Decision-support for treatment with 177Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters

Sobhan Moazemi, Annette Erle, Susanne Lütje, Michael Muders, Markus Essler, Thomas Schultz, and Ralph A. Bundschuh
In: Annals of Translational Medicine (May 2021), 9:9(818)
 

Abstract

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 177Lu-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 (PETMin, PETCorrelation, CTMin, CTBusyness and CTCoarseness) 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 68Ga-PSMA PET/CT radiomics features holds promise for the prediction of response to 177Lu-PSMA treatment, given only base-line 68Ga-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.

Keywords: Prostate cancer (PC); prostate specific membrane antigen (PSMA); positron emission tomography (PET); computed tomography (CT); machine learning (ML)

Images

Bibtex

@ARTICLE{Moazemi:ATM2021,
    author = {Moazemi, Sobhan and Erle, Annette and L{\"u}tje, Susanne and Muders, Michael and Essler, Markus and
              Schultz, Thomas and Bundschuh, Ralph A.},
     pages = {818},
     title = {Decision-support for  treatment with 177Lu-PSMA: machine learning predicts response with high
              accuracy  based on PSMA-PET/CT and clinical parameters},
   journal = {Annals of Translational Medicine},
    volume = {9},
    number = {9},
      year = {2021},
     month = may,
  abstract = {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 177Lu-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 68Ga-PSMA PET/CT radiomics features holds promise for the
              prediction of response to 177Lu-PSMA treatment, given only base-line 68Ga-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.
              
              Keywords: Prostate cancer (PC); prostate specific membrane antigen (PSMA); positron emission
              tomography (PET); computed tomography (CT); machine learning (ML)},
       doi = {10.21037/atm-20-6446}
}