Detection and localization of hyperfunctioning parathyroid glands on [18F]fluorocholine PET/ CT using deep learning - model performance and comparison to human experts.

BACKGROUND: In the setting of primary hyperparathyroidism (PHPT), [18F]fluorocholine PET/CT (FCH-PET) has excellent diagnostic performance, with experienced practitioners achieving 97.7% accuracy in localising hyperfunctioning parathyroid tissue (HPTT). Due to the relative triviality of the task for human readers, we explored the performance of deep learning (DL) methods for HPTT detection and localisation on FCH-PET images in the setting of PHPT. PATIENTS AND METHODS: We used a dataset of 93 subjects with PHPT imaged using FCH-PET, of which 74 subjects had visible HPTT while 19 controls had no visible HPTT on FCH-PET. A conventional Resnet10 as well as a novel mPETResnet10 DL model were trained and tested to detect (present, not present) and localise (upper left, lower left, upper right or lower right) HPTT. Our mPETResnet10 architecture also contained a region-of-interest masking algorithm that we evaluated qualitatively in order to try to explain the model's decision process. RESULTS: The models detected the presence of HPTT with an accuracy of 83% and determined the quadrant of HPTT with an accuracy of 74%. The DL methods performed statistically worse (p < 0.001) in both tasks compared to human readers, who localise HPTT with the accuracy of 97.7%. The produced region-of-interest mask, while not showing a consistent added value in the qualitative evaluation of model's decision process, had correctly identified the foreground PET signal. CONCLUSIONS: Our experiment is the first reported use of DL analysis of FCH-PET in PHPT. We have shown that it is possible to utilize DL methods with FCH-PET to detect and localize HPTT. Given our small dataset of 93 subjects, results are nevertheless promising for further research.

Image reconstruction using small-voxel size improves small lesion detection for positron emission tomography.

BACKGROUND: PET/CT imaging is widely used in oncology and provides both metabolic and anatomic information. Because of the relatively poor spatial resolution of PET, the detection of small lesions is limited. The low spatial resolution introduces the partial-volume effect (PVE) which negatively affects images both qualitatively and quantitatively. The aim of the study was to investigate the effect of small-voxel (2 mm in-line pixel size) vs. standard-voxel (4 mm in-line pixel size) reconstruction on lesion detection and image quality in a range of activity ratios. MATERIALS AND METHODS: The National Electrical Manufacturers Association (NEMA) body phantom and the Micro Hollow-Sphere phantom spheres were filled with a solution of [18F]fluorodeoxyglucose ([18F]FDG) in sphere-to-background ratios of 2:1, 3:1, 4:1 and 8:1. In all images reconstructed with 2 mm and 4 mm in-line pixel size the visual lesion delineation, contrast recovery coefficient (CRC) and contrast-to-noise ratio (CNR) were evaluated. RESULTS: For smaller (≤ 13 mm) phantom spheres, significantly higher CRC and CNR using small-voxel reconstructions were found, also improving visual lesion delineation. CRC did not differ significantly for larger (≥ 17 mm) spheres using 2 mm and 4 mm in-line pixel size, but CNR was significantly lower; however, lower CNR did not affect visual lesion delineation. CONCLUSIONS: Small-voxel reconstruction consistently improves precise small lesion delineation, lesion contrast and image quality.

Diagnostic value of [18F]Fluorocholine PET/CT in detection of primary medullary thyroid cancer.

