AMS (Finland)

Cracks on concrete surfaces are vital factors affecting construction safety. Accurate and efficient crack detection can prevent safety accidents. Using drones to photograph cracks on a concrete surface and detect them through computer vision technology has the advantages of accurate target recognition, simple practical operation, and low cost. To solve this problem, an improved CenterNet concrete crack-detection model is proposed. First, a channel-space attention mechanism is added to the original model to enhance the ability of the convolution neural network to pay attention to the image. Second, a feature selection module is introduced to scale the feature map in the downsampling stage to a uniform size and combine it in the channel dimension. In the upsampling stage, the feature selection module adaptively selects the combined features and fuses them with the output features of the upsampling. Finally, the target size loss is optimised from a Smooth L1 Loss to IoU Loss to improve its inability to adapt to targets of different sizes. The experimental results show that the improved CenterNet model reduces the FPS by 123.7, increases the GPU memory by 62MB, increases the FLOPs by 3.81, and increases the AP by 0.154 compared with the original model. The GPU memory occupancy remained stable during the training process and exhibited good real-time performance and robustness.

In this single‐center study, we aimed to describe the characteristics, treatment patterns, and outcomes of patients with multiple myeloma (MM) following treatment with bortezomib, carfilzomib, daratumumab, ixazomib, lenalidomide or pomalidomide‐based regimens. Data were collected retrospectively from a study cohort of patients receiving a MM treatment in the Hospital District of Helsinki and Uusimaa (HUS) in Finland between 2016–2020. In total, 472 patients were included in the study. Median age was 68.2 years and nearly 25% had a high cytogenetic risk according to the International Myeloma Working Group categorization. In 2018–2020, the spectrum of regimens used as third‐ or later‐line therapy was notably broader than in 2016–2017. The overall response rates for patients who received the most novel regimens (available ≤ 5 years) in second or third line of therapy (n = 67/430) and fourth line or later (n = 78/151) were 53.3% and 25.0%, respectively. In this real‐world MM patient cohort, the response rates for these novel agents were lower compared to those reported in clinical trials. Given the higher cytogenetic risk profile and more advanced disease stage at the time when treated with novel agents, patients could have benefited from effective novel therapies earlier in their treatment pathway.What is the NEW aspect of your work? (ONE sentence) This study characterized the treatment of Finnish multiple myeloma patients during the era of most novel therapies (after 2016) and also included information on the cytogenetic risk profile of this real‐world population.What is the CENTRAL finding of your work? (ONE sentence) There are clear differences between real‐world populations treated with most novel combinations and those of randomized controlled trials (RCTs), which is reflected by the poorer treatment outcomes in the real‐world setting.What is (or could be) the SPECIFIC clinical relevance of your work? (ONE sentence) Given the high cytogenetic risk profile and advanced disease stage at the time when treated with novel agents, patients could have benefited from effective novel therapies earlier in their treatment pathway.