Background: Knee joint effusion might indicate injury even without bony changes. Automated detection from radiographs could improve the sensitivity of AI algorithms. Purpose: To compare two commercially available AI algorithms, BoneView and RBfracture, in detecting knee joint effusion. Material and Methods: This retrospective study collected 123 lateral knee radiographs. Detection of knee joint effusion by both AI algorithms was compared with two board-certified radiologists with arbitration. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and interobserver agreement (Cohen's Kappa) were calculated. 95% confidence intervals (CI) assessed robustness. McNemar's tests compared sensitivity and specificity between AI algorithms. Results: Knee joint effusion was present in 56% of radiographs. BoneView demonstrated a sensitivity of 0.42 (95% CI: 0.31-0.54), specificity of 1.00 (95% CI: 0.93-1.00), PPV of 1.00 (95% CI: 0.88-1.00), NPV of 0.57 (95% CI: 0.47-0.67), and accuracy of 0.68 (95% CI: 0.59-0.75). RBfracture demonstrated a sensitivity of 0.75 (95% CI: 0.64-0.84), specificity of 0.91 (95% CI: 0.80-0.96), PPV of 0.91 (95% CI: 0.81-0.96), NPV of 0.74 (95% CI: 0.63-0.83), and accuracy of 0.82 (95% CI: 0.74-0.88). Cohen's Kappa was 0.49 (95% CI: 0.35-0.63), indicating moderate agreement between the two AI algorithms. Adding knee joint effusion detection to fracture/dislocation predictions improved sensitivity. Conclusions: Two commercially available AI algorithms demonstrated different operating points for knee joint effusion detection: BoneView achieved high specificity, while RBfracture achieved higher sensitivity. Combining injury and effusion predictions increased sensitivity at the cost of specificity.

Missed fractures are the primary cause of interpretation errors in emergency radiology, and artificial intelligence has recently shown great promise in radiograph interpretation. This study compared the diagnostic performance of two AI algorithms, BoneView and RBfracture, in detecting traumatic abnormalities (fractures and dislocations) in MSK radiographs. AI algorithms analyzed 998 radiographs (585 normal, 413 abnormal), against the consensus of two MSK specialists. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and interobserver agreement (Cohen’s Kappa) were calculated. 95

Regarding our publication, entitled “Discrepancies between Radiology Specialists and Residents in Fracture Detection from Musculoskeletal Radiographs” [...]

(1) Background: The aim of this study was to compare the competence in appendicular trauma radiograph image interpretation between radiology specialists and residents. (2) Methods: In this multicenter retrospective cohort study, we collected radiology reports from radiology specialists (N = 506) and residents (N = 500) during 2018-2021. As a reference standard, we used the consensus of two subspecialty-level musculoskeletal (MSK) radiologists, who reviewed all original reports. (3) Results: A total of 1006 radiograph reports were reviewed by the two subspecialty-level MSK radiologists. Out of the 1006 radiographs, 41% were abnormal. In total, 67 radiographic findings were missed (6.7%) and 31 findings were overcalled (3.1%) in the original reports. Sensitivity, specificity, positive predictive value, and negative predictive value were 0.86, 0.92, 0.91 and 0.88 respectively. There were no statistically significant differences between radiology specialists' and residents' competence in interpretation (p = 0.44). However, radiology specialists reported more subtle cases than residents did (p = 0.04). There were no statistically significant differences between errors made in the morning, evening, or night shifts (p = 0.57). (4) Conclusions: This study found a lack of major discrepancies between radiology specialists and residents in radiograph interpretation, although there were differences between MSK regions and in subtle or obvious radiographic findings. In addition, missed findings found in this study often affected patient treatment. Finally, there are MSK regions where the sensitivity or specificity is below 90%, and these should raise concerns and highlight the need for double reading and should be taken into consideration in radiology education.

