No abstract

No abstract

Background The combination of multiple giant coronary artery aneurysms (CAAs) and right coronary artery (RCA) to pulmonary artery (PA) fistula is extremely rare and the patients with CAAs may suffer from several fatal complications. We herein describe a 60-year-old female with hemodynamic instability who was diagnosed with multiple giant CAAs combined with RCA-PA fistula. Case presentation The patient, a 60-year-old female, presented to the emergency room because of progressive exertional chest distress and fatigue. The transthoracic echocardiography (TTE), coronary computed tomography angiography (CTA) and invasive coronary angiography confirmed the existence of multiple giant CAAs and RCA-PA fistula. Laboratory examinations for systemic vasculitis and infectious diseases demonstrated no abnormalities and work-up for childhood and family history were negative. We have performed a successful surgical treatment for this patient. The patient’s restrictive cardiac dysfunction was improved after debriding the advanced thrombi in aneurysm sac and ligating the fistulous vessel between the native RCA and PA. The postoperative pathologic examination of the aneurysmal wall revealed loss of smooth muscle cells in the media with local mucoid degeneration, no chronic inflammation, sclerosis and IgG4 were observed. Conclusions The treatment decision-making process should depend upon the patients’ specific situations. Our case suggests the surgical intervention should be accepted as the preferred treatment for giant CAAs with restrictive cardiac dysfunction. Electronic supplementary material The online version of this article (10.1186/s12893-019-0547-z) contains supplementary material, which is available to authorized users.

An efficient approach for lane marking detection and classification by the combination of convolution neural network and recurrent neural network is proposed in this paper. First, convolution neural network is trained for lane marking features extraction, and then these convolution neural network features of continuous frames are transferred to recurrent neural network model for lane boundary detection and classification in the time domain. At last, a lane boundary fitting method based on dynamic programming is proposed to improve the lane detection accuracy and robustness. The method presented generates satisfactory results of lane detection and type classification under various traffic conditions according to the experimental results, which show that the approach provided in this paper outperforms traditional methods and the total lane markings classification reached 95.21% accuracy.

Introduction: We sought to evaluate the discrepancies between primary pathology report and second pathology review of radical orchiectomy (RO) specimens. Methods: A retrospective review was performed of RO specimens from the Ontario Cancer Registry. All cases required both a primary pathology report and a second pathology review from another institution. Histopathological variables assessed included histological subtype and components of mixed germ cell tumor (GCT), pathological tumor (pT) stage, lymphovascular invasion (LVI), spermatic cord invasion, and surgical margin. Results: Between 1994 and 2015, 5048 ROs were performed with 2719 (53.9%) seminoma and 2029 (40.2%) non-seminoma. Of these, 519 (10.3%) received a second pathology review. There was concordance between primary pathology report and second pathology review in 326 (62.8%) cases. The most common discrepancies involved a change in pT stage (n=148, 28.5%), with upstaging in 83 (16%) and downstaging in 65 (12.5%) cases relative to the original pT stage. The second most common discrepancy regarded the reporting of LVI (n=121, 23.3%), with 62 (11.9%) reporting presence of LVI when the primary pathology report did not. Other discrepancies included a change in the histological subtype in 28 (5.4%) cases and spermatic cord margin status in 5 (9.6%) cases. Conclusions: Only 10% of orchiectomy specimens underwent a second pathology review, with nearly 40% of reviews leading to a meaningful change in parameters. Such variation could lead to incorrect tumor staging, estimate of relapse risk, and inappropriate treatment decisions. Expert pathology review of RO specimens should be considered, as it has significant implications for decision making.