Analytical performance of aPROMISE: automated anatomic contextualization, detection, and quantification of [18F]DCFPyL (PSMA) imaging for standardized reporting.

PURPOSE: The application of automated image analyses could improve and facilitate standardization and consistency of quantification in [18F]DCFPyL (PSMA) PET/CT scans. In the current study, we analytically validated aPROMISE, a software as a medical device that segments organs in low-dose CT images with deep learning, and subsequently detects and quantifies potential pathological lesions in PSMA PET/CT. METHODS: To evaluate the deep learning algorithm, the automated segmentations of the low-dose CT component of PSMA PET/CT scans from 20 patients were compared to manual segmentations. Dice scores were used to quantify the similarities between the automated and manual segmentations. Next, the automated quantification of tracer uptake in the reference organs and detection and pre-segmentation of potential lesions were evaluated in 339 patients with prostate cancer, who were all enrolled in the phase II/III OSPREY study. Three nuclear medicine physicians performed the retrospective independent reads of OSPREY images with aPROMISE. Quantitative consistency was assessed by the pairwise Pearson correlations and standard deviation between the readers and aPROMISE. The sensitivity of detection and pre-segmentation of potential lesions was evaluated by determining the percent of manually selected abnormal lesions that were automatically detected by aPROMISE. RESULTS: The Dice scores for bone segmentations ranged from 0.88 to 0.95. The Dice scores of the PSMA PET/CT reference organs, thoracic aorta and liver, were 0.89 and 0.97, respectively. Dice scores of other visceral organs, including prostate, were observed to be above 0.79. The Pearson correlation for blood pool reference was higher between any manual reader and aPROMISE, than between any pair of manual readers. The standard deviations of reference organ uptake across all patients as determined by aPROMISE (SD = 0.21 blood pool and SD = 1.16 liver) were lower compared to those of the manual readers. Finally, the sensitivity of aPROMISE detection and pre-segmentation was 91.5% for regional lymph nodes, 90.6% for all lymph nodes, and 86.7% for bone in metastatic patients. CONCLUSION: In this analytical study, we demonstrated the segmentation accuracy of the deep learning algorithm, the consistency in quantitative assessment across multiple readers, and the high sensitivity in detecting potential lesions. The study provides a foundational framework for clinical evaluation of aPROMISE in standardized reporting of PSMA PET/CT.

Validation of 3D finite element models from simulated DXA images for biofidelic simulations of sideways fall impact to the hip.

Computed tomography (CT)-derived finite element (FE) models have been proposed as a tool to improve the current clinical assessment of osteoporosis and personalized hip fracture risk by providing an accurate estimate of femoral strength. However, this solution has two main drawbacks, namely: (i) 3D CT images are needed, whereas 2D dual-energy x-ray absorptiometry (DXA) images are more generally available, and (ii) quasi-static femoral strength is predicted as a surrogate for fracture risk, instead of predicting whether a fall would result in a fracture or not. The aim of this study was to combine a biofidelic fall simulation technique, based on 3D computed tomography (CT) data with an algorithm that reconstructs 3D femoral shape and BMD distribution from a 2D DXA image. This approach was evaluated on 11 pelvis-femur constructs for which CT scans, ex vivo sideways fall impact experiments and CT-derived biofidelic FE models were available. Simulated DXA images were used to reconstruct the 3D shape and bone mineral density (BMD) distribution of the left femurs by registering a projection of a statistical shape and appearance model with a genetic optimization algorithm. The 2D-to-3D reconstructed femurs were meshed, and the resulting FE models inserted into a biofidelic FE modeling pipeline for simulating a sideways fall. The median 2D-to-3D reconstruction error was 1.02 mm for the shape and 0.06 g/cm3 for BMD for the 11 specimens. FE models derived from simulated DXAs predicted the outcome of the falls in terms of fracture versus non-fracture with the same accuracy as the CT-derived FE models. This study represents a milestone towards improved assessment of hip fracture risk based on widely available clinical DXA images.