Virtual high-count PET image generation using a deep learning method.

PURPOSE: Recently, deep learning-based methods have been established to denoise the low-count positron emission tomography (PET) images and predict their standard-count image counterparts, which could achieve reduction of injected dosage and scan time, and improve image quality for equivalent lesion detectability and clinical diagnosis. In clinical settings, the majority scans are still acquired using standard injection dose with standard scan time. In this work, we applied a 3D U-Net network to reduce the noise of standard-count PET images to obtain the virtual-high-count (VHC) PET images for identifying the potential benefits of the obtained VHC PET images. METHODS: The training datasets, including down-sampled standard-count PET images as the network input and high-count images as the desired network output, were derived from 27 whole-body PET datasets, which were acquired using 90-min dynamic scan. The down-sampled standard-count PET images were rebinned with matched noise level of 195 clinical static PET datasets, by matching the normalized standard derivation (NSTD) inside 3D liver region of interests (ROIs). Cross-validation was performed on 27 PET datasets. Normalized mean square error (NMSE), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and standard uptake value (SUV) bias of lesions were used for evaluation on standard-count and VHC PET images, with real-high-count PET image of 90 min as the gold standard. In addition, the network trained with 27 dynamic PET datasets was applied to 195 clinical static datasets to obtain VHC PET images. The NSTD and mean/max SUV of hypermetabolic lesions in standard-count and VHC PET images were evaluated. Three experienced nuclear medicine physicians evaluated the overall image quality of randomly selected 50 out of 195 patients' standard-count and VHC images and conducted 5-score ranking. A Wilcoxon signed-rank test was used to compare differences in the grading of standard-count and VHC images. RESULTS: The cross-validation results showed that VHC PET images had improved quantitative metrics scores than the standard-count PET images. The mean/max SUVs of 35 lesions in the standard-count and true-high-count PET images did not show significantly statistical difference. Similarly, the mean/max SUVs of VHC and true-high-count PET images did not show significantly statistical difference. For the 195 clinical data, the VHC PET images had a significantly lower NSTD than the standard-count images. The mean/max SUVs of 215 hypermetabolic lesions in the VHC and standard-count images showed no statistically significant difference. In the image quality evaluation by three experienced nuclear medicine physicians, standard-count images and VHC images received scores with mean and standard deviation of 3.34±0.80 and 4.26 ± 0.72 from Physician 1, 3.02 ± 0.87 and 3.96 ± 0.73 from Physician 2, and 3.74 ± 1.10 and 4.58 ± 0.57 from Physician 3, respectively. The VHC images were consistently ranked higher than the standard-count images. The Wilcoxon signed-rank test also indicated that the image quality evaluation between standard-count and VHC images had significant difference. CONCLUSIONS: A DL method was proposed to convert the standard-count images to the VHC images. The VHC images had reduced noise level. No significant difference in mean/max SUV to the standard-count images was observed. VHC images improved image quality for better lesion detectability and clinical diagnosis.

PET Image Denoising using a Deep-Learning Method for Extremely Obese Patients.

The image quality in clinical PET scan can be severely degraded due to high noise levels in extremely obese patients. Our work aimed to reduce the noise in clinical PET images of extremely obese subjects to the noise level of lean subject images, to ensure consistent imaging quality. The noise level was measured by normalized standard deviation (NSTD) derived from a liver region of interest. A deep learning-based noise reduction method with a fully 3D patch-based U-Net was used. Two U-Nets, U-Nets A and B, were trained on datasets with 40% and 10% count levels derived from 100 lean subjects, respectively. The clinical PET images of 10 extremely obese subjects were denoised using the two U-Nets. The results showed the noise levels of the images with 40% counts of lean subjects were consistent with those of the extremely obese subjects. U-Net A effectively reduced the noise in the images of the extremely obese patients while preserving the fine structures. The liver NSTD improved from 0.13±0.04 to 0.08±0.03 after noise reduction (p = 0.01). After denoising, the image noise level of extremely obese subjects was similar to that of lean subjects, in terms of liver NSTD (0.08±0.03 vs. 0.08±0.02, p = 0.74). In contrast, U-Net B over-smoothed the images of extremely obese patients, resulting in blurred fine structures. In a pilot reader study comparing extremely obese patients without and with U-Net A, the difference was not significant. In conclusion, the U-Net trained by datasets from lean subjects with matched count level can provide promising denoising performance for extremely obese subjects while maintaining image resolution, though further clinical evaluation is needed.

Altered FDG Biodistribution in Subcutaneous White Fat on PET/CT Following l-Asparaginase Chemotherapy.