OBJECTIVE: Medullary thyroid cancer (MTC) is a challenging neuroendocrine malignancy where the role of nuclear medicine imaging is currently limited. This paper investigates the potential diagnostic value of [18F]Fluorocholine PET/CT in primary MTC. METHODS: We prospectively enrolled 25 patients (10 male, 15 female) with suspicion for primary MTC based on fine-needle aspiration biopsy (FNAB). All patients had a baseline three phase [18F]Fluorocholine PET/CT (2.5 MBq/kg): two regional head and neck and upper mediastinum studies at 5 min (first phase) and 120 min (third phase) and a whole-body PET/CT (from the skull vertex to mid-thighs) at 60 min (second phase). Any non-physiological radiotracer uptake was regarded as MTC positive. All patients referred to surgery had a preoperative neck-US. True lesion status was assessed using either histopathology, FNAB results or follow-up imaging and laboratory (calcitonin, CEA) results. Results with p < 0.05 were considered statistically significant. RESULTS: Nineteen of 25 patients (76%) were surgically treated and histopathology reports were obtained. Patient-based sensitivity and positive predictive value for detection of any MTC lesion using [18F]Fluorocholine PET/CT were both 100%. Neck-US was more specific (100% vs 70%; p = 0.002) and had a higher positive predictive value than [18F]Fluorocholine PET/CT (100% vs 55%; p = 0.018) for N1a and N1b staging. [18F]Fluorocholine PET/CT had a higher sensitivity (100% vs 50%; p = 0.025) and higher negative predictive value (100% vs 81%; p = 0.026) than neck-US for N1b staging. The optimal SUVmax cut-off to differentiate malignant from benign neck lesions at 60 and 120 min was 2.56. Patients with M1 stage on PET/CT had higher calcitonin (median of 5,372 vs 496.6 pg/ml; p = 0.005) and CEA concentrations (median of 95.8 vs 18.65 µg/l; p = 0.034) compared to patients with M0 disease. CONCLUSION: [18F]Fluorocholine PET/CT appears to be a promising radiotracer for primary staging of MTC by increasing diagnostic accuracy for N staging and detecting possible distant metastatic sites at initial presentation of disease.

Best practice for the nuclear medicine technologist in CT-based attenuation correction and calcium score for nuclear cardiology.

The use of hybrid systems is increasingly growing in Europe and this is progressively important for the final result of diagnostic tests. As an integral part of the hybrid imaging system, computed tomography (CT) plays a crucial role in myocardial perfusion imaging diagnostics. Throughout Europe, a variety of equipment is available and also different university curricula of the nuclear medicine technologist are observed. Hence, the Technologist Committee of the European Association of Nuclear Medicine proposes to identify, through a bibliographic review, the recommendations for best practice in computed tomography applied to attenuation correction and calcium score in myocardial perfusion imaging, which courses in the set of knowledge, skills, and competencies for nuclear medicine technologists. This document aims at providing recommendations for CT acquisition protocols and CT image optimization in nuclear cardiology.

18F-Fluorocholine PET/CT in Primary Hyperparathyroidism: Superior Diagnostic Performance to Conventional Scintigraphic Imaging for Localization of Hyperfunctioning Parathyroid Glands.

Primary hyperparathyroidism (PHPT) is a common endocrine disorder, definitive treatment usually requiring surgical removal of the offending parathyroid glands. To perform focused surgical approaches, it is necessary to localize all hyperfunctioning glands. The aim of the study was to compare the efficiency of established conventional scintigraphic imaging modalities with emerging 18F-fluorocholine PET/CT imaging in preoperative localization of hyperfunctioning parathyroid glands in a larger series of PHPT patients. Methods: In total, 103 patients with PHPT were imaged preoperatively with 18F-fluorocholine PET/CT and conventional scintigraphic imaging methods, consisting of 99mTc-sestamibi SPECT/CT, 99mTc-sestamibi/pertechnetate subtraction imaging, and 99mTc-sestamibi dual-phase imaging. The results of histologic analysis, as well as intact parathyroid hormone and serum calcium values obtained 1 d after surgery and on follow-up, served as the standard of truth for evaluation of imaging results. Results: Diagnostic performance of 18F-fluorocholine PET/CT surpassed conventional scintigraphic methods (separately or combined), with calculated sensitivity of 92% for PET/CT and 39%-56% for conventional imaging (65% for conventional methods combined) in the entire patient group. Subgroup analysis, differentiating single and multiple hyperfunctioning parathyroid glands, showed PET/CT to be most valuable in the group with multiple hyperfunctioning glands, with sensitivity of 88%, whereas conventional imaging was significantly inferior, with sensitivity of 22%-34% (44% combined). Conclusion:18F-fluorocholine PET/CT is a diagnostic modality superior to conventional imaging methods in patients with PHPT, allowing for accurate preoperative localization.

