Cargando…
Decision-support for treatment with (177)Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters
BACKGROUND: Treatment with radiolabeled ligands to prostate-specific membrane antigen (PSMA) is gaining importance in the treatment of patients with advanced prostate carcinoma. Previous imaging with positron emission tomography/computed tomography (PET/CT) is mandatory. The aim of this study was to...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
AME Publishing Company
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8246232/ https://www.ncbi.nlm.nih.gov/pubmed/34268431 http://dx.doi.org/10.21037/atm-20-6446 |
_version_ | 1783716272117121024 |
---|---|
author | Moazemi, Sobhan Erle, Annette Khurshid, Zain Lütje, Susanne Muders, Michael Essler, Markus Schultz, Thomas Bundschuh, Ralph A. |
author_facet | Moazemi, Sobhan Erle, Annette Khurshid, Zain Lütje, Susanne Muders, Michael Essler, Markus Schultz, Thomas Bundschuh, Ralph A. |
author_sort | Moazemi, Sobhan |
collection | PubMed |
description | BACKGROUND: Treatment with radiolabeled ligands to prostate-specific membrane antigen (PSMA) is gaining importance in the treatment of patients with advanced prostate carcinoma. Previous imaging with positron emission tomography/computed tomography (PET/CT) is mandatory. The aim of this study was to investigate the role of radiomics features in PSMA-PET/CT scans and clinical parameters to predict response to (177)Lu-PSMA treatment given just baseline PSMA scans using state-of-the-art machine learning (ML) methods. METHODS: A total of 2,070 pathological hotspots annotated in 83 prostate cancer patients undergoing PSMA therapy were analyzed. Two main tasks are performed: (I) analyzing correlation of averaged (per patient) values of radiomics features of individual hotspots and clinical parameters with difference in prostate specific antigen levels (ΔPSA) in pre- and post-therapy as a therapy response indicator. (II) ML-based classification of patients into responders and non-responders based on averaged features values and clinical parameters. To achieve this, machine learning (ML) algorithms and linear regression tests are applied. Grid search, cross validation (CV) and permutation test were performed to assure that the results were significant. RESULTS: Radiomics features (PET_Min, PET_Correlation, CT_Min, CT_Busyness and CT_Coarseness) and clinical parameters such as Alp1 and Gleason score showed best correlations with ΔPSA. For the treatment response prediction task, 80% area under the curve (AUC), 75% sensitivity (SE), and 75% specificity (SP) were obtained, applying ML support vector machine (SVM) classifier with radial basis function (RBF) kernel on a selection of radiomics features and clinical parameters with strong correlations with ΔPSA. CONCLUSIONS: Machine learning based on (68)Ga-PSMA PET/CT radiomics features holds promise for the prediction of response to (177)Lu-PSMA treatment, given only base-line (68)Ga-PSMA scan. In addition, it was shown that, the best correlating set of radiomics features with ΔPSA are superior to clinical parameters for this therapy response prediction task using ML classifiers. |
format | Online Article Text |
id | pubmed-8246232 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | AME Publishing Company |
record_format | MEDLINE/PubMed |
spelling | pubmed-82462322021-07-14 Decision-support for treatment with (177)Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters Moazemi, Sobhan Erle, Annette Khurshid, Zain Lütje, Susanne Muders, Michael Essler, Markus Schultz, Thomas Bundschuh, Ralph A. Ann Transl Med Original Article on Artificial Intelligence in Molecular Imaging BACKGROUND: Treatment with radiolabeled ligands to prostate-specific membrane antigen (PSMA) is gaining importance in the treatment of patients with advanced prostate carcinoma. Previous imaging with positron emission tomography/computed tomography (PET/CT) is mandatory. The aim of this study was to investigate the role of radiomics features in PSMA-PET/CT scans and clinical parameters to predict response to (177)Lu-PSMA treatment given just baseline PSMA scans using state-of-the-art machine learning (ML) methods. METHODS: A total of 2,070 pathological hotspots annotated in 83 prostate cancer patients undergoing