Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

COVID-AL: The diagnosis of COVID-19 with deep active learning.

In Medical image analysis

The efficient diagnosis of COVID-19 plays a key role in preventing the spread of this disease. The computer-aided diagnosis with deep learning methods can perform automatic detection of COVID-19 using CT scans. However, large scale annotation of CT scans is impossible because of limited time and heavy burden on the healthcare system. To meet the challenge, we propose a weakly-supervised deep active learning framework called COVID-AL to diagnose COVID-19 with CT scans and patient-level labels. The COVID-AL consists of the lung region segmentation with a 2D U-Net and the diagnosis of COVID-19 with a novel hybrid active learning strategy, which simultaneously considers sample diversity and predicted loss. With a tailor-designed 3D residual network, the proposed COVID-AL can diagnose COVID-19 efficiently and it is validated on a large CT scan dataset collected from the CC-CCII. The experimental results demonstrate that the proposed COVID-AL outperforms the state-of-the-art active learning approaches in the diagnosis of COVID-19. With only 30% of the labeled data, the COVID-AL achieves over 95% accuracy of the deep learning method using the whole dataset. The qualitative and quantitative analysis proves the effectiveness and efficiency of the proposed COVID-AL framework.

Wu Xing, Chen Cheng, Zhong Mingyu, Wang Jianjia, Shi Jun


COVID-19, Computer-aided diagnosis, Deep active learning, Predicted loss, Sample diversity

General General

Dynamic MRI reconstruction with end-to-end motion-guided network.

In Medical image analysis

Temporal correlation in dynamic magnetic resonance imaging (MRI), such as cardiac MRI, is informative and important to understand motion mechanisms of body regions. Modeling such information into the MRI reconstruction process produces temporally coherent image sequence and reduces imaging artifacts and blurring. However, existing deep learning based approaches neglect motion information during the reconstruction procedure, while traditional motion-guided methods are hindered by heuristic parameter tuning and long inference time. We propose a novel dynamic MRI reconstruction approach called MODRN and an end-to-end improved version called MODRN(e2e), both of which enhance the reconstruction quality by infusing motion information into the modeling process with deep neural networks. The central idea is to decompose the motion-guided optimization problem of dynamic MRI reconstruction into three components: Dynamic Reconstruction Network, Motion Estimation and Motion Compensation. Extensive experiments have demonstrated the effectiveness of our proposed approach compared to other state-of-the-art approaches.

Huang Qiaoying, Xian Yikun, Yang Dong, Qu Hui, Yi Jingru, Wu Pengxiang, Metaxas Dimitris N


Dynamic MRI reconstruction, Motion compensation, Motion estimation

General General

Age verification using random forests on facial 3D landmarks.

In Forensic science international

Three-dimensional facial images are becoming more and more widespread. As such images provide more information about facial morphology than 2D imagery, they show great promise for use in future forensic applications, including age estimation and verification. This paper proposes an approach using random forests, a machine learning method, to develop and test models for classification of legal age thresholds (15 years and 18 years) using 3D facial landmarks. Our approach was developed on a set of 3D facial scans from 394 Czech individuals (194 males and 200 females) aged between 10 and 25 years. The dataset was retrieved from a sizable database of Central European faces - The FIDENTIS 3D Face Database. Three main types of input variables were processed using random forests: I) shape (size-invariant) coordinates of 3D landmarks, II) size and shape coordinates of 3D landmarks, and III) inter-landmark distances, angles and indices. The performance rates for the combinations of variables and age threshold were expressed in terms of sensitivity and specificity. The overall accuracy rates varied from 71.4%-91.5% (when the male and female samples were pooled). In general, higher accuracy was achieved for the age limit of 18 years than for 15 years. Whereas size-variant variables showed a better performance rate for the age limit of 15 years, the size-invariant variables (i.e., shape variables) were better for classifying individuals under 18 years. The verification models grounded on traditional variables (distances, angles, indices) yielded consistently higher performance rates on females than on males, whereas the inverse trend was observed for the models built on 3D coordinates. The results indicate that age verification based on 3D facial data with processing by the random forests method has high potential for further forensic or biometric applications.

Jandová Marie, Daňko Marek, Urbanová Petra


3D facial models, Age estimation, Age verification, FIDENTIS database, Random forests

General General

Sensitivity and specificity of the driver sleepiness detection methods using physiological signals: A systematic review.

