Adaptive region-growing with maximum curvature strategy for tumor segmentation in (18)F-FDG PET Journal Article
| Authors: | Tan, S.; Li, L.; Choi, W.; Kang, M. K.; D'Souza, W. D.; Lu, W. |
| Article Title: | Adaptive region-growing with maximum curvature strategy for tumor segmentation in (18)F-FDG PET |
| Abstract: | Accurate tumor segmentation in PET is crucial in many oncology applications. We developed an adaptive region-growing (ARG) algorithm with a maximum curvature strategy (ARG-MC) for tumor segmentation in PET. The ARG-MC repeatedly applied a confidence connected region-growing algorithm with increasing relaxing factor f. The optimal relaxing factor (ORF) was then determined at the transition point on the f-volume curve, where the volume just grew from the tumor into the surrounding normal tissues. The ARG-MC along with five widely used algorithms were tested on a phantom with 6 spheres at different signal to background ratios and on two clinic datasets including 20 patients with esophageal cancer and 11 patients with non-Hodgkin lymphoma (NHL). The ARG-MC did not require any phantom calibration or any a priori knowledge of the tumor or PET scanner. The identified ORF varied with tumor types (mean ORF = 9.61, 3.78 and 2.55 respectively for the phantom, esophageal cancer, and NHL datasets), and varied from one tumor to another. For the phantom, the ARG-MC ranked the second in segmentation accuracy with an average Dice similarity index (DSI) of 0.86, only slightly worse than Daisne's adaptive thresholding method (DSI = 0.87), which required phantom calibration. For both the esophageal cancer dataset and the NHL dataset, the ARG-MC had the highest accuracy with an average DSI of 0.87 and 0.84, respectively. The ARG-MC was robust to parameter settings and region of interest selection, and it did not depend on scanners, imaging protocols, or tumor types. Furthermore, the ARG-MC made no assumption about the tumor size or tumor uptake distribution, making it suitable for segmenting tumors with heterogeneous FDG uptake. In conclusion, the ARG-MC was accurate, robust and easy to use, it provides a highly potential tool for PET tumor segmentation in clinic. © 2017 Institute of Physics and Engineering in Medicine. |
| Keywords: | scanning; positron emission tomography; calibration; oncology; medical imaging; tumors; segmentation; diseases; non-hodgkin lymphoma; image segmentation; fdg pet; 18f-fdg pet; adaptive thresholding; adaptive region growing; f-volume curve; local maximum curvature; optimal relaxing factor; local maximum; segmentation accuracy; signal-to-background ratio |
| Journal Title: | Physics in Medicine and Biology |
| Volume: | 62 |
| Issue: | 13 |
| ISSN: | 0031-9155 |
| Publisher: | IOP Publishing Ltd |
| Date Published: | 2017-07-07 |
| Start Page: | 5383 |
| End Page: | 5402 |
| Language: | English |
| DOI: | 10.1088/1361-6560/aa6e20 |
| PROVIDER: | scopus |
| PUBMED: | 28604372 |
| PMCID: | PMC5497763 |
| DOI/URL: | |
| Notes: | Article -- Export Date: 3 July 2017 -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
Related MSK Work