Joint effusion due to elbow fractures are common among adults and children. Radiography is the most commonly used imaging procedure to diagnose elbow injuries. The purpose of the study was to investigate the diagnostic accuracy of deep convolutional neural network algorithms in joint effusion classification in pediatric and adult elbow radiographs. This retrospective study consisted of a total of 4423 radiographs in a 3-year period from 2017 to 2020. Data was randomly separated into training (n = 2672), validation (n = 892) and test set (n = 859). Two models using VGG16 as the base architecture were trained with either only lateral projection or with four projections (AP, LAT and Obliques). Three radiologists evaluated joint effusion separately on the test set. Accuracy, precision, recall, specificity, F1 measure, Cohen’s kappa, and two-sided 95% confidence intervals were calculated. Mean patient age was 34.4 years (1–98) and 47% were male patients. Trained deep learning framework showed an AUC of 0.951 (95% CI 0.946–0.955) and 0.906 (95% CI 0.89–0.91) for the lateral and four projection elbow joint images in the test set, respectively. Adult and pediatric patient groups separately showed an AUC of 0.966 and 0.924, respectively. Radiologists showed an average accuracy, sensitivity, specificity, precision, F1 score, and AUC of 92.8%, 91.7%, 93.6%, 91.07%, 91.4%, and 92.6%. There were no statistically significant differences between AUC's of the deep learning model and the radiologists ( p value > 0.05). The model on the lateral dataset resulted in higher AUC compared to the model with four projection datasets. Using deep learning it is possible to achieve expert level diagnostic accuracy in elbow joint effusion classification in pediatric and adult radiographs. Deep learning used in this study can classify joint effusion in radiographs and can be used in image interpretation as an aid for radiologists.

To prospectively compare 18F-prostate-specific membrane antigen (PSMA)-1007 positron emission tomography (PET)/CT, whole-body magnetic resonance imaging (WBMRI) including diffusion-weighted imaging (DWI) and standard computed tomography (CT), in primary nodal staging of prostate cancer (PCa). Men with newly diagnosed unfavourable intermediate- or high-risk PCa prospectively underwent 18F-PSMA-1007 PET/CT, WBMRI with DWI and contrast-enhanced CT within a median of 8 days. Six readers (two for each modality) independently reported pelvic lymph nodes as malignant, equivocal or benign while blinded to the other imaging modalities. Sensitivity, specificity and accuracy were reported according to optimistic (equivocal lesions interpreted as benign) and pessimistic (equivocal lesions interpreted as malignant) analyses. The reference standard diagnosis was based on multidisciplinary consensus meetings where available histopathology, clinical and follow-up data were used. Seventy-nine patients completed all the imaging modalities, except for one case of interrupted WBMRI. Thirty-one (39%) patients had pelvic lymph node metastases, which were detected in 27/31 (87%), 14/31 (45%) and 8/31 (26%) patients by 18F-PSMA-1007 PET/CT, WBMRI with DWI and CT, respectively (optimistic analysis). In 8/31 (26%) patients, only 18F-PSMA-1007 PET/CT detected malignant lymph nodes, while the other two imaging modalities were reported as negative. At the patient level, sensitivity and specificity values for 18F-PSMA-1007 PET/CT, WBMRI with DWI and CT in optimistic analysis were 0.87 (95%CI 0.71–0.95) and 0.98 (95%CI 0.89–1.00), 0.37 (95%CI 0.22–0.55) and 0.98 (95%CI 0.89–1.00) and 0.26 (95%CI 0.14–0.43) and 1.00 (95%CI 0.93–1.00), respectively. 18F-PSMA-1007 PET/CT showed significantly greater sensitivity in nodal staging of primary PCa than did WBMRI with DWI or CT, while maintaining high specificity. Clinicaltrials.gov ID: NCT03537391