18F-choline PET/CT for parathyroid scintigraphy: significantly lower radiation exposure of patients in comparison to conventional nuclear medicine imaging approaches.

BACKGROUND: Parathyroid subtraction scintigraphy (PSS) is the most commonly used imaging method for localisation of hyperfunctioning parathyroid glands (HPGs) in primary hyperparathyroidism (PHP), a common endocrine disorder. Hybrid (SPECT/CT) imaging with 99mTc-sestaMIBI (MIBI) at an early and delayed phase (dual-phase imaging) may be the most accurate conventional imaging approach, but includes additional radiation exposure due to added CT imaging. Recently, 18F-choline (FCH) PET/CT was introduced for HPG imaging, which can also be performed using the dual-phase approach. To date, no studies have compared organ doses and the effective dose (ED) from conventional subtraction scintigraphy, dual-phase MIBI SPECT/CT, and FCH PET/CT in the localisation of HPGs. AIM: In addition to the comparison of the diagnostic performance of FCH PET/CT and conventional scintigraphic imaging methods, the aim of the study was to measure the organ doses and the ED for conventional subtraction parathyroid imaging protocols, using dual-phase MIBI SPECT/CT as a potential conventional imaging method of choice and FCH dual-phase PET/CT as a potential future imaging method of choice for the localisation of HPGs. Materials, methods. Thirty-six patients referred for parathyroid imaging with a clinical indication of PHP underwent preoperative PSS and dual-phase SPECT/CT imaging with the addition of FCH PET/CT. The diagnostic performance of the imaging modalities was assessed by using histology results as a gold standard. Radiation exposure was calculated for the administered activities of radiopharmaceuticals using ICRP80 weighting factors and for CT exposure at hybrid imaging using dose-length products and the ImPACT CT Patient Dosimetry Calculator. RESULTS: The diagnostic performance of FCH PET/CT was significantly better than that of conventional imaging modalities (sensitivity of 97% vs 64% and 46% for MIBI SPECT/CT and PSS, respectively, with comparable specificity of over 95% for all modalities). The highest radiation exposure was caused by conventional PSS (7.4 mSv), followed by dual-phase MIBI SPECT/CT (6.8 mSv). The radiation exposure was the lowest for dual-phase FCH PET/CT imaging (2.8 mSv). The added CT imaging for both hybrid approaches did not cause significant additional radiation exposure (1.4 mSv for MIBI SPECT/CT, additional 26.4% to overall exposure; 0.8 mSv for FCH PET/CT, additional 42.4% to overall exposure). CONCLUSION: In comparison to conventional scintigraphic imaging of HPGs, emerging hybrid (SPECT/CT, PET/CT) imaging techniques combine superior diagnostic performance with lower radiation exposure to patients.

The effect of 18F-FDG-PET image reconstruction algorithms on the expression of characteristic metabolic brain network in Parkinson's disease.

PURPOSE: To evaluate the reproducibility of the expression of Parkinson's Disease Related Pattern (PDRP) across multiple sets of 18F-FDG-PET brain images reconstructed with different reconstruction algorithms. METHODS: 18F-FDG-PET brain imaging was performed in two independent cohorts of Parkinson's disease (PD) patients and normal controls (NC). Slovenian cohort (20 PD patients, 20 NC) was scanned with Siemens Biograph mCT camera and reconstructed using FBP, FBP+TOF, OSEM, OSEM+TOF, OSEM+PSF and OSEM+PSF+TOF. American Cohort (20 PD patients, 7 NC) was scanned with GE Advance camera and reconstructed using 3DRP, FORE-FBP and FORE-Iterative. Expressions of two previously-validated PDRP patterns (PDRP-Slovenia and PDRP-USA) were calculated. We compared the ability of PDRP to discriminate PD patients from NC, differences and correlation between the corresponding subject scores and ROC analysis results across the different reconstruction algorithms. RESULTS: The expression of PDRP-Slovenia and PDRP-USA networks was significantly elevated in PD patients compared to NC (p<0.0001), regardless of reconstruction algorithms. PDRP expression strongly correlated between all studied algorithms and the reference algorithm (r⩾0.993, p<0.0001). Average differences in the PDRP expression among different algorithms varied within 0.73 and 0.08 of the reference value for PDRP-Slovenia and PDRP-USA, respectively. ROC analysis confirmed high similarity in sensitivity, specificity and AUC among all studied reconstruction algorithms. CONCLUSIONS: These results show that the expression of PDRP is reproducible across a variety of reconstruction algorithms of 18F-FDG-PET brain images. PDRP is capable of providing a robust metabolic biomarker of PD for multicenter 18F-FDG-PET images acquired in the context of differential diagnosis or clinical trials.

