Quantitative Analysis of Torso FDG-PET Scans by Using Anatomical Standardization of Normal Cases from Thorough Physical Examinations

Abstract

Understanding of standardized uptake value (SUV) of 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography (FDG-PET) depends on the background accumulations of glucose because the SUV often varies the status of patients. The purpose of this study was to develop a new method for quantitative analysis of SUV of FDG-PET scan images. The method included an anatomical standardization and a statistical comparison with normal cases by using Z-score that are often used in SPM or 3D-SSP approach for brain function analysis. Our scheme consisted of two approaches, which included the construction of a normal model and the determination of the SUV scores as Z-score index for measuring the abnormality of an FDG-PET scan image. To construct the normal torso model, all of the normal images were registered into one shape, which indicated the normal range of SUV at all voxels. The image deformation process consisted of a whole body rigid registration of shoulder to bladder region and liver registration and a non-linear registration of body surface by using the thin-plate spline technique. In order to validate usefulness of our method, we segment suspicious regions on FDG-PET images manually, and obtained the Z-scores of the regions based on the corresponding voxels that stores the mean and the standard deviations from the normal model. We collected 243 (143 males and 100 females) normal cases to construct the normal model. We also extracted 432 abnormal spots from 63 abnormal cases (73 cancer lesions) to validate the Z-scores. The Z-scores of 417 out of 432 abnormal spots were higher than 2.0, which statistically indicated the severity of the spots. In conclusions, the Z-scores obtained by our computerized scheme with anatomical standardization of torso region would be useful for visualization and detection of subtle lesions on FDG-PET scan images even when the SUV may not clearly show an abnormality.

A Registration Method Based on Contour Point Cloud for 3D Whole-Body PET and CT Images

“…For example, some slices that include only arms and legs of a human body have little clinical meaning for a doctor. Therefore, in order to reduce the computation and increase the time efficiency, a new automated trunk slices extraction method is proposed in this paper which is different from the manual method in [ 17 ]. Trunk slices are considered as those slices that contain only one connected region.…”

“…Secondly, this paper proposes a new automated trunk slices extraction method to extract feature point cloud sequences automatically. This method is different from the manual method proposed in [ 17 ] where the identification of trunk slices must be done manually. Finally, a simple downsampling method and a multithread ICP are used to achieve registration quickly with a considerable accuracy.…”

Anomaly detection in chest 18F-FDG PET/CT by Bayesian deep learning

“…A combination of positron emission tomography (PET) using the tracer 18 F-fluorodeoxyglucose (FDG) is a useful imaging technique to find malignant and inflammatory lesions. Computer-aided diagnosis (CAD) in 18 F-FDG PET (hereinafter, PET) and its combination with computed tomography (hereinafter, PET/CT) has been actively studied to this day [1][2][3][4][5][6][7][8]. These CAD studies can be divided into two groups by techniques employed: (1) supervised learning and (2) semi-supervised/unsupervised anomaly detection (hereafter, anomaly detection).…”

“…However, preparing such annotated datasets can take a considerable amount of time [9,10]. In the second group [6][7][8], on the other hand, anomaly detection is employed, that is, training only with normal class instances and detecting outliers different from the normal data [11][12][13]. Here, the training dataset does not require any abnormal images or lesion annotations and, therefore, far easier to prepare than annotated datasets in supervised CAD.…”

“…Previous anomaly detection method for PET or PET/ CT images [6][7][8] has the limitations detecting anomalies only in a specific organ or region [7,8] or requiring complicated anatomical standardization [6]. In this paper, we propose a novel anomaly detection CAD method for PET/ CT images that can detect anomalies at any location in a simple way.…”