Background: Computed tomography (CT) and bone scintigraphy (BS) are the imaging modalities currently used for distant metastasis staging of prostate cancer (PCa). Objective: To compare standard staging modalities with newer and potentially more accurate imaging modalities. Design, setting, and participants: This prospective, single-centre trial (NCT03537391) enrolled 80 patients with newly diagnosed high-risk PCa (International Society of Urological Pathology grade group >= 3 and/or prostate-specific antigen [PSA] >= 20 and/or cT >= T3; March 2018-June 2019) to undergo primary metastasis staging with two standard and three advanced imaging modalities. Outcome measurements and statistical analysis: The participants underwent the following five imaging examinations within 2 wk of enrolment and without a prespecified sequence: BS, CT, Tc-99m-hydroxymethylene diphosphonate (Tc-99m-HMDP) single-photon emission computed tomography (SPECT)-CT, 1.5 T whole-body magnetic resonance imaging (WBMRI) using diffusion-weighted imaging, and F-18-prostate-specific membrane antigen-1007 (F-18-PSMA-1007) positron emission tomography(PET)-CT. Each modality was reviewed by two independent experts blinded to the results of the prior studies, who classified lesions as benign, equivocal, or malignant. Pessimistic and optimistic analyses were performed to resolve each equivocal diagnosis. The reference standard diagnosis was defined using all available information accrued during at least 12 mo of clinical follow-up. Patients with equivocal reference standard diagnoses underwent MRI and/or CT to search for the development of anatomical correspondence. PSMA PET-avid lesions without histopathological verification were rated to be malignant only if there was a corresponding anatomical finding suspicious for malignancy at the primary or follow-up imaging. Results and limitations: Seventy-nine men underwent all imaging modalities except for one case of interrupted MRI. The median interval per patient between the first and the last imaging study was 8 d (interquartile range [IQR]: 6-9). The mean age was 70 yr (standard deviation: 7) and median PSA 12 ng/mL (IQR:7-23). The median follow-up was 435 d (IQR: 378-557). Metastatic disease was detected in 20 (25%) patients. The imaging modality F-18-PSMA-1007 PET-CT had superior sensitivity and highest inter-reader agreement. The area under the receiver-operating characteristic curve (AUC) values for bone metastasis detection with PSMA PET-CT were 0.90 (95% confidence interval [CI]: 0.85-0.95) and 0.91 (95% CI: 0.87-0.96) for readers 1 and 2, respectively, while the AUC values for BS, CT, SPECT-CT, and WBMRI were 0.71 (95% CI: 0.58-0.84) and 0.8 (95% CI: 0.67-0.92), 0.53 (95% CI: 0.39-0.67) and 0.66 (95% CI: 0.54-0.77), 0.77 (95% CI: 0.65-0.89) and 0.75 (95% CI: 0.62-0.88), and 0.85 (95% CI: 0.74-0.96) and 0.67 (95% CI: 0.54-0.80), respectively, for the other four pairs of readers. The imaging method F-18-PSMA-1007 PET-CT detected metastatic disease in 11/20 patients in whom standard imaging was negative and influenced clinical decision making in 14/79 (18%) patients. In 12/79 cases, false positive bone disease was reported only by PSMA PET-CT. Limitations included a nonrandomised study setting and few histopathologically validated suspicious lesions. Conclusions: Despite the risk of false positive bone lesions, F-18-PSMA-1007 PET-CT outperformed all other imaging methods studied for the detection of primary distant metastasis in high-risk PCa. Patient summary: In this report, we compared the diagnostic performance of conventional and advanced imaging. It was found that F-18-prostate-specific membrane antigen-1007 positron emission tomography/computed tomography (F-18-PSMA-1007 PET-CT) was superior to the other imaging modalities studied for the detection of distant metastasis at the time of initial diagnosis of high-risk prostate cancer. PSMA PET-CT also appears to detect some nonmetastatic bone lesions. (C) 2020 The Author(s). Published by Elsevier B.V. on behalf of European Association of Urology.

