Explore the vast range of titles available.

Objectives To evaluate if radiomics with machine learning can differentiate between F-18-fluorodeoxyglucose (FDG)-avid breast cancer metastatic lymphadenopathy and FDG-avid COVID-19 mRNA vaccine–related axillary lymphadenopathy. Materials and methods We retrospectively analyzed FDG-positive, pathology-proven, metastatic axillary lymph nodes in 53 breast cancer patients who had PET/CT for follow-up or staging, and FDG-positive axillary lymph nodes in 46 patients who were vaccinated with the COVID-19 mRNA vaccine. Radiomics features (110 features classified into 7 groups) were extracted from all segmented lymph nodes. Analysis was performed on PET, CT, and combined PET/CT inputs. Lymph nodes were randomly assigned to a training ( n = 132) and validation cohort ( n = 33) by 5-fold cross-validation. K-nearest neighbors (KNN) and random forest (RF) machine learning models were used. Performance was evaluated using an area under the receiver-operator characteristic curve (AUC-ROC) score. Results Axillary lymph nodes from breast cancer patients ( n = 85) and COVID-19-vaccinated individuals ( n = 80) were analyzed. Analysis of first-order features showed statistically significant differences ( p < 0.05) in all combined PET/CT features, most PET features, and half of the CT features. The KNN model showed the best performance score for combined PET/CT and PET input with 0.98 (± 0.03) and 0.88 (± 0.07) validation AUC, and 96% (± 4%) and 85% (± 9%) validation accuracy, respectively. The RF model showed the best result for CT input with 0.96 (± 0.04) validation AUC and 90% (± 6%) validation accuracy. Conclusion Radiomics features can differentiate between FDG-avid breast cancer metastatic and FDG-avid COVID-19 vaccine–related axillary lymphadenopathy. Such a model may have a role in differentiating benign nodes from malignant ones. Key Points • Patients who were vaccinated with the COVID-19 mRNA vaccine have shown FDG-avid reactive axillary lymph nodes in PET-CT scans. • We evaluated if radiomics and machine learning can distinguish between FDG-avid metastatic axillary lymphadenopathy in breast cancer patients and FDG-avid reactive axillary lymph nodes. • Combined PET and CT radiomics data showed good test AUC (0.98) for distinguishing between metastatic axillary lymphadenopathy and post-COVID-19 vaccine–associated axillary lymphadenopathy. Therefore, the use of radiomics may have a role in differentiating between benign from malignant FDG-avid nodes.

Purpose: The goal of this study was to evaluate the outpatient workflow efficiency of an optimized facility (OF) compared to an established reference facility (RF) for abdominal magnetic resonance imaging (MRI). Methods: In this retrospective study, we analyzed 2,723 contrast-enhanced liver and prostate MRI examinations conducted between March 2022 and April 2024. All examinations were performed on 3T scanners (MAGNETOM Vida, Siemens Healthineers) at two different imaging facilities within our institution. The optimized facility featured a three-bay setup, with each bay consisting of one magnet, two dockable tables, and one dedicated preparation room, while the reference facility utilized a single scanner-single table setup with one dedicated preparation room. Workflow metrics were extracted from scanner logs and electronic health records. Three-way ANOVA and chi-square tests were used to assess the impact of facility design, body region, and date on workflow metrics. Results: The OF significantly reduced mean table turnaround times (4.6 min vs. 8.3 min, p  < 0.001) and achieved shorter total process cycle times for both liver (30.6 min vs. 32.7 min, p  < 0.01) and prostate exams (32.5 min vs. 36.4 min, p  < 0.001) compared to the RF. Additionally, the OF achieved turnaround times of ≤ 1 min in 37.2% of exams, compared to just 0.6% at the RF ( p  < 0.001). On-time performance was also notably higher at the OF (79.4% vs. 66.0%, p  < 0.001). Furthermore, the mean time from patient arrival to exam start was reduced by 9 min at the OF ( p  < 0.001). Minor differences in acquisition times were observed between facilities, with both benefiting from deep learning reconstruction techniques. Conclusion: The optimized MRI facility demonstrated superior outpatient workflow efficiency compared to an already efficient reference facility, particularly in table turnover time, resulting in increased patient throughput for abdominal MRI examinations. These findings highlight that even highly efficient MRI facilities can significantly benefit from comprehensive redesign strategies.

