Graph-Based Fusion of Imaging, Genetic and Clinical Data for Degenerative Disease Diagnosis.

Graph learning methods have achieved noteworthy performance in disease diagnosis due to their ability to represent unstructured information such as inter-subject relationships. While it has been shown that imaging, genetic and clinical data are crucial for degenerative disease diagnosis, existing methods rarely consider how best to use their relationships. How best to utilize information from imaging, genetic and clinical data remains a challenging problem. This study proposes a novel graph-based fusion (GBF) approach to meet this challenge. To extract effective imaging-genetic features, we propose an imaging-genetic fusion module which uses an attention mechanism to obtain modality-specific and joint representations within and between imaging and genetic data. Then, considering the effectiveness of clinical information for diagnosing degenerative diseases, we propose a multi-graph fusion module to further fuse imaging-genetic and clinical features, which adopts a learnable graph construction strategy and a graph ensemble method. Experimental results on two benchmarks for degenerative disease diagnosis (Alzheimers Disease Neuroimaging Initiative and Parkinson's Progression Markers Initiative) demonstrate its effectiveness compared to state-of-the-art graph-based methods. Our findings should help guide further development of graph-based models for dealing with imaging, genetic and clinical data.

Computer vision-based helmet use registration for e-scooter riders - The impact of the mandatory helmet law in Copenhagen.

PROBLEM: E-scooters are a new form of mobility used more frequently in urban environments worldwide. As there is evidence of an increased risk of head injuries, helmets are recommended and (less frequently) legislated. Denmark has enacted mandatory e-scooter helmet use legislation from January 1, 2022. So far, it is unclear how this newly implemented law influenced helmet use of e-scooter riders in Denmark immediately after its implementation. METHOD: In this observational study, we register and compare e-scooter helmet use before the mandatory helmet use legislation (December 2021) and after (February 2022). As observational survey data collection in the field can be highly time-consuming, we conducted a video-based observation survey. We trained and applied a computer vision algorithm to automatically register e-scooter helmet use in the video data. RESULTS: The trained algorithm produces accurate helmet use data, which does not differ significantly from human-registered helmet use. In applying the algorithm to video data collected in December 2021 and February 2022, we register an overall e-scooter helmet use of 4.4% in n = 1054 riders. Splitting the observation between the time before and after the implementation of the helmet use law reveals a significant increase in helmet use from 1.80% to 5.56%. DISCUSSION: In this study, we successfully train and apply an object detection algorithm to register accurate helmet use data in videos collected in Copenhagen, Denmark. Using this algorithm, we find a significant impact of a new mandatory e-scooter helmet use law on e-scooter riders' helmet use behavior. Limitations of the study as well as future research needs, are discussed. PRACTICAL APPLICATIONS: Computer vision algorithms can be used for accurate e-scooter helmet assessments. Implementing a mandatory helmet use law can increase helmet use of e-scooters at specific observation sites.

Neural Inference Search for Multiloss Segmentation Models.

Semantic segmentation is vital for many emerging surveillance applications, but current models cannot be relied upon to meet the required tolerance, particularly in complex tasks that involve multiple classes and varied environments. To improve performance, we propose a novel algorithm, neural inference search (NIS), for hyperparameter optimization pertaining to established deep learning segmentation models in conjunction with a new multiloss function. It incorporates three novel search behaviors, i.e., Maximized Standard Deviation Velocity Prediction, Local Best Velocity Prediction, and n -dimensional Whirlpool Search. The first two behaviors are exploratory, leveraging long short-term memory (LSTM)-convolutional neural network (CNN)-based velocity predictions, while the third employs n -dimensional matrix rotation for local exploitation. A scheduling mechanism is also introduced in NIS to manage the contributions of these three novel search behaviors in stages. NIS optimizes learning and multiloss parameters simultaneously. Compared with state-of-the-art segmentation methods and those optimized with other well-known search algorithms, NIS-optimized models show significant improvements across multiple performance metrics on five segmentation datasets. NIS also reliably yields better solutions as compared with a variety of search methods for solving numerical benchmark functions.

KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment.

Deep learning methods for image quality assessment (IQA) are limited due to the small size of existing datasets. Extensive datasets require substantial resources both for generating publishable content and annotating it accurately. We present a systematic and scalable approach to creating KonIQ-10k, the largest IQA dataset to date, consisting of 10,073 quality scored images. It is the first in-the-wild database aiming for ecological validity, concerning the authenticity of distortions, the diversity of content, and quality-related indicators. Through the use of crowdsourcing, we obtained 1.2 million reliable quality ratings from 1,459 crowd workers, paving the way for more general IQA models. We propose a novel, deep learning model (KonCept512), to show an excellent generalization beyond the test set (0.921 SROCC), to the current state-of-the-art database LIVE-in-the-Wild (0.825 SROCC). The model derives its core performance from the InceptionResNet architecture, being trained at a higher resolution than previous models (512 × 384). Correlation analysis shows that KonCept512 performs similar to having 9 subjective scores for each test image.

Detecting motorcycle helmet use with deep learning.

The continuous motorization of traffic has led to a sustained increase in the global number of road related fatalities and injuries. To counter this, governments are focusing on enforcing safe and law-abiding behavior in traffic. However, especially in developing countries where the motorcycle is the main form of transportation, there is a lack of comprehensive data on the safety-critical behavioral metric of motorcycle helmet use. This lack of data prohibits targeted enforcement and education campaigns which are crucial for injury prevention. Hence, we have developed an algorithm for the automated registration of motorcycle helmet usage from video data, using a deep learning approach. Based on 91,000 annotated frames of video data, collected at multiple observation sites in 7 cities across the country of Myanmar, we trained our algorithm to detect active motorcycles, the number and position of riders on the motorcycle, as well as their helmet use. An analysis of the algorithm's accuracy on an annotated test data set, and a comparison to available human-registered helmet use data reveals a high accuracy of our approach. Our algorithm registers motorcycle helmet use rates with an accuracy of -4.4% and +2.1% in comparison to a human observer, with minimal training for individual observation sites. Without observation site specific training, the accuracy of helmet use detection decreases slightly, depending on a number of factors. Our approach can be implemented in existing roadside traffic surveillance infrastructure and can facilitate targeted data-driven injury prevention campaigns with real-time speed. Implications of the proposed method, as well as measures that can further improve detection accuracy are discussed.