Short Acquisition Time PET/MR Pharmacokinetic Modelling Using CNNs

Scott, Catherine J.; Jiao, Jieqing; Cardoso, M. Jorge; Kläser, Kerstin; Melbourne, Andrew; Markiewicz, Paweł; Schott, Jonathan M.; Hutton, Brian F.; Ourselin, Sébastien

doi:10.1007/978-3-030-00928-1_6

Cited by 5 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model was trained to predict the SPECT perfusion image from the 0% and 50% phases of the 4DCT. The performance of this model in small datasets as compared with other models such as U-net and the efficiency of residual connections have been explored in our prior publication on another CT-based imaging task (Porter et al 2020b), with additional publications demonstrating state-of-the-art results specifically in synthetic imaging tasks (Scott et al 2018, Poirot et al 2019.…”

Section: Model Design and Trainingmentioning

confidence: 99%

Synthetic pulmonary perfusion images from 4DCT for functional avoidance using deep learning

et al. 2021

View full text Add to dashboard Cite

Purpose. To develop and evaluate the performance of a deep learning model to generate synthetic pulmonary perfusion images from clinical 4DCT images for patients undergoing radiotherapy for lung cancer. Methods. A clinical data set of 58 pre- and post-radiotherapy 99mTc-labeled MAA-SPECT perfusion studies (32 patients) each with contemporaneous 4DCT studies was collected. Using the inhale and exhale phases of the 4DCT, a 3D-residual network was trained to create synthetic perfusion images utilizing the MAA-SPECT as ground truth. The training process was repeated for a 50-imaging study, five-fold validation with twenty model instances trained per fold. The highest performing model instance from each fold was selected for inference upon the eight-study test set. A manual lung segmentation was used to compute correlation metrics constrained to the voxels within the lungs. From the pre-treatment test cases (N = 5), 50th percentile contours of well-perfused lung were generated from both the clinical and synthetic perfusion images and the agreement was quantified. Results. Across the hold-out test set, our deep learning model predicted perfusion with a Spearman correlation coefficient of 0.70 (IQR: 0.61–0.76) and a Pearson correlation coefficient of 0.66 (IQR: 0.49–0.73). The agreement of the functional avoidance contour pairs was Dice of 0.803 (IQR: 0.750–0.810) and average surface distance of 5.92 mm (IQR: 5.68–7.55). Conclusion. We demonstrate that from 4DCT alone, a deep learning model can generate synthetic perfusion images with potential application in functional avoidance treatment planning.

show abstract

Section: Model Design and Trainingmentioning

confidence: 99%