This work compares Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) deep neural networks for the outdoor advertisement panel detection problem by handling multiple and combined variabilities in the scenes. Publicity panel detection in images offers important advantages both in the real world as well as in the virtual one. For example, applications like Google Street View can be used for Internet publicity and when detecting these ads panels in images, it could be possible to replace the publicity appearing inside the panels by another from a funding company. In our experiments, both SSD and YOLO detectors have produced acceptable results under variable sizes of panels, illumination conditions, viewing perspectives, partial occlusion of panels, complex background and multiple panels in scenes. Due to the difficulty of finding annotated images for the considered problem, we created our own dataset for conducting the experiments. The major strength of the SSD model was the almost elimination of False Positive (FP) cases, situation that is preferable when the publicity contained inside the panel is analyzed after detecting them. On the other side, YOLO produced better panel localization results detecting a higher number of True Positive (TP) panels with a higher accuracy. Finally, a comparison of the two analyzed object detection models with different types of semantic segmentation networks and using the same evaluation metrics is also included.
Autologous stem cell transplantation (PBSCT) is standard for young patients in MM and its TRM has decreased after the 2000s. Bortezomib and immunomodulatory agents (IMiDs) in MM have improved the outcome. However, they seem to boost pro-inflammatory stage increasing the incidence of engraftment syndrome (ES). Favorable factors in PBSCT such as G-CSF could increase inflammatory stage during transplant. Corticosteroids have shown an excellent response of ES and some authors propose them as prophylaxis for ES. The aim was to analyze the impact of G-CSF avoidance and corticosteroids' prophylaxis in 170 patients diagnosed of MM treated with bortezomib/IMiDs that underwent PBSCT. We established three groups: Group-I [(G-CSF_administration), 60 patients (35%)], group-II [(nonG-CSF), 60 patients (35%)] and group-III [(nonG-CSF plus corticosteroid's prophylaxis), 50 patients (30%)]. A decreased ES incidence among groups was observed: 62, 42, and 22% (P < 0.0001). The incidence of symptoms mimicking a capillary leak syndrome associated with ES dropped: 43, 32, and 0% (P = 0.03). The G-CSF avoidance and corticosteroids had impact over admission 24, 21, and 20 days (P = 0.001). The most important variables related to ES were HCT-CI >2 (p < 0.0001; HR 8.5) and risk groups (p < 0.0001; HR 7.2). Hence, G-CSF avoidance and corticosteroid's prophylaxis decrease morbidity in patients undergoing PBSCT with MM treated with bortezomib/IMiDs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.