PurposeTo externally validate an algorithm for non-invasive differentiation of hepatic mucinous cystic neoplasms (MCN) from benign hepatic cysts (BHC), which differ in management.MethodsPatients with cystic liver lesions pathologically confirmed as MCN or BHC between January 2005 and March 2022 from multiple institutions were retrospectively included. Five readers (2 radiologists, 3 non-radiologist physicians) independently reviewed contrast-enhanced CT or MRI examinations before tissue sampling and applied the 3-feature classification algorithm described by Hardie et al. to differentiate between MCN and BHC, which had a reported accuracy of 93.5%. The classification was then compared to the pathology results. Interreader agreement between readers across different levels of experience was evaluated with Fleiss’ Kappa.ResultsThe final cohort included 159 patients, median age of 62 years (IQR [52.0, 70.0]), 66.7% female (106). Of all patients, 89.3% (142) had BHC, and the remaining 10.7% (17) had MCN on pathology. Agreement for class designation between the radiologists was almost perfect (Fleiss’ Kappa 0.840, p < 0.001). The algorithm had an accuracy of 98.1% (95% CI [94.6%, 99.6%]), a positive predictive value of 100.0% (95% CI [76.8%, 100.0%]), a negative predictive value of 97.9% (95% CI [94.1%, 99.6%]), and an area under the receiver operator characteristic curve (AUC) of 0.911 (95% CI [0.818, 1.000]).ConclusionThe evaluated algorithm showed similarly high diagnostic accuracy in our external, multi-institutional validation cohort. This 3-feature algorithm is easily and rapidly applied and its features are reproducible among radiologists, showing promise as a clinical decision support tool.

This paper provides an overview of the different deep convolutional neural network (DCNNs) architectures that have been investigated in the past years for the generation of synthetic computed tomography (CT) or pseudo-CT from magnetic resonance (MR). The U-net, the Atrous-net and the Residual-net architectures were analyzed, implemented and compared. Each network was implemented using 2D filters and 3D filters with 2D slices and 3D patches respectively as inputs. Two datasets were used for training and evaluation. The first one is composed by pairs of 3D T1-weighted MR and Low-dose CT images from the head of 19 healthy women. The second database contains dual echo Dixon-VIBE MR images and CT images from the pelvis of 13 colorectal and 6 prostate cancer patients. Bone structures in the target anatomy were key in choosing the right deep learning approach. This work provides a deep explanation of the architectures in order to know which DCNN fits better each medical application. According to this study, the 3D U-net architecture would be the best option to generate head pseudo-CTs while the 2D Residual-net provides the most accurate results for the pelvis anatomy.

