Machine-learned target volume delineation of 18F-FDG PET images after one cycle of induction chemotherapy

Parkinson, Craig ORCID: https://orcid.org/0000-0003-3454-4957, Evans, Mererid, Guerrero-Urbano, Teresa, Michaelidou, Andriana, Pike, Lucy, Barrington, Sally, Jayaprakasam, Vetri, Rackley, Thomas, Palaniappan, Nachi, Staffurth, John ORCID: https://orcid.org/0000-0002-7834-3172, Marshall, Christopher ORCID: https://orcid.org/0000-0002-2228-883X and Spezi, Emiliano ORCID: https://orcid.org/0000-0002-1452-8813 2019. Machine-learned target volume delineation of 18F-FDG PET images after one cycle of induction chemotherapy. Physica Medica, European Journal of Medical Physics 61 , pp. 85-93. 10.1016/j.ejmp.2019.04.020

Preview

PDF - Accepted Post-Print Version Download (579kB) | Preview

Abstract

Biological tumour volume (GTVPET) delineation on 18F-FDG PET acquired during induction chemotherapy (ICT) is challenging due to the reduced metabolic uptake and volume of the GTVPET. Automatic segmentation algorithms applied to 18F-FDG PET (PET-AS) imaging have been used for GTVPET delineation on 18F-FDG PET imaging acquired before ICT. However, their role has not been investigated in 18F-FDG PET imaging acquired after ICT. In this study we investigate PET-AS techniques, including ATLAAS a machine learned method, for accurate delineation of the GTVPET after ICT. Twenty patients were enrolled onto a prospective phase I study (FiGaRO). PET/CT imaging was acquired at baseline and 3 weeks following 1 cycle of induction chemotherapy. The GTVPET was manually delineated by a nuclear medicine physician and clinical oncologist. The resulting GTVPET was used as the reference contour. The ATLAAS original statistical model was expanded to include images of reduced metabolic activity and the ATLAAS algorithm was re-trained on the new reference dataset. Estimated GTVPET contours were derived using sixteen PET-AS methods and compared to the GTVPET using the Dice Similarity Coefficient (DSC). The mean DSC for ATLAAS, 60% Peak Thresholding (PT60), Adaptive Thresholding (AT) and Watershed Thresholding (WT) was 0.72, 0.61, 0.63 and 0.60 respectively. The GTVPET generated by ATLAAS compared favourably with manually delineated volumes and in comparison, to other PET-AS methods, was more accurate for GTVPET delineation after ICT. ATLAAS would be a feasible method to reduce inter-observer variability in multi-centre trials.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Medicine Engineering
Publisher:	Elsevier
ISSN:	1120-1797
Date of First Compliant Deposit:	30 April 2019
Date of Acceptance:	23 April 2019
Last Modified:	15 Nov 2024 00:00
URI:	https://orca.cardiff.ac.uk/id/eprint/121958

Citation Data

Actions (repository staff only)

Edit Item