Machine learning diagnosis of active Juvenile Idiopathic Arthritis on blood pool [ 99M Tc] Tc-MDP scintigraphy images.

PURPOSE: Neural network has widely been applied for medical classifications and disease diagnosis. This study employs deep learning to best discriminate Juvenile Idiopathic Arthritis (JIA), a pediatric chronic joint inflammatory disease, from healthy joints by exploring blood pool images of 2phase [ 99m Tc] Tc-MDP bone scintigraphy. METHODS: Self-deigned multi-input Convolutional Neural Network (CNN) in addition to three available pre-trained models including VGG16, ResNet50 and Xception are applied on 1304 blood pool images of 326 healthy and known JIA children and adolescents (aged 1-16). RESULTS: The self-designed model ROC analysis shows diagnostic efficiency with Area Under the Curve (AUC) 0.82 and 0.86 for knee and ankle joints, respectively. Among the three pertained models, VGG16 ROC analysis reveals AUC 0.76 and 0.81 for knee and ankle images, respectively. CONCLUSION: The self-designed model shows best performance on blood pool scintigraph diagnosis of patients with JIA. VGG16 was the most efficient model rather to other pre-trained networks. This study can pave the way of artificial intelligence (AI) application in nuclear medicine for the diagnosis of pediatric inflammatory disease.

[99m Tc] Tc-MDP bone SPECT/CT diagnosing unstable slipped capital femoral epiphysis with secondary AVN in a patient with misleading knee pain.

Bone scan is highly sensitive whole-body imaging with relative low radiation in patients with non-localized skeletal symptoms. Patient is 12-year-old boy with Down syndrome, suffering recent claudication and exacerbated left knee pain unable to walk even with crutches. Three-dimensional Single photon emission computed tomography/Computed tomography (SPECT/CT) detected left slipped capital femoral epiphysis (SCFE) and secondary Avascular necrosis (AVN).

Diagnostic Performance of [18F]Fluorocholine and [68Ga]Ga-PSMA PET/CT in Prostate Cancer: A Comparative Study.

The current study endeavored to closely compare the detection rate of 68-Gallium labelled prostate-specific membrane antigen ([68Ga]Ga-PSMA) versus [18F]Fluorocholine in men with prostate cancer (PC), to investigate the benefits and pitfalls of each modality in the setting of various patient characteristics. We retrospectively analyzed 29 biopsy-proven PC patients in two categories, staging and restaging, who underwent both scans within a maximum of 30 days of each other. Variables including patient demographics, prostate specific antigen (PSA) level, Gleason score, clinical course, and following treatments were recorded. The number and location of suspicious lesions as well as uptake values were noted. A total of 148 suspicious lesions were detected, of which 70.9% (105/148) were concordantly visualized in both imaging modalities. [68Ga]Ga-PSMA positron emission tomography/computed tomography (PET/CT) revealed a higher number of metastatic lesions per patients (91% vs 78%). The mean of maximum standardized uptake value (SUV max) in concordant lesions was significantly higher in [68Ga]Ga-PSMA compared to [18F]Fluorocholine PET/CT (14.6 ± 8.44 vs. 6.9 ± 3.4, p = 0.001). Discordant lesions were detected by both modalities, but more frequently by [68Ga]Ga-PSMA PET/CT (20.3% in [68Ga]Ga-PSMA versus 8.8% by [18F]Fluorocholine PET/CT). In patients with PSA levels below 1.0 ng/mL and <2.0 ng/mL, [18F]Fluorocholine PET/CT detection rate was half (57% and 55%, respectively) that of [68Ga]Ga-PSMA PET/CT. Tumor, nodes and metastases (TNM) staging, and subsequently patient management, was only influenced in 4/29 patients (14%), particularly by [68Ga]Ga-PSMA PET/CT with PSA values under 0.5 ng/mL. [68Ga]Ga-PSMA PET/CT revealed superior diagnostic performance to [18F]Fluorocholine PET/CT in staging and restaging of PC patients, especially in cases with low PSA levels. However, in a few hormone resistant high-risk PC patients, [18F]Fluorocholine PET/CT may improve overall diagnostic accuracy.

False-positive elevated CEA during colon cancer surveillance: a cholecystitis case report diagnosed by PET-CT scan.

A 53-year-old man with previous history of sigmoid colon adenocarcinoma who had undergone surgical resection and adjuvant chemotherapy presented with slightly rising carcinoembryonic antigen (CEA), while anatomical imaging modalities were unremarkable. FDG PET-CT study did not identify residual tumoral disease; however, there were abnormalities in the gallbladder most likely suggestive of cholecystitis. Eight weeks after cholecystectomy, serum CEA concentration reached normal values. Final histopathology of the gallbladder was also consistent with acute on chronic cholecystitis.

18F-Fluorocholine PET/CT in the assessment of primary hyperparathyroidism compared with 99mTc-MIBI or 99mTc-tetrofosmin SPECT/CT: a prospective dual-centre study in 100 patients.