You have accessJournal of UrologyProstate Cancer: Staging I (MP62)1 Apr 2020MP62-18 PRIMARY METASTASIS STAGING USING 18F-PSMA-1007 PET-CT IN HIGH-RISK PROSTATE CANCER Mikael Anttinen*, Otto Ettala, Simona Malaspina, Ivan Jambor, Minna Sandell, Sami Kajander, Irina Rinta-Kiikka, Jukka Schildt, Ekaterina Saukko, Pentti Rautio, Kirsi L. Timonen, Tommi Noponen, Jani Saunavaara, Eliisa Löyttyniemi, Pekka Taimen, Jukka Kemppainen, Peter B. Dean, Roberto Sequeiros Blanco, Hannu J. Aronen, Marko Seppänen, and Peter J. Boström Mikael Anttinen*Mikael Anttinen* More articles by this author , Otto EttalaOtto Ettala More articles by this author , Simona MalaspinaSimona Malaspina More articles by this author , Ivan JamborIvan Jambor More articles by this author , Minna SandellMinna Sandell More articles by this author , Sami KajanderSami Kajander More articles by this author , Irina Rinta-KiikkaIrina Rinta-Kiikka More articles by this author , Jukka SchildtJukka Schildt More articles by this author , Ekaterina SaukkoEkaterina Saukko More articles by this author , Pentti RautioPentti Rautio More articles by this author , Kirsi L. TimonenKirsi L. Timonen More articles by this author , Tommi NoponenTommi Noponen More articles by this author , Jani SaunavaaraJani Saunavaara More articles by this author , Eliisa LöyttyniemiEliisa Löyttyniemi More articles by this author , Pekka TaimenPekka Taimen More articles by this author , Jukka KemppainenJukka Kemppainen More articles by this author , Peter B. DeanPeter B. Dean More articles by this author , Roberto Sequeiros BlancoRoberto Sequeiros Blanco More articles by this author , Hannu J. AronenHannu J. Aronen More articles by this author , Marko SeppänenMarko Seppänen More articles by this author , and Peter J. BoströmPeter J. Boström More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000000937.018AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Computed tomography (CT) and bone scintigraphy are currently the mainly used imaging modalities for primary metastasis staging of high-risk prostate cancer (PCa). This trial was designed to compare these standard staging modalities with three potentially more accurate imaging modalities: single photon emission computed tomography-CT (SPECT-CT), magnetic resonance imaging (MRI), prostate specific membrane antigen positron emission tomography (PSMA PET). METHODS: This prospective, registered (NCT03537391), ethics committee -approved, single-centre, open-label, single-arm trial enrolled patients with primary high-risk PCa. Results of standard bone scintigraphy and CT (chest, abdomen and pelvis) were compared with 99mTc-HMDP SPECT-CT, 1.5T WBMRI using diffusion weighted imaging and 18F-PSMA-1007 PET-CT. Each imaging modality was reviewed by two separate modality-based specialists blinded for the other modalities. The lesions were initially classified as benign, equivocal or malignant. Pessimistic and optimistic analyses were performed to resolve equivocal lesion status. Based on clinical data, including follow-up investigations (imaging, PSA kinetics, and histopathological specimens) the best valuable comparator was defined at lesion level in multidisciplinary consensus meetings. The lesions reported from each modality were rated according to this comparator, which was either benign or malignant. RESULTS: 79 men were included and underwent all imaging modalities, except for one MRI, which was cancelled due to claustrophobia. Mean age was 70 years and median PSA 12 ng/ml (range: 3-2000). Metastatic disease was detected in 27 patients. In pessimistic and optimistic analysis at patient, region (bone) and lesion levels, PSMA PET-CT was superior to all other modalities concerning sensitivity and the AUC values at the bone region (pessimistic analysis) [PET reader 1:0·94 (95%CI;0·90-0·99), PET reader 2: 0·96 (95%CI;0·92-0·99)], while maintaining high specificity and demonstrating the highest inter-reader agreement (PSMA PET κ=0.82;95%CI 0.69-0.95). The sensitivity values in pessimistic analysis at patient level were 0.93 (95%CI;0.77-0.98) and 0.96 (95%CI;0.82-0.99) for PSMA PET reader 1 and reader 2, respectively. PSMA PET-CT revealed metastatic disease in 18/27 patients where standard imaging was negative and 11/27 patients where all other imaging were negative. CONCLUSIONS: 18F-PSMA-1007 PET-CT significantly outperformed all other imaging methods in primary metastasis staging of high-risk PCa. We recommend further evaluation of this method as a new reference standard. Source of Funding: None. © 2020 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 203Issue Supplement 4April 2020Page: e952-e952 Advertisement Copyright & Permissions© 2020 by American Urological Association Education and Research, Inc.MetricsAuthor Information Mikael Anttinen* More articles by this author Otto Ettala More articles by this author Simona Malaspina More articles by this author Ivan Jambor More articles by this author Minna Sandell More articles by this author Sami Kajander More articles by this author Irina Rinta-Kiikka More articles by this author Jukka Schildt More articles by this author Ekaterina Saukko More articles by this author Pentti Rautio More articles by this author Kirsi L. Timonen More articles by this author Tommi Noponen More articles by this author Jani Saunavaara More articles by this author Eliisa Löyttyniemi More articles by this author Pekka Taimen More articles by this author Jukka Kemppainen More articles by this author Peter B. Dean More articles by this author Roberto Sequeiros Blanco More articles by this author Hannu J. Aronen More articles by this author Marko Seppänen More articles by this author Peter J. Boström More articles by this author Expand All Advertisement PDF downloadLoading ...