ObjectivesDespite the advantages of prostate-specific membrane antigen (PSMA)-PET/MR over PSMA-PET/CT, its relatively long scanning time and suboptimal PET attenuation correction necessitate careful assessment of the most appropriate setting for this type of study. We assessed lesion agreement between PSMA-PET/MR and PSMA-PET/CT in patients undergoing initial evaluation of prostate cancer.MethodsThis was a prospective study of consecutive patients with histological biopsy-proven prostate cancer who underwent pelvic PSMA-PET/MR followed by whole-body PSMA-PET/CT. All conspicuous PSMA-avid foci were counted on PSMA-PET/CT and PSMA-PET/MR with CT or MR correlation. Analysis was performed for intra-prostatic lesions, capsular invasion, seminal vesicle involvement and lymph node and bone involvement. Incidental and significant findings seen on PSMA-PET/CT outside the PSMA-PET/MR field of view were also analysed. Agreements between PSMA-PET/CT and PSMA-PET/MR findings were performed using Cohen’s kappa test.ResultsImage analysis was performed on 140 patients (mean age, 67.3 ± 8.2 years). Agreement between PSMA PET/CT and PSMA-PET/MR was very good for intra-prostatic PSMA-avid foci (K = 0.85) and pelvic lymph nodes (K = 0.98), good for PSMA-avid bone metastases (K = 0.76) and fair for prostatic capsular invasion (K = 0.25) and seminal vesicle involvement (K = 0.31). Twelve patients (8.5%) had incidental findings and two patients (1.4%) had clinically significant findings.ConclusionLimited pelvic PSMA-PET/MR has very good agreement with PET/CT regarding PSMA-avid prostatic, regional lymph nodes and bone lesions, and is superior to PET/CT with regard to capsular invasion and seminal vesicle involvement.Key Points• Limited pelvic PSMA-PET/MR is superior to whole-body PSMA-PET/CT in detecting extensions of localised disease, mainly due to the high soft tissue resolution of MR.• Limited pelvic PSMA-PET/MR may be useful for initial evaluation of histological biopsy-proven prostate cancer.• Further studies are warranted to evaluate limited pelvic PSMA-PET/MR for screening and active surveillance in selected populations.

Purpose To evaluate the effect of CT perfusion (CTp) protocol modifications on quantitative perfusion parameters, radiation dose and data processing time. Materials & methods CTp datasets of 30 patients (21M:9F) with rectal ( n  = 24) or retroperitoneal ( n  = 6) tumours were studied. Standard CTp protocol included 50 sec cine-phase (0.5 sec/rotation) and delayed-phase after 70 ml contrast bolus at 5–7 ml/sec. CTp-data was sub-sampled to generate modified datasets ( n  = 105) with cine-phase( n  = 15) alone, varying cine-phase duration (20-40 sec, n  = 45) and varying temporal sampling-interval (1–3 sec, n  = 45). The estimated CTp parameters (BF,BV,MTT&PS) and radiation dose of standard CTp served as reference for comparison. Results CTp with 50 sec cine-phase showed moderate to high correlation with standard CTp for BF&MTT ( r  = 0.96&0.85) and low correlation for BV (0.75, p  = 0.04). Limiting cine-phase duration to 30 sec demonstrated comparable results for BF&MTT, while considerable variation in CTp values existed at 20 sec. There was moderate-to-high correlation of CTp parameters with sampling interval of 1&2 sec ( r  = 0.83–0.97, p  > 0.05), while at 3 sec only BF showed high correlation ( r  = 0.96, p  = 0.05). Increasing sampling interval (47–60%) and reducing cine-phase duration substantially reduced dose(30.8–65%) which paralleled reduced data processing time (3–10 min). Conclusion Limiting CTp cine-phase to 30 sec results in comparable BF&MTT values and increasing cine-phase sampling interval to 2 sec provides good correlation for all CTp parameters with substantial dose reduction and improved computational efficiency.

A 41-year-old woman with presumed Alport’s syndrome was admitted with bloody stools and rectal pain. Six months earlier, she had undergone deceased-donor renal transplantation. On admission, the blood pressure was 85/46 mm Hg, the hemoglobin level 6 g per deciliter, and the platelet count 0 per microliter. A diagnostic test was performed.

