Fully automatic prognostic biomarker extraction from metastatic prostate lesion segmentations in whole-body [68Ga]Ga-PSMA-11 PET/CT images

Abstract

Purpose This study aimed to develop and assess an automated segmentation framework based on deep learning for metastatic prostate cancer (mPCa) lesions in whole-body [68Ga]Ga-PSMA-11 PET/CT images for the purpose of extracting patient-level prognostic biomarkers. Methods Three hundred thirty-seven [68Ga]Ga-PSMA-11 PET/CT images were retrieved from a cohort of biochemically recurrent PCa patients. A fully 3D convolutional neural network (CNN) is proposed which is based on the self-configuring nnU-Net framework, and was trained on a subset of these scans, with an independent test set reserved for model evaluation. Voxel-level segmentation results were assessed using the dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity. Sensitivity and PPV were calculated to assess lesion level detection; patient-level classification results were assessed by the accuracy, PPV, and sensitivity. Whole-body biomarkers total lesional volume (TLVauto) and total lesional uptake (TLUauto) were calculated from the automated segmentations, and Kaplan–Meier analysis was used to assess biomarker relationship with patient overall survival. Results At the patient level, the accuracy, sensitivity, and PPV were all > 90%, with the best metric being the PPV (97.2%). PPV and sensitivity at the lesion level were 88.2% and 73.0%, respectively. DSC and PPV measured at the voxel level performed within measured inter-observer variability (DSC, median = 50.7% vs. second observer = 32%, p = 0.012; PPV, median = 64.9% vs. second observer = 25.7%, p < 0.005). Kaplan–Meier analysis of TLVauto and TLUauto showed they were significantly associated with patient overall survival (both p < 0.005). Conclusion The fully automated assessment of whole-body [68Ga]Ga-PSMA-11 PET/CT images using deep learning shows significant promise, yielding accurate scan classification, voxel-level segmentations within inter-observer variability, and potentially clinically useful prognostic biomarkers associated with patient overall survival. Trial registration This study was registered with the Australian New Zealand Clinical Trials Registry (ACTRN12615000608561) on 11 June 2015.

A review of artificial intelligence in prostate cancer detection on imaging

“…One such modality is Gallium-68 PSMA-11 PET-CT scans. 204 Recent studies demonstrate that PSMA PET-CT scans can significantly improve prostate cancer detection and treatment planning, are more accurate than conventional imaging with CT and bone scanning, 205 add value to MRI for diagnosis, 206 and may enable better prediction of pre-operative pathological outcomes than MRI.207–209 There is an opportunity for AI to address shortcomings of these new imaging modalities, but due to its recent FDA approval, only a few published AI models 32 , 210 , 211 exist for prostate cancer detection using PSMA PET currently.…”

Automated quantification of PET/CT skeletal tumor burden in prostate cancer using artificial intelligence: The PET index

“…Quantitative assessment of tumor burden in patients scheduled for PSMA-directed radioligand therapies could also be used for personalized dosimetry. Further, prognostic information may be obtained through the assessment of tumor burden in patients with advanced PCa [ 10 , 20 , 34 ]. An AI-based model for quantification of tumor burden in PET/CT has a potential to risk-stratify patients with metastatic PCa, and to provide potentially prognostic and predictive information in the clinic.…”

“…The majority of these methods require drawing volumes of interest to encompass regions of suspicious uptake and manual exclusion of uptake unrelated to bone metastases, making them labor-intensive and subject to individual interpretation despite their semi-automated feature. However, recent leaps forward in methodology include fully automated convolutional neural network (CNN)-based quantification of whole-body tumor burden in PSMA PET/CT [ 19 , 20 ].…”

A Systematic Review on Artificial Intelligence Evaluating Metastatic Prostatic Cancer and Lymph Nodes on PSMA PET Scans

“…Of the 11 included studies, only one study by Kendrick et al [25] was prospective, the remaining 10 were retrospective in nature (see Table 1). Tracers being used were 18 F-PSMA (n = 5) and 68 Ga-PSMA (n = 6).…”

“…The mean STREAM-URO score of the 11 studies was 21 out of 28 (see Figure 2). The main areas where studies scored the least were cohort characteristic (n = 4) as only four studies described the age and PSA of the included patients [24][25][26]33] and eligibility criteria (n = 1) as only one of the included studies described their exclusion criteria [33].…”