Continued sac perfusion of popliteal artery aneurysms after ligation and bypass. Relevance of duplex ultrasound surveillance and treatment.

AIM: Conventional management of popliteal artery aneurysms (PAA) through a medial approach may be lon term ineffective. We report our long term rate of continued sac perfusion after ligation and bypass, combined to duplex ultrasound (DUS) surveillance protocol. PATIENTS AND METHODS: Follow-up data of 24 PAA (mean diameter 37.5 ± 8.8 mm) treated by ligation and bypass with eventual adjunctive procedures (direct sac embolization or resection) were collected. The endpoints of the study were the long term rate of continued sac perfusion and the freedom from any reintervention. RESULTS: Twentyfour PAA were treated in 20 patients. Long term follow-up was complete for 19 graft (79.1%). During a median follow-up of 71.2 months (4-168), persistent sac flow was found in 5 legs (26.3%), 4 to 36 months after surgery, without enlargement or rupture. The cumulative Kaplan-Meier survival free from PAA reperfusion at 1, 3, and 6 years was 91.5%, 77.5%, and 71.5%, respectively. Basing on DUS surveillance, late additional procedures were required in 5 patients (25%), to treat sac reperfusion or preserve graft patency. The cumulative Kaplan-Meier survival free from any reintervention at 1, 3, and 6 years was 91.5%, 72.8%, and 67%, respectively. CONCLUSIONS: Conventional management of PAA through a medial approach may be associated to progressive sac expansion. The DUS surveillance protocol remains strongly recommended to detect sac perfusion and suggest the timing of reintervention before rupture occurs. Adjunctive intraoperative procedures could improve the long term results, but further studies on large series are needed. KEY WORDS: Acrylic glue, Duplex ultrasound study, Femoropopliteal bypass, Popliteal artery aneurysm, Ultrasoundguided embolization.

AI-based detection and classification of distal radius fractures using low-effort data labeling: evaluation of applicability and effect of training set size.

OBJECTIVES: To evaluate the performance of a deep convolutional neural network (DCNN) in detecting and classifying distal radius fractures, metal, and cast on radiographs using labels based on radiology reports. The secondary aim was to evaluate the effect of the training set size on the algorithm's performance. METHODS: A total of 15,775 frontal and lateral radiographs, corresponding radiology reports, and a ResNet18 DCNN were used. Fracture detection and classification models were developed per view and merged. Incrementally sized subsets served to evaluate effects of the training set size. Two musculoskeletal radiologists set the standard of reference on radiographs (test set A). A subset (B) was rated by three radiology residents. For a per-study-based comparison with the radiology residents, the results of the best models were merged. Statistics used were ROC and AUC, Youden's J statistic (J), and Spearman's correlation coefficient (ρ). RESULTS: The models' AUC/J on (A) for metal and cast were 0.99/0.98 and 1.0/1.0. The models' and residents' AUC/J on (B) were similar on fracture (0.98/0.91; 0.98/0.92) and multiple fragments (0.85/0.58; 0.91/0.70). Training set size and AUC correlated on metal (ρ = 0.740), cast (ρ = 0.722), fracture (frontal ρ = 0.947, lateral ρ = 0.946), multiple fragments (frontal ρ = 0.856), and fragment displacement (frontal ρ = 0.595). CONCLUSIONS: The models trained on a DCNN with report-based labels to detect distal radius fractures on radiographs are suitable to aid as a secondary reading tool; models for fracture classification are not ready for clinical use. Bigger training sets lead to better models in all categories except joint affection. KEY POINTS: • Detection of metal and cast on radiographs is excellent using AI and labels extracted from radiology reports. • Automatic detection of distal radius fractures on radiographs is feasible and the performance approximates radiology residents. • Automatic classification of the type of distal radius fracture varies in accuracy and is inferior for joint involvement and fragment displacement.

Imaging of Cardiopulmonary Involvement in Systemic Immune-mediated Diseases: A Comprehensive Review.

Systemic immune-mediated diseases (SID) are a large group of disorders characterized by complex inflammatory and autoimmune damage to various organs and tissues. Among the possible manifestations, SIDs may potentially involve each structure of the cardiopulmonary system. Each disease is characterized by a specific clinical presentation. Coronary artery disease, myocarditis, pericarditis, valvular disease, pulmonary arterial hypertension, and interstitial lung disease represent characteristic findings of cardiopulmonary involvement in these disorders and their prompt recognition is crucial for the diagnosis of SIDs and the patient's prognosis. In this setting, chest high-resolution computed tomography and cardiac magnetic resonance are the most important noninvasive techniques for the assessment of these diseases and their complications. The knowledge of various cardiac and pulmonary radiologic patterns increases the likelihood of diagnosing these disorders and can lead to improved understanding of the underlying pathophysiology to personalize the treatment for each patient.