Optimal scan time for evaluation of parathyroid adenoma with [(18)F]-fluorocholine PET/CT.

BACKGROUND: Parathyroid adenomas, the most common cause of primary hyperparathyroidism, are benign tumours which autonomously produce and secrete parathyroid hormone. [(18)F]-fluorocholine (FCH), PET marker of cellular proliferation, was recently demonstrated to accumulate in lesions representing enlarged parathyroid tissue; however, the optimal time to perform FCH PET/CT after FCH administration is not known. The aim of this study was to determine the optimal scan time of FCH PET/CT in patients with primary hyperparathyroidism. PATIENTS AND METHODS: 43 patients with primary hyperparathyroidism were enrolled in this study. A triple-phase PET/CT imaging was performed five minutes, one and two hours after the administration of FCH. Regions of interest (ROI) were placed in lesions representing enlarged parathyroid tissue and thyroid tissue. Standardized uptake value (SUVmean), retention index and lesion contrast for parathyroid and thyroid tissue were calculated. RESULTS: Accumulation of FCH was higher in lesions representing enlarged parathyroid tissue in comparison to the thyroid tissue with significantly higher SUVmean in the second and in the third phase (p < 0.0001). Average retention index decreased significantly between the first and the second phase and increased significantly between the second and the third phase in lesions representing enlarged parathyroid tissue and decreased significantly over all three phases in thyroid tissue (p< 0.0001). The lesion contrast of lesions representing enlarged parathyroid tissue and thyroid tissue was significantly better in the second and the third phase compared to the first phase (p < 0.05). CONCLUSIONS: According to the results the optimal scan time of FCH PET/CT for localization of lesions representing enlarged parathyroid tissue is one hour after administration of the FCH.

¹8F-Fluorocholine PET/CT for localization of hyperfunctioning parathyroid tissue in primary hyperparathyroidism: a pilot study.

PURPOSE: Primary hyperparathyroidism is a common endocrine disorder which is diagnosed biochemically and for which therapy is surgical. A prerequisite for minimally invasive surgery, which minimizes morbidity and cost, is accurate localization of the involved gland(s). The aim of this study was to evaluate the usefulness of (18)F-fluorocholine PET/CT for preoperative localization of hyperfunctioning parathyroid tissue. METHODS: (18)F-Fluorocholine PET/CT and conventional parathyroid scintigraphic imaging consisting of (99m)Tc-sestaMIBI SPECT/CT, (99m)Tc-sestaMIBI dual-phase imaging and (99m)Tc-sestaMIBI/pertechnetate subtraction imaging were performed in 24 patients. The diagnostic performance of the imaging methods was compared against histology as the gold standard and postoperative serum Ca(2+) and iPTH values. RESULTS: The sensitivity and specificity of (18)F-fluorocholine PET/CT were 92% and 100%, respectively, in contrast to 49% and 100%, 46% and 100%, and 44% and 100% for (99m)Tc-sestaMIBI SPECT/CT, (99m)Tc-sestaMIBI/pertechnetate subtraction imaging and (99m)Tc-sestaMIBI dual-phase imaging, respectively. Combined conventional scintigraphic imaging had a sensitivity and specificity of 64% and 100%, respectively. The performance of (18)F-fluorocholine PET/CT was superior particularly in patients with multiple lesions or hyperplasia. CONCLUSION: (18)F-Fluorocholine PET/CT appears to be a promising, effective imaging method for localization of hyperfunctioning parathyroid tissue.