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

Authors

Evan M. Porter, Beaumont Health
Nicholas K. Myziuk, Beaumont Health
Thomas J. Quinn, Beaumont Health
Daniela Lozano, Oakland University William Beaumont School of Medicine Medical Student
Avery B. Peterson
Duyen M. Quach, Oakland University William Beaumont School of Medicine Medical Student
Zaid A. Siddiqui, Beaumont Health Resident
Thomas M. Guerrero, Beaumont Health

Document Type

Article

Publication Date

8-23-2021

Publication Title

Physics in medicine and biology

Abstract

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-radiotherapy99mTc-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.

Volume

66

Issue

17

Recommended Citation

Porter EM, Myziuk NK, Quinn TJ, Lozano D, Peterson AB, Quach DM, Siddiqui ZA, Guerrero TM. Synthetic pulmonary perfusion images from 4DCT for functional avoidance using deep learning. Phys Med Biol. 2021 Aug 23;66(17). doi: 10.1088/1361-6560/ac16ec. PMID: 34293726.

DOI

10.1088/1361-6560/ac16ec

ISSN

1361-6560

PubMed ID

34293726