Pathology-validated PET image data sets and their role in PET segmentation

摘要: Positron emission tomography (PET)/computed has recently been finding broader application for the diagnosis, treatment and therapy assessment of malignant disease. Accurate definition tumor border is extremely important success localized therapies. PET promises to provide metabolically active volume and, at present, it used target in a variety tumors. This process is, however, subject uncertainties different origin. Resolving these challenging, since validating images segmentation contours against pathology experimentally difficult. In addition accurate lesion contouring, this challenges validation tracers investigations functional heterogeneity. paper, we briefly review present studies providing image data sets with validation. We focus on specimen handling techniques aimed achieving higher geometrical accuracy pathology-derived “ground truth”. also summarize main findings obtained which have tested help sets. Finally, critical summary current state art pathological discuss future possibilities direction.