18F-Fluorodeoxyglucose positron-emission tomography (18F-FDG-PET) with computed tomography (CT) is effective for diagnosing large vessel vasculitis, but its usefulness in accurately diagnosing suspected, unselected vasculitis remains unknown. We evaluated the feasibility of 18F-FDG-PET/CT in real-life cohort of patients with suspicion of vasculitis. The effect of the dose and the timing of glucocorticoid (GC) medication on imaging findings were in special interest. 82 patients with suspected vasculitis were evaluated by whole-body 18F-FDG-PET/CT. GC treatment as prednisolone equivalent doses at the scanning moment and before imaging was evaluated. 38/82 patients were diagnosed with vasculitis. Twenty-one out of 38 patients had increased 18F-FDG accumulation in blood vessel walls indicating vasculitis in various sized vessels. Vasculitis patients with a positive vasculitis finding in 18F-FDG-PET/CT had a significantly shorter duration of GC use (median = 4.0 vs 7.0 days, P=0.034), and they used lower GC dose during the PET scan (median dose = 15.0 mg/day vs 40.0 mg/day, p=0.004) compared to 18F-FDG-PET/CT-negative patients. Vasculitis patients with a positive 18F-FDG-PET/CT result had significantly higher C-reactive protein (CRP) than patients with a negative 18F-FDG-PET/CT finding (mean value = 154.5 vs 90.4 mg/L, p=0.018). We found that 18F-FDG-PET/CT positivity was significantly associated with a lower dose and shorter duration of GC medication and higher CRP level in vasculitis patients. 18F-FDG-PET/CT revealed clinically significant information in over half of the patients and was effective in confirming the final diagnosis.