BackgroundHereditary syndromes such as tuberous sclerosis complex (TSC) account for 10% of pancreatic neuroendocrine tumors (PNETs). Surgical intervention is the current standard of care for sporadic PNETs (spPNETs) that are >2 cm in size. We compared the long-term outcomes of resected TSC-PNETs with patients with spPNETs.MethodsWe conducted a retrospective review of perioperative data and outcomes of TSC-PNETs compared with spPNETs. Inclusion criteria involved selecting patients whose tumors were no larger than 5.1 cm, the maximum size observed in the TSC-PNET group.ResultsOf the 347 patients resected for PNETs, 14 were TSC-PNETs and 241 were non-functional spPNETs. The median age for the whole cohort was 56 years (interquartile range [IQR] 21.0) and 47% were female. The median follow-up was 103.8 months (95% confidence interval [CI] 89.2–118.6). Specifically, 14 patients with TSC-PNETs and 194 patients with spPNETs were included. Compared with spPNETs, patients with TSC-PNETs were operated on at a younger age (24.0 vs. 57.5 years; p < 0.001), were more frequently multifocal (28.5% vs. 0.0%; p < 0.001), were more likely to undergo minimally invasive operations (78.6% vs. 24.3%; p < 0.001), and had more R1 resections (28.6% vs. 5.7%; p = 0.006). Local and distant tumor recurrence was only observed in the spPNET group. The 5-year mortality rates for the spPNET and TSC-PNET groups were 6.2% and 0.0%, respectively. No PNET-related deaths were observed among TSC-PNETs.ConclusionNone of the TSC-PNET patients recurred after a median follow-up of 78.0 months. The risk-benefit of aggressive pancreatic operations in TSC-PNET patients is still unclear and our findings suggest a conservative approach should be considered.

PurposeThe role of positron emission tomography/magnetic resonance (PET/MR) in evaluating the local extent of rectal cancer remains uncertain. This study aimed to investigate the possible role of PET/MR versus magnetic resonance (MR) in clinically staging rectal cancer.MethodsThis retrospective two-center cohort study of 62 patients with untreated rectal cancer investigated the possible role of baseline staging PET/MR versus stand-alone MR in determination of clinical stage. Two readers reviewed T and N stage, mesorectal fascia involvement, tumor length, distance from the anal verge, sphincter involvement, and extramural vascular invasion (EMVI). Sigmoidoscopy, digital rectal examination, and follow-up imaging, along with surgery when available, served as the reference standard.ResultsPET/MR outperformed MR in evaluating tumor size (42.5 ± 21.03 mm per the reference standard, 54 ± 20.45 mm by stand-alone MR, and 44 ± 20 mm by PET/MR, P = 0.004), and in identifying N status (correct by MR in 36/62 patients [58%] and by PET/MR in 49/62 cases [79%]; P = 0.02) and external sphincter infiltration (correct by MR in 6/10 and by PET/MR in 9/10; P = 0.003). No statistically significant differences were observed in relation to any other features.ConclusionPET/MR provides a more precise assessment of the local extent of rectal cancers in evaluating cancer length, N status, and external sphincter involvement. PET/MR offers the opportunity to improve clinical decision-making, especially when evaluating low rectal tumors with possible external sphincter involvement.

Background Oligometastatic colorectal cancer (CRC) is potentially curable and demands individualised strategies. Methods This single-centre retrospective study investigated if positron emission tomography (PET)/magnetic resonance imaging (MR) had a clinical impact on oligometastatic CRC relative to the standard of care imaging (SCI). Adult patients with oligometastatic CRC on SCI who also underwent PET/MR between 3/2016 and 3/2019 were included. The exclusion criterion was lack of confirmatory standard of reference, either surgical pathology, intraoperative gross confirmation or imaging follow-up. SCI consisted of contrast-enhanced (CE) computed tomography (CT) of the chest/abdomen/pelvis, abdominal/pelvic CE-MR, and/or CE whole-body PET/CT with diagnostic quality (i.e. standard radiation dose) CT. Follow-up was evaluated until 3/2020. Results Thirty-one patients constituted the cohort, 16 (52%) male, median patient age was 53 years (interquartile range: 49–65 years). PET/MR and SCI results were divergent in 19% (95% CI 9–37%) of the cases, with PET/MR leading to management changes in all of them. The diagnostic accuracy of PET/MR was 90 ± 5%, versus 71 ± 8% for SCI. In a pairwise analysis, PET/MR outperformed SCI when compared to the reference standard ( p  = 0.0412). Conclusions These findings suggest the potential usefulness of PET/MR in the management of oligometastatic CRC.