Cargando…

3D vs. 2D MRI radiomics in skeletal Ewing sarcoma: Feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction

OBJECTIVE: The extent of response to neoadjuvant chemotherapy predicts survival in Ewing sarcoma. This study focuses on MRI radiomics of skeletal Ewing sarcoma and aims to investigate feature reproducibility and machine learning prediction of response to neoadjuvant chemotherapy. MATERIALS AND METHO...

Descripción completa

Detalles Bibliográficos
Autores principales: Gitto, Salvatore, Corino, Valentina D. A., Annovazzi, Alessio, Milazzo Machado, Estevāo, Bologna, Marco, Marzorati, Lorenzo, Albano, Domenico, Messina, Carmelo, Serpi, Francesca, Anelli, Vincenzo, Ferraresi, Virginia, Zoccali, Carmine, Aliprandi, Alberto, Parafioriti, Antonina, Luzzati, Alessandro, Biagini, Roberto, Mainardi, Luca, Sconfienza, Luca Maria
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9755864/
https://www.ncbi.nlm.nih.gov/pubmed/36531029
http://dx.doi.org/10.3389/fonc.2022.1016123
_version_ 1784851514907426816
author Gitto, Salvatore
Corino, Valentina D. A.
Annovazzi, Alessio
Milazzo Machado, Estevāo
Bologna, Marco
Marzorati, Lorenzo
Albano, Domenico
Messina, Carmelo
Serpi, Francesca
Anelli, Vincenzo
Ferraresi, Virginia
Zoccali, Carmine
Aliprandi, Alberto
Parafioriti, Antonina
Luzzati, Alessandro
Biagini, Roberto
Mainardi, Luca
Sconfienza, Luca Maria
author_facet Gitto, Salvatore
Corino, Valentina D. A.
Annovazzi, Alessio
Milazzo Machado, Estevāo
Bologna, Marco
Marzorati, Lorenzo
Albano, Domenico
Messina, Carmelo
Serpi, Francesca
Anelli, Vincenzo
Ferraresi, Virginia
Zoccali, Carmine
Aliprandi, Alberto
Parafioriti, Antonina
Luzzati, Alessandro
Biagini, Roberto
Mainardi, Luca
Sconfienza, Luca Maria
author_sort Gitto, Salvatore
collection PubMed
description OBJECTIVE: The extent of response to neoadjuvant chemotherapy predicts survival in Ewing sarcoma. This study focuses on MRI radiomics of skeletal Ewing sarcoma and aims to investigate feature reproducibility and machine learning prediction of response to neoadjuvant chemotherapy. MATERIALS AND METHODS: This retrospective study included thirty patients with biopsy-proven skeletal Ewing sarcoma, who were treated with neoadjuvant chemotherapy before surgery at two tertiary sarcoma centres. 7 patients were poor responders and 23 were good responders based on pathological assessment of the surgical specimen. On pre-treatment T1-weighted and T2-weighted MRI, 2D and 3D tumour segmentations were manually performed. Features were extracted from original and wavelet-transformed images. Feature reproducibility was assessed through small geometrical transformations of the regions of interest mimicking multiple manual delineations, and intraclass correlation coefficient >0.75 defined feature reproducibility. Feature selection also consisted of collinearity and significance analysis. After class balancing in the training cohort, three machine learning classifiers were trained and tested on unseen data using hold-out cross-validation. RESULTS: 1303 (77%) 3D and 620 (65%) 2D radiomic features were reproducible. 4 3D and 4 2D features passed feature selection. Logistic regression built upon 3D features achieved the best performance with 85% accuracy (AUC=0.9) in predicting response to neoadjuvant chemotherapy. CONCLUSION: Compared to 2D approach, 3D MRI radiomics of Ewing sarcoma had superior reproducibility and higher accuracy in predicting response to neoadjuvant chemotherapy, particularly when using logistic regression classifier.
format Online
Article
Text
id pubmed-9755864
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-97558642022-12-17 3D vs. 2D MRI radiomics in skeletal Ewing sarcoma: Feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction Gitto, Salvatore Corino, Valentina D. A. Annovazzi, Alessio Milazzo Machado, Estevāo Bologna, Marco Marzorati, Lorenzo Albano, Domenico Messina, Carmelo Serpi, Francesca Anelli, Vincenzo Ferraresi, Virginia Zoccali, Carmine Aliprandi, Alberto Parafioriti, Antonina Luzzati, Alessandro Biagini, Roberto Mainardi, Luca Sconfienza, Luca Maria Front Oncol Oncology OBJECTIVE: The extent of response to neoadjuvant chemotherapy predicts survival in Ewing sarcoma. This study focuses on MRI radiomics of skeletal Ewing sarcoma and aims to investigate feature reproducibility and machine learning prediction of response to neoadjuvant chemotherapy. MATERIALS AND METHODS: This retrospective study included thirty patients with biopsy-proven skeletal Ewing sarcoma, who were treated with neoadjuvant chemotherapy before surgery at two tertiary sarcoma centres. 