PSMA therapy were analyzed. Two main tasks are performed: (I) analyzing correlation of averaged (per patient) values of radiomics features of individual hotspots and clinical parameters with difference in prostate specific antigen levels (ΔPSA) in pre- and post-therapy as a therapy response indicator. (II) ML-based classification of patients into responders and non-responders based on averaged features values and clinical parameters. To achieve this, machine learning (ML) algorithms and linear regression tests are applied. Grid search, cross validation (CV) and permutation test were performed to assure that the results were significant. RESULTS: Radiomics features (PET_Min, PET_Correlation, CT_Min, CT_Busyness and CT_Coarseness) and clinical parameters such as Alp1 and Gleason score showed best correlations with ΔPSA. For the treatment response prediction task, 80% area under the curve (AUC), 75% sensitivity (SE), and 75% specificity (SP) were obtained, applying ML support vector machine (SVM) classifier with radial basis function (RBF) kernel on a selection of radiomics features and clinical parameters with strong correlations with ΔPSA. CONCLUSIONS: Machine learning based on (68)Ga-PSMA PET/CT radiomics features holds promise for the prediction of response to (177)Lu-PSMA treatment, given only base-line (68)Ga-PSMA scan. In addition, it was shown that, the best correlating set of radiomics features with ΔPSA are superior to clinical parameters for this therapy response prediction task using ML classifiers. AME Publishing Company 2021-05 /pmc/articles/PMC8246232/ /pubmed/34268431 http://dx.doi.org/10.21037/atm-20-6446 Text en 2021 Annals of Translational Medicine. All rights reserved. https://creativecommons.org/licenses/by-nc-nd/4.0/Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0 (https://creativecommons.org/licenses/by-nc-nd/4.0/) . |
spellingShingle | Original Article on Artificial Intelligence in Molecular Imaging Moazemi, Sobhan Erle, Annette Khurshid, Zain Lütje, Susanne Muders, Michael Essler, Markus Schultz, Thomas Bundschuh, Ralph A. Decision-support for treatment with (177)Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters |
title | Decision-support for treatment with (177)Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters |
title_full | Decision-support for treatment with (177)Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters |
title_fullStr | Decision-support for treatment with (177)Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters |
title_full_unstemmed | Decision-support for treatment with (177)Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters |
title_short | Decision-support for treatment with (177)Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters |
title_sort | decision-support for treatment with (177)lu-psma: machine learning predicts response with high accuracy based on psma-pet/ct and clinical parameters |
topic | Original Article on Artificial Intelligence in Molecular Imaging |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8246232/ https://www.ncbi.nlm.nih.gov/pubmed/34268431 http://dx.doi.org/10.21037/atm-20-6446 |
work_keys_str_mv | AT moazemisobhan decisionsupportfortreatmentwith177lupsmamachinelearningpredictsresponsewithhighaccuracybasedonpsmapetctandclinicalparameters AT erleannette decisionsupportfortreatmentwith177lupsmamachinelearningpredictsresponsewithhighaccuracybasedonpsmapetctandclinicalparameters AT khurshidzain decisionsupportfortreatmentwith177lupsmamachinelearningpredictsresponsewithhighaccuracybasedonpsmapetctandclinicalparameters AT lutjesusanne decisionsupportfortreatmentwith177lupsmamachinelearningpredictsresponsewithhighaccuracybasedonpsmapetctandclinicalparameters AT mudersmichael decisionsupportfortreatmentwith177lupsmamachinelearningpredictsresponsewithhighaccuracybasedonpsmapetctandclinicalparameters AT esslermarkus decisionsupportfortreatmentwith177lupsmamachinelearningpredictsresponsewithhighaccuracybasedonpsmapetctandclinicalparameters AT schultzthomas decisionsupportfortreatmentwith177lupsmamachinelearningpredictsresponsewithhighaccuracybasedonpsmapetctandclinicalparameters AT bundschuhralpha decisionsupportfortreatmentwith177lupsmamachinelearningpredictsresponsewithhighaccuracybasedonpsmapetctandclinicalparameters |