A review on segmentation of positron emission tomography images

Abstract

Positron Emission Tomography (PET), a non-invasive functional imaging method at the molecular level, images the distribution of biologically targeted radiotracers with high sensitivity. PET imaging provides detailed quantitative information about many diseases and is often used to evaluate inflammation, infection, and cancer by detecting emitted photons from a radiotracer localized to abnormal cells. In order to differentiate abnormal tissue from surrounding areas in PET images, image segmentation methods play a vital role; therefore, accurate image segmentation is often necessary for proper disease detection, diagnosis, treatment planning, and follow-ups. In this review paper, we present state-of-the-art PET image segmentation methods, as well as the recent advances in image segmentation techniques. In order to make this manuscript self-contained, we also briefly explain the fundamentals of PET imaging, the challenges of diagnostic PET image analysis, and the effects of these challenges on the segmentation results.

Reproducibility of F18‐FDG PET radiomic features for different cervical tumor segmentation methods, gray‐level discretization, and reconstruction algorithms

“…For more information calculating the probabilities for this method, the reader is encouraged to read Zhu et al62 and Yushkevich et al61 A major disadvantage of thresholding method is that the intensity histogram does not provide spatial information about the ROIs. Also, there is no consensus on the selection of an optimum threshold level because of the large variability of pathologies, low resolution, inherent noise, and high uncertainties in fuzzy object boundaries 31. Moreover, defining tumor volumes based on SUV thresholds has been widely challenged 63, 64.…”

“…An extensive review study by Foster et al31 identified five sophisticated procedures of PET tumor segmentation, namely manual segmentation, thresholding‐based methods, learning methods and stochastic modeling‐based techniques, region‐based (graphical‐based) segmentation methods, and boundary‐based methods. The study concluded that there is no notion of one acceptable PET image segmentation method over the other.…”

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

“…10,19 All these methods offer different compromises in terms of versatility and performance and compare well against manual segmentations by clinicians or the pathological measurements with varying rates of success. 3 Yet there is not enough consensus among the clinical community on algorithms that work well to be incorporated into commercially available imaging software and treatment planning systems. 3,4 Most of these state-of-the-art algorithms are proprietary and are currently unavailable for clinical use.…”

“…The methods range from simple to complex methods. 1,3,4 The segmentation methods include but are not limited to constant and adaptive threshold methods, [5][6][7][8][9] region growing methods, [10][11][12] gradient-based methods, [13][14][15] fuzzy models, [16][17][18] and Gaussian mixture modeling. 10,19 All these methods offer different compromises in terms of versatility and performance and compare well against manual segmentations by clinicians or the pathological measurements with varying rates of success.…”

PET Image Segmentation Based on Gabor Annulus Filtering and Region Growing

“…A review conducted by Foster et al on the state-of-the-art image segmentation methods for PET scans of body images, as well as the recent advances in PET image segmentation techniques, pointed resolution related issues, noise and large variability in the shape, texture, and location of pathologies as factors that significantly affect PET image segmentation. They also indicate to the lack of standardization between different segmentation techniques and the need for a publicly available database of PET images for evaluating new and old methods [13].…”