Deep learning-based fully automated Z-axis coverage range definition from scout scans to eliminate overscanning in chest CT imaging

Background Despite the prevalence of chest CT in the clinic, concerns about unoptimized protocols delivering high radiation doses to patients still remain. This study aimed to assess the additional radiation dose associated with overscanning in chest CT and to develop an automated deep learning-assisted scan range selection technique to reduce radiation dose to patients. Results A significant overscanning range (31 ± 24) mm was observed in clinical setting for over 95% of the cases. The average Dice coefficient for lung segmentation was 0.96 and 0.97 for anterior–posterior (AP) and lateral projections, respectively. By considering the exact lung coverage as the ground truth, and AP and lateral projections as input, The DL-based approach resulted in errors of 0.08 ± 1.46 and − 1.5 ± 4.1 mm in superior and inferior directions, respectively. In contrast, the error on external scout views was − 0.7 ± 4.08 and 0.01 ± 14.97 mm for superior and inferior directions, respectively.The ED reduction achieved by automated scan range selection was 21% in the test group. The evaluation of a large multi-centric chest CT dataset revealed unnecessary ED of more than 2 mSv per scan and 67% increase in the thyroid absorbed dose. Conclusion The proposed DL-based solution outperformed previous automatic methods with acceptable accuracy, even in complicated and challenging cases. The generizability of the model was demonstrated by fine-tuning the model on AP scout views and achieving acceptable results. The method can reduce the unoptimized dose to patients by exclunding unnecessary organs from field of view.

Quantifying effects of snow depth on caribou winter range selection and movement in Arctic Alaska

Background Caribou and reindeer across the Arctic spend more than two thirds of their lives moving in snow. Yet snow-specific mechanisms driving their winter ecology and potentially influencing herd health and movement patterns are not well known. Integrative research coupling snow and wildlife sciences using observations, models, and wildlife tracking technologies can help fill this knowledge void. Methods Here, we quantified the effects of snow depth on caribou winter range selection and movement. We used location data of Central Arctic Herd (CAH) caribou in Arctic Alaska collected from 2014 to 2020 and spatially distributed and temporally evolving snow depth data produced by SnowModel. These landscape-scale (90 m), daily snow depth data reproduced the observed spatial snow-depth variability across typical areal extents occupied by a wintering caribou during a 24-h period. Results We found that fall snow depths encountered by the herd north of the Brooks Range exerted a strong influence on selection of two distinct winter range locations. In winters with relatively shallow fall snow depth (2016/17, 2018/19, and 2019/20), the majority of the CAH wintered on the tundra north of the Brooks Range mountains. In contrast, during the winters with relatively deep fall snow depth (2014/15, 2015/16, and 2017/18), the majority of the CAH caribou wintered in the mountainous boreal forest south of the Brooks Range. Long-term (19 winters; 2001–2020) monitoring of CAH caribou winter distributions confirmed this relationship. Additionally, snow depth affected movement and selection differently within these two habitats: in the mountainous boreal forest, caribou avoided areas with deeper snow, but when on the tundra, snow depth did not trigger significant deep-snow avoidance. In both wintering habitats, CAH caribou selected areas with higher lichen abundance, and they moved significantly slower when encountering deeper snow. Conclusions In general, our findings indicate that regional-scale selection of winter range is influenced by snow depth at or prior to fall migration. During winter, daily decision-making within the winter range is driven largely by snow depth. This integrative approach of coupling snow and wildlife observations with snow-evolution and caribou-movement modeling to quantify the multi-facetted effects of snow on wildlife ecology is applicable to caribou and reindeer herds throughout the Arctic.

TLDS: A Transfer-Learning-Based Delivery Station Location Selection Pipeline

Delivery stations play important roles in logistics systems. Well-designed delivery station planning can improve delivery efficiency significantly. However, existing delivery station locations are decided by experts, which requires much preliminary research and data collection work. It is not only time consuming but also expensive for logistics companies. Therefore, in this article, we propose a data-driven pipeline that can transfer expert knowledge among cities and automatically allocate delivery stations. Based on existing well-designed station location planning in the source city, we first train a model to learn the expert knowledge about delivery range selection for each station. Then we transfer the learned knowledge to a new city and design three strategies to select delivery stations for the new city. Due to the differences in characteristics among different cities, we adopt a transfer learning method to eliminate the domain difference so that the model can be adapted to a new city well. Finally, we conduct extensive experiments based on real-world datasets and find the proposed method can solve the problem well.

NOAH

Spreadsheet systems are by far the most popular platform for data exploration on the planet, supporting millions of rows of data. However, exploring spreadsheets that are this large via operations such as scrolling or issuing formulae can be overwhelming and error-prone. Users easily lose context and suffer from cognitive and mechanical burdens while issuing formulae on data spanning multiple screens. To address these challenges, we introduce dynamic hierarchical overviews that are embedded alongside spreadsheets. Users can employ this overview to explore the data at various granularities, zooming in and out of the spreadsheet. They can issue formulae over data subsets without cumbersome scrolling or range selection, enabling users to gain a high or low-level perspective of the spreadsheet. An implementation of our dynamic hierarchical overview, NOAH, integrated within DataSpread, preserves spreadsheet semantics and look and feel, while introducing such enhancements. Our user studies demonstrate that NOAH makes it more intuitive, easier, and faster to navigate spreadsheet data compared to traditional spreadsheets like Microsoft Excel and spreadsheet plug-ins like Pivot Table, for a variety of exploration tasks; participants made fewer mistakes in NOAH while being faster in completing the tasks.

GA-Based Optimized Image Watermarking Method With Histogram and Butterworth Filtering

The present paper proposes a new and significant method of optimization for digital image watermarking by using a combination of Genetic Algorithms (GA), Histogram and Butterworth filtering. In this proposed method, the histogram range selection of low frequency components is taken as a significant parameter which assists in bettering the imperceptibility and robustness against attacks. The tradeoff between the perceptual transparency and robustness is considered as an optimization puzzle which is solved with the help of Genetic Algorithm. As a result, the experimental outcomes of the present approach are obtained. These results are secure and robust to various attacks such as rotation, cropping, scaling, additive noise and filtering attacks. The peak signal to noise ratio (PSNR) and Normalized cross correlation (NC) are carefully analyzed and assessed for a set of images and MATLAB2016B software is employed as a means of accomplishing or achieving these experimental results.