Background: Computed tomography (CT) and bone scintigraphy are the imaging modalities currently used for primary metastasis staging of high-risk prostate cancer (PCa). This trial compared these standard staging modalities with potentially more accurate imaging modalities: single photon emission computed tomography-CT (SPECT-CT), magnetic resonance imaging (MRI), prostate specific membrane antigen positron emission tomography (PSMA PET).Methods: This prospective, registered, single-centre, open-label, single-arm trial enrolled patients with primary high-risk PCa. Results of bone scintigraphy and CT were compared with 99mTc-HMDP SPECT-CT, 1.5T whole-body MRI using diffusion-weighted imaging and 18 F-PSMA-1007 PET-CT. Each imaging modality was reviewed by two independent experts blinded for the other modalities. The lesions were classified as benign, equivocal or malignant. Pessimistic and optimistic analyses were performed to resolve equivocal lesion status. Based on clinical data, including follow-up investigations, the best valuable comparator was defined at lesion level in multidisciplinary consensus meetings.Findings: 79 men were included and underwent all imaging modalities, except for one cancelled MRI due to claustrophobia. Mean age was 70 years and median PSA 12 ng/ml (range: 3-2000). Metastatic disease was detected in 27 (34%) patients. In pessimistic and optimistic analysis at patient, region and lesion levels, PSMA PET-CT was superior to all other modalities concerning sensitivity, and the area under curve values (AUC) at the bone region, while maintaining high specificity and demonstrating the highest inter-reader agreement. AUC for detection of bone metastasis for PSMA PET-CT was 0·94 (95%Cl;0·90-0·99) and 0·96 (95%CI;0·92-0·99) (reader 1, and reader 2, respectively) while AUC for all other modalities was in the range of 0·55-0·76. PSMA PET-CT revealed metastatic disease in 18/27 patients where standard imaging was negative.Interpretation: 18F-PSMA-1007 PET-CT outperformed other imaging methods in primary metastasis staging of high-risk PCa. We recommend further evaluation of this method as a new reference standard.Trial Registration number: (ClinicalTrials.gov NCT03537391).Funding Statement: This study was financially supported by grants from Finnish Government Research and Development Funds for Medical Research, Turku University Hospital and TYKS-SAPA Research Fund.Declaration of Interests: Dr. Anttinen reports grants from Profound Medical Inc, Finnish Urological Research Foundation and Finnish Urological Association, outside the submitted work. Dr. Ettala reports non-financial support from Ferring Pharmaceuticals Inc, SwanMedica and Pierre-Fabre Pharma Norden AB, and personal fees from Astellas, outside the submitted work. Dr. Sandell reports personal fees from Roche, outside the submitted work. Dr. Taimen reports personal fees from Roche, AstraZeneca and MSD, and non-financial support from MSD, all outside the submitted work. Dr. Boström reports grants from the Cancer Foundation Finland, personal fees from Profound Medical Inc and Janssen-Cilag Company, outside the submitted work. The other authors declare that there is no conflict of interest regarding the publication of this article.Ethical Approval Statement: The trial protocol, included in the Supplemental material, was approved by the ethics committee of the Hospital District of Southwest Finland, and written informed consent was obtained from all participants. The trial was performed in accordance with the principles of the Declaration of Helsinki.

Despite recent technological advances allowing for quantitative single-photon emission computed tomography (SPECT), quantitative SPECT has not been widely used in the clinical practice. The aim of this study is to evaluate the feasibility of quantitative SPECT for measuring metastatic bone uptake in breast and prostate cancer by comparing standard uptake values (SUVs) measured with 99mTc-HDP SPECT/CT and 18F-NaF PET/CT. Twenty-six breast and 27 prostate cancer patients at high risk of bone metastases underwent both 99mTc-HDP SPECT/CT and 18F-NaF PET/CT within 14 days of each other. The SPECT and PET data were reconstructed using ordered-subset expectation-maximization algorithms achieving quantitative images. Metastatic and benign skeletal lesions visible in both data sets were identified, and their maximum, peak, and mean SUVs (SUVmax, SUVpeak, and SUVmean) were determined. SUV ratios (SUVRs) between the lesions and adjacent normal appearing bone were also calculated. Linear regression was used to evaluate the correlations between the SUVs of SPECT and PET and Bland-Altman plots to evaluate the differences between the SUVs and SUVRs of SPECT and PET. A total of 231 skeletal lesions, 129 metastatic and 102 benign, were analyzed. All three SUV measures correlated very strongly between SPECT and PET (R2 ≥ 0.80, p < 0.001) when all lesions were included, and the PET SUVs were significantly higher than SPECT SUVs (p < 0.001). The median differences were 21%, 12%, and 19% for SUVmax, SUVpeak, and SUVmean, respectively. On the other hand, the SUVRs were similar between SPECT and PET with median differences of 2%, − 9%, and 2% for SUVRmax, SUVRpeak, and SUVRmean, respectively. The strong correlation between SUVs and similar SUVRs of 99mTc-HDP SPECT/CT and 18F-NaF PET/CT demonstrate that SPECT is an applicable tool for clinical quantification of bone metabolism in osseous metastases in breast and prostate cancer patients.