Coronary Computed Tomography Angiography in the Clinical Workflow of Athletes With Anomalous Origin of Coronary Arteries From the Contralateral Valsalva Sinus.

PURPOSE: This study aimed to assess the role of coronary computed tomography-angiography (CCTA) in the workflow of competitive sports eligibility in a cohort of athletes with anomalous origin of the left-coronary artery (AOLCA)/anomalous origin of the right-coronary artery (AORCA) in an attempt to outline relevant computed tomography features likely to impact diagnostic assessment and clinic management. MATERIALS AND METHODS: Patients with suspected AOLCA/AORCA at transthoracic echocardiography or with inconclusive transthoracic echocardiography underwent CCTA to rule out/confirm and characterize the anatomic findings: partially interarterial course or full-INT, high-take-off, acute-take-off-angle (ATO), slit-like origin, intramural course (IM), interarterial-course-length, and lumen-reduction/hypoplasia (HYPO). RESULTS: CCTA identified 28 athletes: 6 AOLCA (3 males; 20.3±11.0 y) and 22 AORCA (18 males; 29.1±16.5 y). Symptoms were present only in 13 athletes (46.4%; 10 AORCA). Four patients (3 AORCA) had abnormal rest electrocardiogram, 11 (40.7%; 9 AORCA) had abnormal stress-electrocardiogram. The INT course was observed in 15 athletes (53.6%): 6/6 AOLCA and 9/22 AORCA (40.9%). Slit-like origin was present in 7/22 AORCA (31.8%) and never in AOLCA. Suspected IM resulted in 3 AOLCA (50%), always with HYPO/ATO, and in 6/22 AORCA (27.3%) with HYPO. No statistically significant differences were found between asymptomatic/symptomatic patients in the prevalence of partially INT/INT courses, high-take-off/ATO, and slit-like ostium. A slightly significant relationship between suspected proximal-IM (r=0.47, P<0.05) and proximal-HYPO of anomalous vessel (r=0.65, P<0.01) resulted in AORCA and was confirmed on AOLCA/AORCA pooled analysis (r=0.58, P<0.01 for HYPO). All AOLCA/AORCA athletes were disqualified from competitive sports and warned to avoid vigorous physical efforts. Surgery was recommended to all AOLCA athletes and to 13 AORCA (3 asymptomatic), but only 6 underwent surgery. No major cardiovascular event/ischemic symptoms/signs developed during a mean follow-up of 49.6±39.5 months. CONCLUSION: CCTA provides essential information for safe/effective clinical management of athletes, with important prognostic/sport-activity implications.

Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic: The synergetic effect of an open, clinically embedded software development platform and machine learning.

PURPOSE: During the emerging COVID-19 pandemic, radiology departments faced a substantial increase in chest CT admissions coupled with the novel demand for quantification of pulmonary opacities. This article describes how our clinic implemented an automated software solution for this purpose into an established software platform in 10 days. The underlying hypothesis was that modern academic centers in radiology are capable of developing and implementing such tools by their own efforts and fast enough to meet the rapidly increasing clinical needs in the wake of a pandemic. METHOD: Deep convolutional neural network algorithms for lung segmentation and opacity quantification on chest CTs were trained using semi-automatically and manually created ground-truth (Ntotal = 172). The performance of the in-house method was compared to an externally developed algorithm on a separate test subset (N = 66). RESULTS: The final algorithm was available at day 10 and achieved human-like performance (Dice coefficient = 0.97). For opacity quantification, a slight underestimation was seen both for the in-house (1.8 %) and for the external algorithm (0.9 %). In contrast to the external reference, the underestimation for the in-house algorithm showed no dependency on total opacity load, making it more suitable for follow-up. CONCLUSIONS: The combination of machine learning and a clinically embedded software development platform enabled time-efficient development, instant deployment, and rapid adoption in clinical routine. The algorithm for fully automated lung segmentation and opacity quantification that we developed in the midst of the COVID-19 pandemic was ready for clinical use within just 10 days and achieved human-level performance even in complex cases.