In Accident; analysis and prevention

Driver sleepiness is a major contributor to road crashes. A system that monitors and warns the driver at a certain, critical level of arousal, could aid in reducing sleep-related crashes. To determine how driver sleepiness detection systems perform, a systematic review of the sensitivity and specificity outcomes was performed. In total, 21 studies were located that met inclusion criteria for the review. The range of sensitivity outcomes was between 39.0-98.8 % and between 73.0-98.9 % for specificity outcomes. There was considerable variation in the outcomes of the studies employing only one physiological measure (mono-signal approach), whereas, a poly-signal approach with multiple physiological signals resulted in more consistency with higher outcomes on both sensitivity and specificity metrics. Only six of the 21 studies had both sensitivity and specificity outcomes above 90.0 %, which included mono- and poly-signal approaches. Moreover, increases in the number of features used in the sleepiness detection system did not result in higher sensitivity and specificity outcomes. Overall, there was considerable variability between the studies reviewed, including measures of ground truth, the features employed and the machine learning approach of the systems. A critical need for progressing any system is a revalidation of the system on a new sample of users. These aspects indicate considerable progress is needed with physiological-based driver sleepiness systems before they are at a sufficient standard to be deployed on-road.

Watling Christopher N, Mahmudul Hasan Md, Larue Grégoire S


Driving, Drowsiness, Fatigue, Features, Ground truth, Machine learning, Physiological sleepiness

General General

Discovering latent themes in traffic fatal crash narratives using text mining analytics and network topology.

In Accident; analysis and prevention

The proliferation of digital textual archives in the transportation safety domain makes it imperative for the inventions of efficient ways of extracting information from the textual data sources. The present study aims at utilizing crash narratives complemented by crash metadata to discern the prevalence and co-occurrence of themes that contribute to crash incidents. Ten years (2009-2018) of Michigan traffic fatal crash narratives were used as a case study. The structural topic modeling (STM) and network topology analysis were used to generate and examine the prevalence and interaction of themes from the crash narratives that were mainly categorized into pre-crash events, crash locations and involved parties in the traffic crashes. The main advantage of the STM over the other topic modeling approaches is that it allows the researchers to discover themes from documents and estimate how the topic relates to the document metadata. Topics with the highest prevalence for the angle, head-on, rear-end, sideswipe and single motor vehicle crashes were crash at stop-sign, crossing the centerline, unable to stop, lane change maneuver and run-off-road crash, respectively. Eigenvector centrality measure in network topology showed that event-related topics were consistently central in articulating the crash occurrence. The centrality and association between topics varied across crash types. The efficacy of generated topics in classifying crashes by type was tested using a machine learning algorithm, Random Forest. The classification accuracy in the held-out sample ranged between 89.3 % for sideswipe crashes to 99.2 % for single motor vehicle crashes. High classification accuracy suggests that automation of crash typing and consistency checks can be accomplished effectively by using extracted latent themes from the crash narratives.

Kwayu Keneth Morgan, Kwigizile Valerian, Lee Kevin, Oh Jun-Seok


Network centrality measures, Network topology, Structural topic modeling, Traffic crashes

Public Health Public Health

Causal relationships between gut metabolites and Alzheimer's disease: a bidirectional Mendelian randomization study.

In Neurobiology of aging ; h5-index 69.0

Observational studies have shown that gut microbiota-dependent metabolites are associated with the risk of Alzheimer's disease (AD). However, whether such association reflects a causality remains unclear. We conducted a bidirectional Mendelian randomization analysis to examine the causal relationships between gut microbiota-dependent metabolites trimethylamine N-oxide (TMAO) or its predecessors and AD. We observed that genetically predicted TMAO (odds ratio: 0.99, 95% confidence interval: 0.89 to 1.09 per 10 units, p = 0.775) or its predecessors including betaine (1.06, 1.00 to 1.12 per 10 units, p = 0.056), carnitine (1.05, 0.98 to 1.12 per 10 units, p = 0.178), and choline (1.01, 0.92 to 1.10 per 10 units, p = 0.905) were not associated with the risk of AD. Our Mendelian randomization estimates from AD to metabolites showed that genetically predicted higher risk of AD was also not causally associated with TMAO, betaine, carnitine, and choline levels. Our findings support that gut microbiota-dependent metabolites TMAO or its predecessors do not play causal roles in the development of AD.

Zhuang Zhenhuang, Gao Meng, Yang Ruotong, Liu Zhonghua, Cao Weihua, Huang Tao


“Alzheimers disease”, Causality, Genetic association, Mendelian randomization, Trimethylamine N-oxide