We propose an automated lung tumor segmentation method for whole body PET images based on a novel downhill
region growing (DRG) technique, which regards homogeneous tumor hotspots as 3D monotonically decreasing
functions. The method has three major steps: thoracic slice extraction with K-means clustering of the slice features;
hotspot segmentation with DRG; and decision tree analysis based hotspot classification. To overcome the common
problem of leakage into adjacent hotspots in automated lung tumor segmentation, DRG employs the tumors' SUV
monotonicity features. DRG also uses gradient magnitude of tumors' SUV to improve tumor boundary definition. We
used 14 PET volumes from patients with primary NSCLC for validation. The thoracic region extraction step achieved
good and consistent results for all patients despite marked differences in size and shape of the lungs and the presence of
large tumors. The DRG technique was able to avoid the problem of leakage into adjacent hotspots and produced a
volumetric overlap fraction of 0.61 ± 0.13 which outperformed four other methods where the overlap fraction varied
from 0.40 ± 0.24 to 0.59 ± 0.14. Of the 18 tumors in 14 NSCLC studies, 15 lesions were classified correctly, 2 were false
negative and 15 were false positive.
Automated segmentation for the delineation of lung tumors with PET-CT is a challenging task. In PET images, primary
lung tumors can have varying degrees of tracer uptake, which sometimes does not differ markedly from normal adjacent
structures such as the mediastinum, heart and liver. In addition, separation of tumor from adjacent soft tissues and bone
in the chest wall is problematic due to limited resolution. For CT, the tumor soft tissue density can be similar to that in
the blood vessels and the chest wall; and although CT provides better boundary definition, exact tumor delineation is
also difficult when the tumor density is similar to adjacent structures. We propose an innovative automated adaptive
method to delineate lung tumors in PET-CT images in conjunction with a lung atlas in which an iterative mean-SUV
(Standardized Uptake Value) threshold is used to gradually define the tumor region in PET. Tumor delineation in the CT
data is performed using region growing and seeds obtained autonomously from the PET tumor regions. We evaluated our
approach in 13 patients with non-small cell lung cancer (NSCLC) and found it could delineate tumors of different size,
shape and location, even when when the NSCLC involved the chest wall.
A two-step non-linear medical image registration approach is proposed, based on the image intensity. In the first step, the global affme medical image registration is used to establish one-to-one mapping between the two images to be registered. After this first step, the images are registered up to small local elastic deformation. Then the mapped images are used as inputs in the second step, during which, the study image is modeled as elastic sheet by being divided into several sub-images. Moving the individual sub-image in the reference image, the local displacement vectors are found and the global elastic transformation is achieved by assimilating all of the local transformation into a continuous transformation. This algorithm has been tested by both simulated and clinical tomographic images.