PURPOSE: In this prospective study we compared the accuracy of 18F-fluorocholine PET/CT with that of 99mTc-MIBI or99mTc-tetrofosmin SPECT/CT in the preoperative detection of parathyroid adenoma in patients with primary hyperparathyroidism. We also assessed the value of semiquantitative parameters in differentiating between parathyroid hyperplasia and adenoma. METHODS: Both 18F-fluorocholine PET/CT and 99mTc-MIBI/tetrofosmin SPECT/CT were performed in 100 consecutive patients with biochemical evidence of primary hyperparathyroidism. At least one abnormal focus on either 18F-fluorocholine or 99mTc-MIBI/tetrofosmin corresponding to a parathyroid gland or ectopic parathyroid tissue was considered as a positive finding. In 76 patients with positive findings on at least one imaging modality, surgical exploration was performed within 6 months, and the results were related to histopathological findings and clinical and laboratory findings at 3-6 months as the standard of truth. In 24 patients, no surgery was performed: in 18 patients with positive imaging findings surgery was refused or considered risky, and in 6 patients imaging was negative. Therefore, data from 82 patients (76 undergoing surgery, 6 without surgery) in whom the standard of truth criteria were met, were used in the final analysis. RESULTS: All patients showed biochemical evidence of primary hyperparathyroidism with a mean serum calcium level of 2.78 ± 0.34 mmol/l and parathormone (PTH) level of 196.5 ± 236.4 pg/ml. The study results in 76 patients with verified histopathology and 3 patients with negative imaging findings were analysed. Three of six patients with negative imaging showed normalized serum PTH and calcium levels on laboratory follow-up at 3 and 6 months, and the results were considered true negative. In a patient-based analysis, the detection rate with 18F-fluorocholine PET/CT was 93% (76/82), but was only 61% (50/82) with 99mTc-MIBI/tetrofosmin SPECT/CT. In a lesion-based analysis, the sensitivity, specificity, positive predictive value, negative predictive value and overall accuracy of 18F-fluorocholine PET/CT in the detection of parathyroid adenoma were 93.7%, 96.0%, 90.2%, 97.4% and 95.3%, respectively, and of 99mTc-MIBI/tetrofosmin SPECT/CT were 60.8%, 98.5%, 94.1%, 86.3% and 87.7%, respectively. Although 18F-fluorocholine PET-positive adenomatous lesions showed higher SUVmax values than the hyperplastic glands (6.80 ± 3.78 vs. 4.53 ± 0.40) in the semiquantitative analysis, the difference was not significant (p = 0.236). The mean size (measured as the length of the greatest dimension) and weight of adenomas were 15.9 ± 7.6 mm (median 15 mm, range 1-40 mm) and 1.71 ± 1.86 g (median 1 g, range: 0.25-9 g), respectively. Among the analysed parameters including serum calcium and PTH and the size and weight of parathyroid adenomas, size was significantly different between patients with negative 99mTc-MIBI/tetrofosmin SPECT/CT and those with positive 99mTc-MIBI/tetrofosmin SPECT/CT (mean size 13.4 ± 7.6 mm vs. 16.9 ± 7.4 mm, respectively; p = 0.042). CONCLUSION: In this prospective study, 18F-fluorocholine PET/CT showed promise as a functional imaging modality, being clearly superior to 99mTc-MIBI/tetrofosmin SPECT/CT, especially in the detection and localization of small parathyroid adenomas in patients with primary hyperparathyroidism. SUVmax was higher in parathyroid adenomas than in hyperplasia. However, further evaluation of this modality is needed.

Optimal time-point for 68Ga-PSMA-11 PET/CT imaging in assessment of prostate cancer: feasibility of sterile cold-kit tracer preparation?

PURPOSE: In this prospective study, we evaluated the optimal time-point for 68Ga-PSMA-11 PET/CT acquisition in the assessment of prostate cancer. We also examined, for the first time the feasibility of tracer production using a PSMA-11 sterile cold-kit in the clinical workflow of PET/CT centres. METHODS: Fifty prostate cancer patients (25 staging, 25 biochemical recurrence) were enrolled in this study. All patients received an intravenous dose of 2.0 MBq/kg body weight 68Ga-PSMA-11 prepared using a sterile cold kit (ANMI SA, Liege, Belgium), followed by an early (20 min after injection) semi-whole-body PET/CT scan and a standard-delay (100 min after injection) abdominopelvic PET/CT scan. The detection rates with 68Ga-PSMA-11 were compared between the two acquisitions. The pattern of physiological background activity and tumour to background ratio were also analysed. RESULTS: The total preparation time was reduced to 5 min using the PSMA-11 sterile cold kit, which improved the final radionuclide activity by about 30% per single 68Ge/68Ga generator elution. Overall, 158 pathological lesions were analysed in 45 patients (90%) suggestive of malignancy on both (early and standard-delay) 68Ga-PSMA PET/CT images. There was a significant (p < 0.001) increase in SUVmax on delayed images in suspicious prostates (11.6 ± 8.2 to 14.8 ± 1.0) and lymph nodes (LNs; 9.7 ± 5.9 to 12.3 ± 8.8), while bone lesions showed no significant increase (8.5 ± 5.6 to 9.2 ± 7.0, p = 0.188). However, the SUVmax of suspicious lesions on early images was adequate to support the criteria for correct interpretation (mean SUVmax 9.83 ± 6.7).In 26 of 157 lesions, but a decrease in SUV was seen, mostly in subcentimetre lesions in patients with multiple metastases. However, it did not affect the staging of the disease or patient management. The tumour to background ratio of primary prostate lesions and LNs showed a significant (p < 0.001) increase from the early to the standard-delay acquisition, but no significant increase was seen in bony lesions (p = 0.11). CONCLUSION: The PSMA-11 sterile cold kit seems to be feasible for use in routine clinical practice, and it has a shorter radionuclide preparation time and is less operator-dependent than the synthesizer-based production method. In addition, early 68Ga-PSMA-11 PET/CT imaging seems to provide a detection rate comparable with that of standard-delay imaging. Furthermore, the shorter preparation time using the 68Ga-PSMA-11 sterile cold kit and promising value of early PET/CT scanning could allow tailoring of imaging protocols which may reduce the costs and improve the time efficiency in PET/CT centres.