Background: Prostate-specific membrane antigen (PSMA) ligand PET/CT has already provided promising results in prostate cancer (PC) imaging, yet simple and reproductible reporting criteria are still lacking. This study aimed at retrospectively evaluating interobserver agreement of [ 68 Ga]Ga-PSMA-11 PET/CT images interpretation according to PC molecular imaging standardized evaluation (PROMISE) criteria and reproducibility of PSMA reporting and data systems (RADS). Methods: Forty-three patients with newly diagnosed, histologically proven intermediate-or high-risk PC, eligible for radical prostatectomy and who underwent [ 68 Ga]Ga-PSMA-11 PET/CT before surgery were retrospectively included. Three nuclear medicine physicians (2 experienced and 1 resident) independently reviewed PET/CT images. Interpretation of [ 68 Ga]Ga-PSMA-11 PET/CT images was based on PROMISE criteria including miTNM staging and lesions miPSMA expression score visual estimation and PSMA-RADS version 1.0 for a given scan. Readers' agreement was measured using Krippendorff's coefficients Results: Agreement between observers was almost perfect (coefficient ≥ 0.81) for miM; it was substantial (coefficient ≥ 0.61) for the following criteria: miT, miN, PSMA-RADS, and miPSMA expression score of primary PC lesion and metastases. However, agreement was moderate (coefficient = 0.41-0.60) for miPSMA score of positive lymph nodes and for detection of PC primary lesion. Conclusion: Visual interpretation of [ 68 Ga]Ga-PSMA-11 PET/CT images in patients with newly diagnosed PC in a clinical setting leads to at least substantial agreement for PROMISE criteria and PSMA-RADS classification except for PC primary lesion detection and for miPSMA expression scoring of positive lymph nodes that might have been hampered by the interindividual variability of reference organs PSMA expression.

Sarcoidosis and lymphoma often share common features on 18 F-FDG PET/CT, such as intense hypermetabolic lesions of lymph nodes and multiple organs. We aimed at developing and validating radiomics signatures to differentiate sarcoidosis from Hodgkin (HL) and diffuse large B-cell (DLBCL) lymphoma. Methods: We retrospectively collected 420 patients (169 sarcoidosis, 140 HL and 111 DLBCL) who underwent a pretreatment 18 F-FDG PET/CT at the University Hospital of Liege. The studies were randomly distributed to 4 physicians who gave their diagnostic suggestion between the 3 diseases. Individual and pooled performances of physicians were then calculated. The inter-observer variability was evaluated using a sample of 34 studies interpreted by all physicians. Volumes of interest (VOI) were delineated over the lesions and the liver using MIM software, and 215 radiomic features were extracted using Radiomics toolbox. Models were developed combining clinical data (age, gender and weight) and radiomics (original and tumor-to-liver TLR radiomics), with 7 different feature selection approaches and 4 different machine learning (ML) classifiers, to differentiate sarcoidosis and lymphomas on both lesion-based and patient-based approaches. Results: For identifying lymphoma vs. sarcoidosis, physicians' pooled sensitivity, specificity, area under the curve (AUC) and accuracy were 0.

We report the case of an 11-year-old girl who complained about severe asthenia, orthostatic dizziness and abdominal pain for 4 weeks. The primary investigation concluded on febrile urinary tract infection treated by antibiotics. Symptom persistence prompted cardiological and endocrinological investigations. A fluctuation in blood pressure, long QT interval, dilation of the aortic root and left ventricular hypertrophy were documented. Elevated levels of urinary catecholamines together with the presence of a right-sided adrenal mass shown via abdominal ultrasound and magnetic resonance imaging were highly suggestive of a pheochromocytoma. This was confirmed by through iodine-123-metaiodobenzylguathdine ([123I]-mIBG) scintigraphy. Genetic analysis allowed for the exclusion of pathogenic mutations in genes implicated in hereditary paragangliomas and pheochromocytomas but showed a rare somatic mutation in exon 3 of the von Hippel-Lindau gene. The patient was treated with a β-blocker and calcium channel antagonist and underwent laparoscopic right-sided adrenalectomy. Cardiac manifestations resolved soon after surgery indicating that they were secondary to the pheochromocytoma. After 5 years of follow-up, the patient remains asymptomatic without any sign of tumor recurrence. The presence of aortic root dilation, a prolonged QT-interval and left ventricular hypertrophy may be early cardiac manifestations of a pheochromocytoma in a child and should prompt this diagnosis to be evoked.

Purpose Metastatic bone disease (MBD) is the most common form of metastases, most frequently deriving from prostate cancer. MBD is screened with bone scintigraphy (BS), which have high sensitivity but low specificity for the diagnosis of MBD, often requiring further investigations. Deep learning (DL) - a machine learning technique designed to mimic human neuronal interactions- has shown promise in the field of medical imaging analysis for different purposes, including segmentation and classification of lesions. In this study, we aim to develop a DL algorithm that can classify areas of increased uptake on bone scintigraphy scans. Methods We collected 2365 BS from three European medical centres. The model was trained and validated on 1203 and 164 BS scans respectively. Furthermore we evaluated its performance on an external testing set composed of 998 BS scans. We further aimed to enhance the explainability of our developed algorithm, using activation maps. We compared the performance of our algorithm to that of 6 nuclear medicine physicians. Results The developed DL based algorithm is able to detect MBD on BSs, with high specificity and sensitivity (0.80 and 0.82 respectively on the external test set), in a shorter time compared to the nuclear medicine physicians (2.5 min for AI and 30 min for nuclear medicine physicians to classify 134 BSs). Further prospective validation is required before the algorithm can be used in the clinic.

No abstract