Continued therapeutic gain in the treatment of non-small-cell lung cancer (NSCLC) will depend upon our ability to escalate the dose to the primary tumour while minimizing normal tissue toxicity. Both these objectives are facilitated by the accurate definition of a target volume that is as small as possible. To this end, both tumour immobilizations via deep inspiratory breath-hold, along with positron emission tomography (PET), have emerged as two promising approaches. Though PET is an excellent means of defining the general location of a tumour focus, its ability to define exactly the geometric extent of such a focus strongly depends upon selection of an appropriate image threshold. However, in clinical practice, the image threshold is typically not chosen according to consistent, well-established criteria. This study explores the relationship between image threshold and the resultant PET-defined volume using a series of F-18 radiotracer-filled hollow spheres of known internal volumes, both static and under oscillatory motion. The effects of both image threshold and tumour motion on the resultant PET image are examined. Imaging data are further collected from a series of simulated gated PET acquisitions in order to test the feasibility of a patient-controlled gating mechanism during deep inspiratory breath-hold. This study illustrates quantitatively considerable variability in resultant PET-defined tumour volumes depending upon numerous factors, including image threshold, size of the lesion, the presence of tumour motion and the scanning protocol. In this regard, when using PET in treatment planning for NSCLC, the radiation oncologist must select the image threshold very carefully to avoid either under-dosing the tumour or overdosing normal tissues.
PET-derived volumes of NSCLC must be interpreted with caution. The data presented in this study may be used to guide the selection of appropriate image thresholds for potential clinical application.
We applied a learning methodology framework to assist in the threshold-based segmentation of non-small-cell lung cancer (nsclc) tumours in positron-emission tomography–computed tomography (pet–ct) imaging for use in radiotherapy planning. Gated and standard free-breathing studies of two patients were independently analysed (four studies in total). Each study had a pet–ct and a treatment-planning ct image. The reference gross tumour volume (gtv) was identified by two experienced radiation oncologists who also determined reference standardized uptake value (suv) thresholds that most closely approximated the gtv contour on each slice. A set of uptake distribution-related attributes was calculated for each pet slice. A machine learning algorithm was trained on a subset of the pet slices to cope with slice-to-slice variation in the optimal suv threshold: that is, to predict the most appropriate suv threshold from the calculated attributes for each slice. The algorithm’s performance was evaluated using the remainder of the pet slices. A high degree of geometric similarity was achieved between the areas outlined by the predicted and the reference suv thresholds (Jaccard index exceeding 0.82). No significant difference was found between the gated and the free-breathing results in the same patient. In this preliminary work, we demonstrated the potential applicability of a machine learning methodology as an auxiliary tool for radiation treatment planning in nsclc.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.