Coronary computed tomography angiography (CCTA) can accurately rule out obstructive coronary artery disease (CAD), but functional evaluation is recommended before revascularization. In our center, hybrid imaging with CCTA followed by selective assessment of absolute stress myocardial blood flow (MBF

BackgroundMachine learning (ML) represents a family of algorithms that has rapidly developed within the last years in a wide variety of knowledge areas. ML is able to elucidate and grasp complex patterns from data in order to approach prediction and classification problems. The present narrative review summarizes fundamental notions in ML as well as the evidence of its application in standard cardiac imaging and the potential for implementation in cardiac hybrid imaging.ResultsML, and in particular Deep Learning, has begun to revolutionize medical imaging though the optimization of diagnostic and prognostic estimations at the individual-patient level. On the other hand, the spread and availability of high quality non-invasive imaging has provided growing amounts of data in the characterization of suspected cardiovascular diseases. At the same time, modern combined imaging equipment has set the ground for the concept of hybrid imaging to develop. Cardiac hybrid imaging refers to the combination of diagnostic images and offers the possibility to comprehensively characterize the heart and great vessels when a pathology is suspected or clinically known. Analysis and integration of large amounts of cardiac hybrid imaging data (and corresponding clinical profiles) constitutes a highly complex process and ML will likely be able to enhance it in the near future.ConclusionML conveys novel and powerful approaches in the processing of large and complex datasets that may include images as well as imaging-derived data. Given the growing amount of data in the realm of cardiac hybrid imaging and the rapid development of ML, it is highly desirable to implement and test ML in the optimization of our multimodality imaging diagnostic and prognostic evaluations in cardiovascular disease.

Background. Several techniques have been introduced to treat acromioclavicular (AC) separation using the semitendinosus tendon as a graft for coracoclavicular (CC) ligament reconstruction. However, the tendon may have been used previously or the patient may not want it harvested. Hence, synthetic tendon transfers have become increasingly popular. Methods. Five patients with chronic AC separations were treated. A synthetic polyurethane urea tendon graft (Artelon Tissue Reinforcement [ATR]) was chosen for its ability to partially transform into connective tissue. The patient follow-up period lasted 45 to 60 months. Results. The mean preoperative Constant Score increased from 64.8 to 100 postoperatively. The mean preoperative Simple Shoulder Test increased from 7.2 to 12 postoperatively. The mean postoperative increase of the CC distance was 1.5 mm. The mean expansion of the clavicular drill hole from the original was 2.1 mm. According to the postoperative magnetic resonance imaging, the grafts had healed well and the cross-sections of the grafts were up to 10.5 mm between the coracoid and the clavicle. Discussion. The synthetic ATR tendon strip was a practical method for reconstructing a torn CC ligament complex. The ATR graft appears promising for future CC ligament reconstructions.