7 patients were poor responders and 23 were good responders based on pathological assessment of the surgical specimen. On pre-treatment T1-weighted and T2-weighted MRI, 2D and 3D tumour segmentations were manually performed. Features were extracted from original and wavelet-transformed images. Feature reproducibility was assessed through small geometrical transformations of the regions of interest mimicking multiple manual delineations, and intraclass correlation coefficient >0.75 defined feature reproducibility. Feature selection also consisted of collinearity and significance analysis. After class balancing in the training cohort, three machine learning classifiers were trained and tested on unseen data using hold-out cross-validation. RESULTS: 1303 (77%) 3D and 620 (65%) 2D radiomic features were reproducible. 4 3D and 4 2D features passed feature selection. Logistic regression built upon 3D features achieved the best performance with 85% accuracy (AUC=0.9) in predicting response to neoadjuvant chemotherapy. CONCLUSION: Compared to 2D approach, 3D MRI radiomics of Ewing sarcoma had superior reproducibility and higher accuracy in predicting response to neoadjuvant chemotherapy, particularly when using logistic regression classifier. Frontiers Media S.A. 2022-12-02 /pmc/articles/PMC9755864/ /pubmed/36531029 http://dx.doi.org/10.3389/fonc.2022.1016123 Text en Copyright © 2022 Gitto, Corino, Annovazzi, Milazzo Machado, Bologna, Marzorati, Albano, Messina, Serpi, Anelli, Ferraresi, Zoccali, Aliprandi, Parafioriti, Luzzati, Biagini, Mainardi and Sconfienza 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
Gitto, Salvatore
Corino, Valentina D. A.
Annovazzi, Alessio
Milazzo Machado, Estevāo
Bologna, Marco
Marzorati, Lorenzo
Albano, Domenico
Messina, Carmelo
Serpi, Francesca
Anelli, Vincenzo
Ferraresi, Virginia
Zoccali, Carmine
Aliprandi, Alberto
Parafioriti, Antonina
Luzzati, Alessandro
Biagini, Roberto
Mainardi, Luca
Sconfienza, Luca Maria
3D vs. 2D MRI radiomics in skeletal Ewing sarcoma: Feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction
title 3D vs. 2D MRI radiomics in skeletal Ewing sarcoma: Feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction
title_full 3D vs. 2D MRI radiomics in skeletal Ewing sarcoma: Feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction
title_fullStr 3D vs. 2D MRI radiomics in skeletal Ewing sarcoma: Feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction
title_full_unstemmed 3D vs. 2D MRI radiomics in skeletal Ewing sarcoma: Feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction
title_short 3D vs. 2D MRI radiomics in skeletal Ewing sarcoma: Feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction
title_sort 3d vs. 2d mri radiomics in skeletal ewing sarcoma: feature reproducibility and preliminary machine learning analysis on neoadjuvant chemotherapy response prediction
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9755864/
https://www.ncbi.nlm.nih.gov/pubmed/36531029
http://dx.doi.org/10.3389/fonc.2022.1016123
work_keys_str_mv AT gittosalvatore 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT corinovalentinada 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT annovazzialessio 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT milazzomachadoestevao 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT bolognamarco 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT marzoratilorenzo 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT albanodomenico 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT messinacarmelo 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT serpifrancesca 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT anellivincenzo 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT ferraresivirginia 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT zoccalicarmine 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT aliprandialberto 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT parafioritiantonina 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT luzzatialessandro 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT biaginiroberto 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT mainardiluca 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction
AT sconfienzalucamaria 3dvs2dmriradiomicsinskeletalewingsarcomafeaturereproducibilityandpreliminarymachinelearninganalysisonneoadjuvantchemotherapyresponseprediction