Adaptive threshold segmentation of pituitary adenomas from FDG PET images for radiosurgery

Abstract

In this study we have attempted to optimize a PET based adaptive threshold segmentation method for delineating small tumors, particularly in a background of high tracer activity. The metabolic nature of pituitary adenomas and the constraints of MRI imaging in the postoperative setting to delineate these tumors during radiosurgical procedures motivated us to develop this method. Phantom experiments were done to establish a relationship between the threshold required for segmenting the PET images and the target size and the activity concentration within the target in relation to its background. The threshold was developed from multiple linear regression of the experimental data optimized for tumor sizes less than 4 cm3. We validated our method against the phantom target volumes with measured target to background ratios ranging from 1.6 to 14.58. The method was tested on ten retrospective patients with residual growth hormone‐secreting pituitary adenomas that underwent radiosurgery and compared against the volumes delineated by manual method. The predicted volumes against the true volume of the phantom inserts gave a correlation coefficient of 99% (p<0.01). In the ten retrospective patients, the automatically segmented tumor volumes against volumes manually delineated by the clinicians had a correlation of 94% (p<0.01). This adaptive threshold segmentation showed promising results in delineating tumor volumes in pituitary adenomas planned for stereotactic radiosurgery, particularly in the postoperative setting where MR and CT images may be associated with artifacts, provided optimization experiment is carried out.PACS number: 87.57.nm, 87.57.uk

Hybrid positron emission tomography segmentation of heterogeneous lung tumors using 3D Slicer: improved GrowCut algorithm with threshold initialization

“…Intuitively, since FDG PET images show substantial contrast in glucose utilization between normal tissue and neoplastic tissue, threshold-based segmentation is one of the easier methods to adopt and implement. 20,28,[30][31][32] However, most threshold methods (T 25 and T 40 ) fail to identify a single threshold that includes the entire tumor in the presence of pronounced heterogeneities. 7 To overcome this methodological shortcoming, we used the interactive GrowCut algorithm implemented in the 3D Slicer.…”

“…Instead, this work was aimed at being simple and clinically implementable using widely used 3D Slicer software. 25,34 A detailed investigation of ways to improve the definition of the background, which was the limiting factor in our previous work, 28 led to the idea of the automated background. From our extended use of the method, we found that the background shell all around the tumor provided ample information about the tissue surrounding the tumor instead of random spheres to estimate the representative uptake values in the background.…”

“…A detailed description of similar phantom measurements has been described in our earlier work. 28 The initial estimate volume for the adaptive threshold was obtained from T 25 threshold. The tracer uptake ratio in the source and background was obtained from the T 25 defined contour and the 3-D shell background, respectively.…”

Medical Image Segmentation Using Improved Chan-Vese Model

“…So far, thousands of segmentation algorithms have been developed, for which numerous classification methods have been proposed. The traditional image segmentation methods can be classified into the following four classes: (1) threshold-based method [1,2]; (2) edge-based method [3,4]; (3) regionbased method [5,6]; and (4) specific theory-based method [7]. With the development of the artificial neural network, such as fuzzy set theory and graph theory, some novel segmentation algorithms have been proposed in combination with these theories [8][9][10].…”

Utility of 13N-Ammonia PET/CT to Detect Pituitary Tissue in Patients with Pituitary Adenomas

“…18 F-FDG appears to be poorly trapped in pituitary tissue in patients with PAs (14). PET imaging of patients with PAs have been used for radiosurgery planning (18,19). So it is essential to detect pituitary tissue in PET to avoid damaging pituitary tissue.…”