ABSTRACT: A 13-year-old boy with mediastinal T-cell lymphoblastic lymphoma demonstrated an altered biodistribution with diffuse activity in subcutaneous white adipose tissue and decreased visceral activity on interim posttreatment FDG PET/CT. This altered biodistribution was attributed to administration of the chemotherapeutic enzyme l-asparaginase 3 hours preceding the PET/CT, altering adipocytes amino acid and glucose metabolism. Treatment response assessment was adversely affected by the altered biodistribution, emphasizing the importance of maximizing the time between chemotherapy and PET/CT during successive oncologic treatment cycles. Because adipocytes protect leukemic cells in culture from l-asparaginase, we hypothesize that white adipose tissue-altered biodistribution may be related to l-asparaginase resistance.

Inferior vena cava syndrome on skeletal scintigraphy secondary to metastatic prostate cancer.

This interesting image illustrates an unusual case of inferior vena cava (IVC) syndrome from prostate cancer retroperitoneal adenopathy initially identified with skeletal scintigraphy. IVC syndrome is an infrequent occurrence resulting from extrinsic compression or intraluminal occlusion of the vessel. Whole-body planar skeletal scintigraphy showed a stable left sacroiliac metastasis and increased soft tissue uptake throughout the lower hemibody up to the lower chest level. Computed tomography (CT) demonstrated extrinsic compression of the IVC from metastatic retroperitoneal adenopathy. This represents a rare presentation of IVC syndrome in prostate cancer with characteristic appearance on skeletal scintigraphy of Fisherman's Wader's sign, that should prompt confirmatory anatomic imaging.

CT pulmonary angiography: increasingly diagnosing less severe pulmonary emboli.

BACKGROUND: It is unknown whether the observed increase in computed tomography pulmonary angiography (CTPA) utilization has resulted in increased detection of pulmonary emboli (PEs) with a less severe disease spectrum. METHODS: Trends in utilization, diagnostic yield, and disease severity were evaluated for 4,048 consecutive initial CTPAs performed in adult patients in the emergency department of a large urban academic medical center between 1/1/2004 and 10/31/2009. Transthoracic echocardiography (TTE) findings and peak serum troponin levels were evaluated to assess for the presence of PE-associated right ventricular (RV) abnormalities (dysfunction or dilatation) and myocardial injury, respectively. Statistical analyses were performed using multivariate logistic regression. RESULTS: 268 CTPAs (6.6%) were positive for acute PE, and 3,780 (93.4%) demonstrated either no PE or chronic PE. There was a significant increase in the likelihood of undergoing CTPA per year during the study period (odds ratio [OR] 1.05, 95% confidence interval [CI] 1.04-1.07, P<0.01). There was no significant change in the likelihood of having a CTPA diagnostic of an acute PE per year (OR 1.03, 95% CI 0.95-1.11, P = 0.49). The likelihood of diagnosing a less severe PE on CTPA with no associated RV abnormalities or myocardial injury increased per year during the study period (OR 1.39, 95% CI 1.10-1.75, P = 0.01). CONCLUSIONS: CTPA utilization has risen with no corresponding change in diagnostic yield, resulting in an increase in PE detection. There is a concurrent rise in the likelihood of diagnosing a less clinically severe spectrum of PEs.

Multiple testing, cumulative radiation dose, and clinical indications in patients undergoing myocardial perfusion imaging.

CONTEXT: Myocardial perfusion imaging (MPI) is the single medical test with the highest radiation burden to the US population. Although many patients undergoing MPI receive repeat MPI testing, or additional procedures involving ionizing radiation, no data are available characterizing their total longitudinal radiation burden and relating radiation burden with reasons for testing. OBJECTIVES: To characterize procedure counts, cumulative estimated effective doses of radiation, and clinical indications for patients undergoing MPI. DESIGN, SETTING, AND PATIENTS: A retrospective cohort study of 1097 consecutive patients undergoing index MPI during the first 100 days of 2006 (January 1-April 10) at Columbia University Medical Center, New York, New York, that evaluated all preceding medical imaging procedures involving ionizing radiation undergone beginning October 1988, and all subsequent procedures through June 2008, at the center. MAIN OUTCOME MEASURES: Cumulative estimated effective dose of radiation, number of procedures involving radiation, and indications for testing. RESULTS: Patients underwent a median of 15 (interquartile range [IQR], 6-32; mean, 23.9) procedures involving radiation exposure; of which 4 (IQR, 2-8; mean, 6.5) were high-dose procedures (≥3 mSv; ie, 1 year's background radiation), including 1 (IQR, 1-2; mean, 1.8) MPI study per patient. A total of 344 patients (31.4%) received cumulative estimated effective dose from all medical sources of more than 100 mSv. Multiple MPIs were performed in 424 patients (38.6%), for whom cumulative estimated effective dose was 121 mSv (IQR, 81-189; mean, 149 mSv). Men and white patients had higher cumulative estimated effective doses. More than 80% of initial and 90% of repeat MPI examinations were performed in patients with known cardiac disease or symptoms consistent with it. CONCLUSION: In this institution, multiple testing with MPI was common and in many patients associated with high cumulative estimated doses of radiation.