Cargando…
Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm
Using nephrographic phase CT images combined with pathology diagnosis, we aim to develop and validate a fusion feature-based stacking ensemble machine learning model to distinguish malignant renal neoplasms from cystic renal lesions (CRLs). This retrospective research includes 166 individuals with C...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9640984/ https://www.ncbi.nlm.nih.gov/pubmed/36387261 http://dx.doi.org/10.3389/fonc.2022.1028577 |
_version_ | 1784825988914348032 |
---|---|
author | He, Quan-Hao Tan, Hao Liao, Fang-Tong Zheng, Yi-Neng Lv, Fa-Jin Jiang, Qing Xiao, Ming-Zhao |
author_facet | He, Quan-Hao Tan, Hao Liao, Fang-Tong Zheng, Yi-Neng Lv, Fa-Jin Jiang, Qing Xiao, Ming-Zhao |
author_sort | He, Quan-Hao |
collection | PubMed |
description | Using nephrographic phase CT images combined with pathology diagnosis, we aim to develop and validate a fusion feature-based stacking ensemble machine learning model to distinguish malignant renal neoplasms from cystic renal lesions (CRLs). This retrospective research includes 166 individuals with CRLs for model training and 47 individuals with CRLs in another institution for model testing. Histopathology results are adopted as diagnosis criterion. Nephrographic phase CT scans are selected to build the fusion feature-based machine learning algorithms. The pretrained 3D-ResNet50 CNN model and radiomics methods are selected to extract deep features and radiomics features, respectively. Fivefold cross-validated least absolute shrinkage and selection operator (LASSO) regression methods are adopted to identify the most discriminative candidate features in the development cohort. Intraclass correlation coefficients and interclass correlation coefficients are employed to evaluate feature’s reproducibility. Pearson correlation coefficients for normal distribution features and Spearman’s rank correlation coefficients for non-normal distribution features are used to eliminate redundant features. After that, stacking ensemble machine learning models are developed in the training cohort. The area under the receiver operator characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) are adopted in the testing cohort to evaluate the performance of each model. The stacking ensemble machine learning algorithm reached excellent diagnostic performance in the testing dataset. The calibration plot shows good stability when using the stacking ensemble model. Net benefits presented by DCA are higher than the Bosniak 2019 version classification when employing any machine learning algorithm. The fusion feature-based machine learning algorithm accurately distinguishes malignant renal neoplasms from CRLs, which outperformed the Bosniak 2019 version classification, and proves to be more applicable for clinical decision-making. |
format | Online Article Text |
id | pubmed-9640984 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-96409842022-11-15 Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm He, Quan-Hao Tan, Hao Liao, Fang-Tong Zheng, Yi-Neng Lv, Fa-Jin Jiang, Qing Xiao, Ming-Zhao Front Oncol Oncology Using nephrographic phase CT images combined with pathology diagnosis, we aim to develop and validate a fusion feature-based stacking ensemble machine learning model to distinguish malignant renal neoplasms from cystic renal lesions (CRLs). This retrospective research includes 166 individuals with CRLs for model training and 47 individuals with CRLs in another institution for model testing. Histopathology results are adopted as diagnosis criterion. Nephrographic phase CT scans are selected to build the fusion feature-based machine learning algorithms. The pretrained 3D-ResNet50 CNN model and radiomics methods are selected to extract deep features and radiomics features, respectively. Fivefold cross-validated least absolute shrinkage and selection operator (LASSO) regression methods are adopted to identify the most discriminative candidate features in the development cohort. Intraclass correlation coefficients and interclass correlation coefficients are employed to evaluate feature’s reproducibility. Pearson correlation coefficients for normal distribution features and Spearman’s rank correlation coefficients for non-normal distribution features are used to eliminate redundant features. After that, stacking ensemble machine learning models are developed in the training cohort. The area under the receiver operator characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) are adopted in the testing cohort to evaluate the performance of each model. The stacking ensemble machine learning algorithm reached excellent diagnostic performance in the testing dataset. The calibration plot shows good stability when using the stacking ensemble model. Net benefits presented by DCA are higher than the Bosniak 2019 version classification when employing any machine learning algorithm. The fusion feature-based machine learning algorithm accurately distinguishes malignant renal neoplasms from CRLs, which outperformed the Bosniak 2019 version classification, and proves to be more applicable for clinical decision-making. Frontiers Media S.A. 2022-10-25 /pmc/articles/PMC9640984/ /pubmed/36387261 http://dx.doi.org/10.3389/fonc.2022.1028577 Text en Copyright © 2022 He, Tan, Liao, Zheng, Lv, Jiang and Xiao https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Oncology He, Quan-Hao Tan, Hao Liao, Fang-Tong Zheng, Yi-Neng Lv, Fa-Jin Jiang, Qing Xiao, Ming-Zhao Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm |
title | Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm |
title_full | Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm |
title_fullStr | Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm |
title_full_unstemmed | Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm |
title_short | Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm |
title_sort | stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble ct machine learning algorithm |
topic | Oncology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9640984/ https://www.ncbi.nlm.nih.gov/pubmed/36387261 http://dx.doi.org/10.3389/fonc.2022.1028577 |
work_keys_str_mv | AT hequanhao stratificationofmalignantrenalneoplasmsfromcysticrenallesionsusingdeeplearningandradiomicsfeaturesbasedonastackingensemblectmachinelearningalgorithm AT tanhao stratificationofmalignantrenalneoplasmsfromcysticrenallesionsusingdeeplearningandradiomicsfeaturesbasedonastackingensemblectmachinelearningalgorithm AT liaofangtong stratificationofmalignantrenalneoplasmsfromcysticrenallesionsusingdeeplearningandradiomicsfeaturesbasedonastackingensemblectmachinelearningalgorithm AT zhengyineng stratificationofmalignantrenalneoplasmsfromcysticrenallesionsusingdeeplearningandradiomicsfeaturesbasedonastackingensemblectmachinelearningalgorithm AT lvfajin stratificationofmalignantrenalneoplasmsfromcysticrenallesionsusingdeeplearningandradiomicsfeaturesbasedonastackingensemblectmachinelearningalgorithm AT jiangqing stratificationofmalignantrenalneoplasmsfromcysticrenallesionsusingdeeplearningandradiomicsfeaturesbasedonastackingensemblectmachinelearningalgorithm AT xiaomingzhao stratificationofmalignantrenalneoplasmsfromcysticrenallesionsusingdeeplearningandradiomicsfeaturesbasedonastackingensemblectmachinelearningalgorithm |