Cargando…
Applying Radiomics to Predict Pathology of Postchemotherapy Retroperitoneal Nodal Masses in Germ Cell Tumors
PURPOSE: After chemotherapy, approximately 50% of patients with metastatic testicular germ cell tumors (GCTs) who undergo retroperitoneal lymph node dissections (RPNLDs) for residual masses have fibrosis. Radiomics uses image processing techniques to extract quantitative textures/features from regio...
Autores principales: | , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Society of Clinical Oncology
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6874033/ https://www.ncbi.nlm.nih.gov/pubmed/30652572 http://dx.doi.org/10.1200/CCI.18.00004 |
_version_ | 1783472765057105920 |
---|---|
author | Lewin, Jeremy Dufort, Paul Halankar, Jaydeep O’Malley, Martin Jewett, Michael A.S. Hamilton, Robert J. Gupta, Abha Lorenzo, Armando Traubici, Jeffrey Nayan, Madhur Leão, Ricardo Warde, Padraig Chung, Peter Anson Cartwright, Lynn Sweet, Joan Hansen, Aaron R. Metser, Ur Bedard, Philippe L. |
author_facet | Lewin, Jeremy Dufort, Paul Halankar, Jaydeep O’Malley, Martin Jewett, Michael A.S. Hamilton, Robert J. Gupta, Abha Lorenzo, Armando Traubici, Jeffrey Nayan, Madhur Leão, Ricardo Warde, Padraig Chung, Peter Anson Cartwright, Lynn Sweet, Joan Hansen, Aaron R. Metser, Ur Bedard, Philippe L. |
author_sort | Lewin, Jeremy |
collection | PubMed |
description | PURPOSE: After chemotherapy, approximately 50% of patients with metastatic testicular germ cell tumors (GCTs) who undergo retroperitoneal lymph node dissections (RPNLDs) for residual masses have fibrosis. Radiomics uses image processing techniques to extract quantitative textures/features from regions of interest (ROIs) to train a classifier that predicts outcomes. We hypothesized that radiomics would identify patients with a high likelihood of fibrosis who may avoid RPLND. PATIENTS AND METHODS: Patients with GCT who had an RPLND for nodal masses > 1 cm after first-line platinum chemotherapy were included. Preoperative contrast-enhanced axial computed tomography images of retroperitoneal ROIs were manually contoured. Radiomics features (n = 153) were used to train a radial basis function support vector machine classifier to discriminate between viable GCT/mature teratoma versus fibrosis. A nested 10-fold cross-validation protocol was used to determine classifier accuracy. Clinical variables/restricted size criteria were used to optimize the classifier. RESULTS: Seventy-seven patients with 102 ROIs were analyzed (GCT, 21; teratoma, 41; fibrosis, 40). The discriminative accuracy of radiomics to identify GCT/teratoma versus fibrosis was 72 ± 2.2% (area under the curve [AUC], 0.74 ± 0.028); sensitivity was 56.2 ± 15.0%, and specificity was 81.9 ± 9.0% (P = .001). No major predictive differences were identified when data were restricted by varying maximal axial diameters (AUC range, 0.58 ± 0.05 to 0.74 ± 0.03). The prediction algorithm using clinical variables alone identified an AUC of 0.76. When these variables were added to the radiomics signature, the best performing classifier was identified when axial masses were limited to diameter < 2 cm (accuracy, 88.2 ± 4.4; AUC, 0.80 ± 0.05; P = .02). CONCLUSION: A predictive radiomics algorithm had a discriminative accuracy of 72% that improved to 88% when combined with clinical predictors. Additional independent validation is required to assess whether radiomics allows patients with a high predicted likelihood of fibrosis to avoid RPLND. |
format | Online Article Text |
id | pubmed-6874033 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | American Society of Clinical Oncology |
record_format | MEDLINE/PubMed |
spelling | pubmed-68740332019-12-03 Applying Radiomics to Predict Pathology of Postchemotherapy Retroperitoneal Nodal Masses in Germ Cell Tumors Lewin, Jeremy Dufort, Paul Halankar, Jaydeep O’Malley, Martin Jewett, Michael A.S. Hamilton, Robert J. Gupta, Abha Lorenzo, Armando Traubici, Jeffrey Nayan, Madhur Leão, Ricardo Warde, Padraig Chung, Peter Anson Cartwright, Lynn Sweet, Joan Hansen, Aaron R. Metser, Ur Bedard, Philippe L. JCO Clin Cancer Inform Original Report PURPOSE: After chemotherapy, approximately 50% of patients with metastatic testicular germ cell tumors (GCTs) who undergo retroperitoneal lymph node dissections (RPNLDs) for residual masses have fibrosis. Radiomics uses image processing techniques to extract quantitative textures/features from regions of interest (ROIs) to train a classifier that predicts outcomes. We hypothesized that radiomics would identify patients with a high likelihood of fibrosis who may avoid RPLND. PATIENTS AND METHODS: Patients