Lung tumor segmentation in PET images using graph cuts.

The aim of segmentation of tumor regions in positron emission tomography (PET) is to provide more accurate measurements of tumor size and extension into adjacent structures, than is possible with visual assessment alone and hence improve patient management decisions. We propose a segmentation energy function for the graph cuts technique to improve lung tumor segmentation with PET. Our segmentation energy is based on an analysis of the tumor voxels in PET images combined with a standardized uptake value (SUV) cost function and a monotonic downhill SUV feature. The monotonic downhill feature avoids segmentation leakage into surrounding tissues with similar or higher PET tracer uptake than the tumor and the SUV cost function improves the boundary definition and also addresses situations where the lung tumor is heterogeneous. We evaluated the method in 42 clinical PET volumes from patients with non-small cell lung cancer (NSCLC). Our method improves segmentation and performs better than region growing approaches, the watershed technique, fuzzy-c-means, region-based active contour and tumor customized downhill.

Automated delineation of lung tumors in PET images based on monotonicity and a tumor-customized criterion.

Reliable automated or semiautomated lung tumor delineation methods in positron emission tomography should provide accurate tumor boundary definition and separation of the lung tumor from surrounding tissue or "hot spots" that have similar intensities to the lung tumor. We propose a tumor-customized downhill (TCD) method to achieve these objectives. Our approach includes: 1) automatic formulation of a tumor-customized criterion to improve tumor boundary definition, 2) a monotonic property of the standardized uptake value (SUV) of tumors to separate the tumor from adjacent regions of increased metabolism ("hot spot"), and 3) accounts for tumor heterogeneity. Three simulated lesions and 30 PET-CT studies, grouped into "simple" and "complex" groups, were used for evaluation. Our main findings are that TCD, when compared to the threshold based on 40% and 50% maximum SUV, adaptive threshold, Fuzzy c-means, and watershed techniques achieved the highest Dice's similarity coefficient average for simulation data (0.73) and "complex" group (0.71); the least volumetric error in the "simple" (1.76 mL) and the "complex" group (14.59 mL); and TCD solves the problem of leakage into adjacent tissues when many other techniques fail.

The impact of reconstruction algorithms on semi-automatic small lesion segmentation for PET: a phantom study.

A robust lesion segmentation method is critical for quantification of lesion activity in positron emission tomography (PET), especially for the cases where lesion boundary is not discernible in the corresponding computed tomography (CT). However, lesion delineation in PET is a challenging task, especially for small lesions, due to the low intrinsic resolution, image noise and partial volume effect. The combinations of different reconstruction methods and post-reconstruction smoothing on PET images also affect the segmentation result significantly which has always been overlooked. Therefore, the aim of this study was to investigate the impact of different reconstruction methods on semi-automated small lesion segmentation for PET images. Four conventional segmentation methods were evaluated including region growing technique based on maximum intensity (RGmax) and mean intensity (RGmean) thresholds, Fuzzy c-mean (FCM) and watershed (WS) technique. All these methods were evaluated on a physical phantom scan which was reconstructed with Ordered Subset Expectation Maximization (OSEM) with Gaussian post-smoothing and Maximum a Posteriori (MAP) with quadratic prior respectively. The results demonstrate that: 1) the performance of all the segmentation methods subject to the smoothness constraint applied on the reconstructed images; 2) FCM method applied on MAP reconstructed images yielded overall superior performance than other evaluated combinations.