Background:The positron emission tomography (PET) radiotracer 18F-sodium fluoride (18F-NaF) preferentially binds to areas of microcalcification.We have previously demonstrated vascular 18F-NaF uptake in human carotid and coronary atherosclerosis that correlates with necrotic inflammation and plaque rupture.In patients with abdominal aortic aneurysm (AAA), we assessed whether 18F-NaF PET-CT can predict AAA growth and clinical outcomes.Methods: We compared 18F-NaF uptake in normal and aneurysmal aortae between 20 patients with AAA and 20 control volunteers without AAA matched for age, sex and smoking status.In a prospective observational cohort study, 72 patients with AAA >40 mm anteroposterior diameter underwent 18F-NaF PET-CT, CT angiogram and calcium scoring.18F-NaF uptake was quantified using tissueto-background ratio (TBR).Patients with AAA were followed up with ultrasound for at least 1 year.The primary endpoints were aneurysm expansion and the composite of AAA repair or rupture.Results: Higher 18F-NaF uptake was observed within the AAA, both when compared to the controls (p=0.023)and within non-aneurysmal regions of the abdominal aorta in patients with AAA (p=0.004).18F-NaF uptake was similar in the thoracic aorta (p=0.970) and the non-aneurysmal aorta (p=0.911) of patients and controls.In the observational cohort, patients with AAA were predominantly elderly (73±7 years) men (85%) with a baseline aneurysm diameter of 48.8±7.7 mm.During 510±196 days of follow-up, there were 19 aneurysm repairs (26.4%) and 3 ruptures (4.2%).18F-NaF uptake in the most-diseased segment (MDS) of the aneurysm was associated with future growth rate (p=0.006)even after adjustment for age, sex, baseline diameter, blood pressure and body-mass index (p=0.042).Aneurysms in the highest tertile of 18F-NaF uptake expanded 2.5 times more rapidly than those in the lowest tertile (3.10 [3.58] vs 1.24 [2.41] mm/year, p=0.008) and were more than twice as likely to experience AAA repair or rupture (15.3% vs 5.6%, log-rank p=0.043).The association between 18F-NaF uptake (log2MDS TBRmax) and risk of repair or rupture remained even after adjustment for age, sex, gender, blood pressure, body-mass index and aneurysm diameter (HR 2.49, 95% CI1.07, 5.78; p=0.034).In contrast, the CT calcium scoring (Agatston score) was not associated with aneurysm expansion or events (both p>0.05).Conclusions: For the first time, we have demonstrated that 18F-NaF PET-CT is a novel approach to the identification of disease activity in patients with AAA and predicts the rate of aneurysm growth and clinical events, independent of established clinical risk factors including aneurysm diameter.

OBJECTIVES The purpose of this study was to evaluate the prognostic value of sequential hybrid imaging strategy in which positron emission tomography (PET) perfusion imaging is performed selectively in patients with suspected obstructive coronary artery disease (CAD) on coronary computed tomography angiography (CTA). BACKGROUND Coronary CTA is an accurate diagnostic test for excluding obstructive CAD. However, the positive predictive value is suboptimal. METHODS We investigated 864 consecutive symptomatic patients with intermediate probability of CAD who adhered to the sequential imaging approach. PET myocardial perfusion imaging using 15O-labeled water during adenosine stress was performed when suspected obstructive stenosis was present on coronary CTA. The major adverse events (AEs) including all-cause mortality, myocardial infarction (MI), and unstable angina pectoris (UAP) were recorded. RESULTS During a median follow-up of 3.6 years, 16 deaths, 10 MIs, and 5 UAPs occurred. Obstructive CAD was excluded by coronary CTA in 462 (53%) patients who had significantly lower annual AE rate than did patients with suspected obstructive stenosis on coronary CTA (0.4% vs. 1.5%; p = 0.003). The latter underwent PET study, on which 195 (49%) had normal and 207 had abnormal perfusion. The annual rate of AEs was 5 times higher in those with abnormal perfusion than with normal perfusion (2.5% vs. 0.5%; p = 0.004). Patients with normal perfusion had AE rate comparable to patients without obstructive CAD on coronary CTA (p = 0.77). CONCLUSIONS In patients with suspected CAD obstructive disease can be excluded in 53% of patients by coronary CTA, and these patients have good outcome. About one-half (49%) of the remaining patients have normal perfusion and event rate comparable to patients without obstructive CAD on coronary CTA while patients with ischemia have clearly worse outcome. Sequential approach utilizing anatomical imaging by coronary CTA followed by selective functional perfusion imaging is a feasible strategy to diagnose and risk-stratify patients with suspected CAD. (C) 2017 by the American College of Cardiology Foundation.