with GCT who had an RPLND for nodal masses > 1 cm after first-line platinum chemotherapy were included. Preoperative contrast-enhanced axial computed tomography images of retroperitoneal ROIs were manually contoured. Radiomics features (n = 153) were used to train a radial basis function support vector machine classifier to discriminate between viable GCT/mature teratoma versus fibrosis. A nested 10-fold cross-validation protocol was used to determine classifier accuracy. Clinical variables/restricted size criteria were used to optimize the classifier. RESULTS: Seventy-seven patients with 102 ROIs were analyzed (GCT, 21; teratoma, 41; fibrosis, 40). The discriminative accuracy of radiomics to identify GCT/teratoma versus fibrosis was 72 ± 2.2% (area under the curve [AUC], 0.74 ± 0.028); sensitivity was 56.2 ± 15.0%, and specificity was 81.9 ± 9.0% (P = .001). No major predictive differences were identified when data were restricted by varying maximal axial diameters (AUC range, 0.58 ± 0.05 to 0.74 ± 0.03). The prediction algorithm using clinical variables alone identified an AUC of 0.76. When these variables were added to the radiomics signature, the best performing classifier was identified when axial masses were limited to diameter < 2 cm (accuracy, 88.2 ± 4.4; AUC, 0.80 ± 0.05; P = .02). CONCLUSION: A predictive radiomics algorithm had a discriminative accuracy of 72% that improved to 88% when combined with clinical predictors. Additional independent validation is required to assess whether radiomics allows patients with a high predicted likelihood of fibrosis to avoid RPLND. American Society of Clinical Oncology 2018-05-11 /pmc/articles/PMC6874033/ /pubmed/30652572 http://dx.doi.org/10.1200/CCI.18.00004 Text en © 2018 by American Society of Clinical Oncology https://creativecommons.org/licenses/by/4.0/ Licensed under the Creative Commons Attribution 4.0 License: https://creativecommons.org/licenses/by/4.0/ |
spellingShingle | Original Report Lewin, Jeremy Dufort, Paul Halankar, Jaydeep O’Malley, Martin Jewett, Michael A.S. Hamilton, Robert J. Gupta, Abha Lorenzo, Armando Traubici, Jeffrey Nayan, Madhur Leão, Ricardo Warde, Padraig Chung, Peter Anson Cartwright, Lynn Sweet, Joan Hansen, Aaron R. Metser, Ur Bedard, Philippe L. Applying Radiomics to Predict Pathology of Postchemotherapy Retroperitoneal Nodal Masses in Germ Cell Tumors |
title | Applying Radiomics to Predict Pathology of Postchemotherapy Retroperitoneal Nodal Masses in Germ Cell Tumors |
title_full | Applying Radiomics to Predict Pathology of Postchemotherapy Retroperitoneal Nodal Masses in Germ Cell Tumors |
title_fullStr | Applying Radiomics to Predict Pathology of Postchemotherapy Retroperitoneal Nodal Masses in Germ Cell Tumors |
title_full_unstemmed | Applying Radiomics to Predict Pathology of Postchemotherapy Retroperitoneal Nodal Masses in Germ Cell Tumors |
title_short | Applying Radiomics to Predict Pathology of Postchemotherapy Retroperitoneal Nodal Masses in Germ Cell Tumors |
title_sort | applying radiomics to predict pathology of postchemotherapy retroperitoneal nodal masses in germ cell tumors |
topic | Original Report |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6874033/ https://www.ncbi.nlm.nih.gov/pubmed/30652572 http://dx.doi.org/10.1200/CCI.18.00004 |
work_keys_str_mv | AT lewinjeremy applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT dufortpaul applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT halankarjaydeep applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT omalleymartin applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT jewettmichaelas applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT hamiltonrobertj applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT guptaabha applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT lorenzoarmando applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT traubicijeffrey applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT nayanmadhur applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT leaoricardo applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT wardepadraig applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT chungpeter applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT ansoncartwrightlynn applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT sweetjoan applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT hansenaaronr applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT metserur applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors AT bedardphilippel applyingradiomicstopredictpathologyofpostchemotherapyretroperitonealnodalmassesingermcelltumors |