Whole-body uptake classification and prostate cancer staging in 68Ga-PSMA-11 PET/CT using dual-tracer learning

Abstract

Purpose: In PSMA-ligand PET/CT imaging, standardized evaluation frameworks and image-derived parameters are increasingly used to support prostate cancer staging. Clinical applicability remains challenging wherever manual measurements of numerous suspected lesions are required. Deep learning methods are promising for automated image analysis, typically requiring extensive expert-annotated image datasets to reach sufficient accuracy. We developed a deep learning method to support image-based staging, investigating the use of training information from two radiotracers.

Methods: In 173 subjects imaged with ⁶⁸Ga-PSMA-11 PET/CT, divided into development (121) and test (52) sets, we trained and evaluated a convolutional neural network to both classify sites of elevated tracer uptake as nonsuspicious or suspicious for cancer and assign them an anatomical location. We evaluated training strategies to leverage information from a larger dataset of ¹⁸F-FDG PET/CT images and expert annotations, including transfer learning and combined training encoding the tracer type as input to the network. We assessed the agreement between the N and M stage assigned based on the network annotations and expert annotations, according to the PROMISE miTNM framework.

Results: In the development set, including ¹⁸F-FDG training data improved classification performance in four-fold cross validation. In the test set, compared to expert assessment, training with ¹⁸F-FDG data and the development set yielded 80.4% average precision [confidence interval (CI): 71.1-87.8] for identification of suspicious uptake sites, 77% (CI: 70.0-83.4) accuracy for anatomical location classification of suspicious findings, 81% agreement for identification of regional lymph node involvement, and 77% agreement for identification of metastatic stage.

Conclusion: The evaluated algorithm showed good agreement with expert assessment for identification and anatomical location classification of suspicious uptake sites in whole-body ⁶⁸Ga-PSMA-11 PET/CT. With restricted PSMA-ligand data available, the use of training examples from a different radiotracer improved performance. The investigated methods are promising for enabling efficient assessment of cancer stage and tumor burden.

Keywords: Deep learning; PET/CT; PSMA; Prostate cancer; Staging; miTNM.

Fig. 1

Convolutional neural network architecture used for PET uptake classification when training a with data from a single radiotracer and b with data from two radiotracers, encoding the tracer type as input to the network. Multiplanar reformations (MPRs) extracted from a region of interest being classified are represented as exemplar input to the network. In the three-dimensional illustration, numbers along layers’ edges indicate the size of the feature maps resulting as output of the corresponding layers

Fig. 2

Performance obtained for a classification of PET uptake sites as nonsuspicious or suspicious and b classification of their anatomical location, using different strategies to train a convolutional network evaluated with four-fold cross validation on the development set of ⁶⁸Ga-PSMA-11 PET/CT scans. Performance metrics are determined by pooling findings of all subjects together. Error bars indicate the 95% confidence interval obtained via bootstrap resampling at subject level

Fig. 3

a Coronal and d sagittal maximum intensity projections (MIP) of a ⁶⁸Ga-PSMA-11 PET scan for a subject in the test set. b, e Regions of interest classified by the convolutional neural network as suspicious overlayed to the PET MIP in yellow, together with the anatomical location label assigned by the network. c, f Regions of interest identified by an expert physician as suspicious uptake overlayed to the PET MIP in yellow, together with the anatomical location label assigned by the expert