesSchool of Biomedical Engineering, Southern Medical UniversitySchool of Biomedical Engineering, Southern Medical UniversityDepartment of Radiology, The First Affiliated Hospital, Jinan UniversitySchool of Biomedical Engineering, Southern Medical UniversitySchool of Biomedical Engineering, Southern Medical UniversityAbstract Background Manual delineation of volume of interest (VOI) is widely used in current radiomics analysis, suffering from high variability. The tolerance of delineation differences and possible influence on each step of radiomics analysis are not clear, requiring quantitative assessment. The purpose of our study was to investigate the effects of delineation of VOIs on radiomics analysis for the preoperative prediction of metastasis in nasopharyngeal carcinoma (NPC) and sentinel lymph node (SLN) metastasis in breast cancer. Methods This study retrospectively enrolled two datasets (NPC group: 238 cases; SLN group: 146 cases). Three operations, namely, erosion, smoothing, and dilation, were implemented on the VOIs accurately delineated by radiologists to generate diverse VOI variations. Then, we extracted 2068 radiomics features and evaluated the effects of VOI differences on feature values by the intra-class correlation coefficient (ICC). Feature selection was conducted by Maximum Relevance Minimum Redundancy combined with 0.632+ bootstrap algorithms. The prediction performance of radiomics models with random forest classifier were tested on an independent validation cohort by the area under the receive operating characteristic curve (AUC). Results The larger the VOIs changed, the fewer features with high ICCs. Under any variation, SLN group showed fewer features with ICC ≥ 0.9 compared with NPC group. Not more than 15% top-predictive features identical to the accurate VOIs were observed across feature selection. The differences of AUCs of models derived from VOIs across smoothing or dilation with 3 pixels were not statistically significant compared with the accurate VOIs (p > 0.05) except for T2-weighted fat suppression images (smoothing: 0.845 vs. 0.725, p = 0.001; dilation: 0.800 vs. 0.725, p = 0.042). Dilation with 5 and 7 pixels contributed to remarkable AUCs in SLN group but the opposite in NPC group. The radiomics models did not perform well when tested by data from other delineations. Conclusions Differences in delineation of VOIs affected radiomics analysis, related to specific disease and MRI sequences. Differences from smooth delineation or expansion with 3 pixels width around the tumors or lesions were acceptable. The delineation for radiomics analysis should follow a predefined and unified standard.https://doi.org/10.1186/s40644-019-0276-7RadiomicsMagnetic resonance imagingBreast cancerNasopharyngeal carcinomaPreoperative predictionSegmentation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiao Zhang Liming Zhong Bin Zhang Lu Zhang Haiyan Du Lijun Lu Shuixing Zhang Wei Yang Qianjin Feng |
spellingShingle |
Xiao Zhang Liming Zhong Bin Zhang Lu Zhang Haiyan Du Lijun Lu Shuixing Zhang Wei Yang Qianjin Feng The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups Cancer Imaging Radiomics Magnetic resonance imaging Breast cancer Nasopharyngeal carcinoma Preoperative prediction Segmentation |
author_facet |
Xiao Zhang Liming Zhong Bin Zhang Lu Zhang Haiyan Du Lijun Lu Shuixing Zhang Wei Yang Qianjin Feng |
author_sort |
Xiao Zhang |
title |
The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups |
title_short |
The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups |
title_full |
The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups |
title_fullStr |
The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups |
title_full_unstemmed |
The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups |
title_sort |
effects of volume of interest delineation on mri-based radiomics analysis: evaluation with two disease groups |
publisher |
BMC |
series |
Cancer Imaging |
issn |
1470-7330 |
publishDate |
2019-12-01 |
description |
Abstract Background Manual delineation of volume of interest (VOI) is widely used in current radiomics analysis, suffering from high variability. The tolerance of delineation differences and possible influence on each step of radiomics analysis are not clear, requiring quantitative assessment. The purpose of our study was to investigate the effects of delineation of VOIs on radiomics analysis for the preoperative prediction of metastasis in nasopharyngeal carcinoma (NPC) and sentinel lymph node (SLN) metastasis in breast cancer. Methods This study retrospectively enrolled two datasets (NPC group: 238 cases; SLN group: 146 cases). Three operations, namely, erosion, smoothing, and dilation, were implemented on the VOIs accurately delineated by radiologists to generate diverse VOI variations. Then, we extracted 2068 radiomics features and evaluated the effects of VOI differences on feature values by the intra-class correlation coefficient (ICC). Feature selection was conducted by Maximum Relevance Minimum Redundancy combined with 0.632+ bootstrap algorithms. The prediction performance of radiomics models with random forest classifier were tested on an independent validation cohort by the area under the receive operating characteristic curve (AUC). Results The larger the VOIs changed, the fewer features with high ICCs. Under any variation, SLN group showed fewer features with ICC ≥ 0.9 compared with NPC group. Not more than 15% top-predictive features identical to the accurate VOIs were observed across feature selection. The differences of AUCs of models derived from VOIs across smoothing or dilation with 3 pixels were not statistically significant compared with the accurate VOIs (p > 0.05) except for T2-weighted fat suppression images (smoothing: 0.845 vs. 0.725, p = 0.001; dilation: 0.800 vs. 0.725, p = 0.042). Dilation with 5 and 7 pixels contributed to remarkable AUCs in SLN group but the opposite in NPC group. The radiomics models did not perform well when tested by data from other delineations. Conclusions Differences in delineation of VOIs affected radiomics analysis, related to specific disease and MRI sequences. Differences from smooth delineation or expansion with 3 pixels width around the tumors or lesions were acceptable. The delineation for radiomics analysis should follow a predefined and unified standard. |
topic |
Radiomics Magnetic resonance imaging Breast cancer Nasopharyngeal carcinoma Preoperative prediction Segmentation |
url |
https://doi.org/10.1186/s40644-019-0276-7 |
work_keys_str_mv |
AT xiaozhang theeffectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT limingzhong theeffectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT binzhang theeffectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT luzhang theeffectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT haiyandu theeffectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT lijunlu theeffectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT shuixingzhang theeffectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT weiyang theeffectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT qianjinfeng theeffectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT xiaozhang effectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT limingzhong effectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT binzhang effectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT luzhang effectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT haiyandu effectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT lijunlu effectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT shuixingzhang effectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT weiyang effectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups AT qianjinfeng effectsofvolumeofinterestdelineationonmribasedradiomicsanalysisevaluationwithtwodiseasegroups |
_version_ |
1721550998491627520 |