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

General General

Tile-based microscopic image processing for malaria screening using a deep learning approach.

In BMC medical imaging

BACKGROUND : Manual microscopic examination remains the golden standard for malaria diagnosis. But it is laborious, and pathologists with experience are needed for accurate diagnosis. The need for computer-aided diagnosis methods is driven by the enormous workload and difficulties associated with manual microscopy based examination. While the importance of computer-aided diagnosis is increasing at an enormous pace, fostered by the advancement of deep learning algorithms, there are still challenges in detecting small objects such as malaria parasites in microscopic images of blood films. The state-of-the-art (SOTA) deep learning-based object detection models are inefficient in detecting small objects accurately because they are underrepresented on benchmark datasets. The performance of these models is affected by the loss of detailed spatial information due to in-network feature map downscaling. This is due to the fact that the SOTA models cannot directly process high-resolution images due to their low-resolution network input layer.

METHODS : In this study, an efficient and robust tile-based image processing method is proposed to enhance the performance of malaria parasites detection SOTA models. Three variants of YOLOV4-based object detectors are adopted considering their detection accuracy and speed. These models were trained using tiles generated from 1780 high-resolution P. falciparum-infected thick smear microscopic images. The tiling of high-resolution images improves the performance of the object detection models. The detection accuracy and the generalization capability of these models have been evaluated using three datasets acquired from different regions.

RESULTS : The best-performing model using the proposed tile-based approach outperforms the baseline method significantly (Recall, [95.3%] vs [57%] and Average Precision, [87.1%] vs [76%]). Furthermore, the proposed method has outperformed the existing approaches that used different machine learning techniques evaluated on similar datasets.

CONCLUSIONS : The experimental results show that the proposed method significantly improves P. falciparum detection from thick smear microscopic images while maintaining real-time detection speed. Furthermore, the proposed method has the potential to assist and reduce the workload of laboratory technicians in malaria-endemic remote areas of developing countries where there is a critical skill gap and a shortage of experts.

Shewajo Fetulhak Abdurahman, Fante Kinde Anlay

2023-Mar-22

Deep learning, Malaria, Object detection, Plasmodium falciparum, Thick smear microscopic image, Tile-based image processing, YOLOV4

General General

Prediction of vancomycin initial dosage using artificial intelligence models applying ensemble strategy.

In BMC bioinformatics

BACKGROUND : Antibiotic resistance has become a global concern. Vancomycin is known as the last line of antibiotics, but its treatment index is narrow. Therefore, clinical dosing decisions must be made with the utmost care; such decisions are said to be "suitable" only when both "efficacy" and "safety" are considered. This study presents a model, namely the "ensemble strategy model," to predict the suitability of vancomycin regimens. The experimental data consisted of 2141 "suitable" and "unsuitable" patients tagged with a vancomycin regimen, including six diagnostic input attributes (sex, age, weight, serum creatinine, dosing interval, and total daily dose), and the dataset was normalized into a training dataset, a validation dataset, and a test dataset. AdaBoost.M1, Bagging, fastAdaboost, Neyman-Pearson, and Stacking were used for model training. The "ensemble strategy concept" was then used to arrive at the final decision by voting to build a model for predicting the suitability of vancomycin treatment regimens.

RESULTS : The results of the tenfold cross-validation showed that the average accuracy of the proposed "ensemble strategy model" was 86.51% with a standard deviation of 0.006, and it was robust. In addition, the experimental results of the test dataset revealed that the accuracy, sensitivity, and specificity of the proposed method were 87.54%, 89.25%, and 85.19%, respectively. The accuracy of the five algorithms ranged from 81 to 86%, the sensitivity from 81 to 92%, and the specificity from 77 to 88%. Thus, the experimental results suggest that the model proposed in this study has high accuracy, high sensitivity, and high specificity.

CONCLUSIONS : The "ensemble strategy model" can be used as a reference for the determination of vancomycin doses in clinical treatment.

Ho Wen-Hsien, Huang Tian-Hsiang, Chen Yenming J, Zeng Lang-Yin, Liao Fen-Fen, Liou Yeong-Cheng

2023-Mar-22

Ensemble strategy, Monitoring of blood concentration of drugs, Therapeutic drug monitoring (TDM), Vancomycin

General General

Dense reinforcement learning for safety validation of autonomous vehicles.

In Nature ; h5-index 368.0

One critical bottleneck that impedes the development and deployment of autonomous vehicles is the prohibitively high economic and time costs required to validate their safety in a naturalistic driving environment, owing to the rarity of safety-critical events1. Here we report the development of an intelligent testing environment, where artificial-intelligence-based background agents are trained to validate the safety performances of autonomous vehicles in an accelerated mode, without loss of unbiasedness. From naturalistic driving data, the background agents learn what adversarial manoeuvre to execute through a dense deep-reinforcement-learning (D2RL) approach, in which Markov decision processes are edited by removing non-safety-critical states and reconnecting critical ones so that the information in the training data is densified. D2RL enables neural networks to learn from densified information with safety-critical events and achieves tasks that are intractable for traditional deep-reinforcement-learning approaches. We demonstrate the effectiveness of our approach by testing a highly automated vehicle in both highway and urban test tracks with an augmented-reality environment, combining simulated background vehicles with physical road infrastructure and a real autonomous test vehicle. Our results show that the D2RL-trained agents can accelerate the evaluation process by multiple orders of magnitude (103 to 105 times faster). In addition, D2RL will enable accelerated testing and training with other safety-critical autonomous systems.

Feng Shuo, Sun Haowei, Yan Xintao, Zhu Haojie, Zou Zhengxia, Shen Shengyin, Liu Henry X

2023-Mar

General General

Forecasting PM2.5 concentrations using statistical modeling for Bengaluru and Delhi regions.

In Environmental monitoring and assessment

India is home to some of the most polluted cities on the planet. The worsening air quality in most of the cities has gone to an extent of causing severe impact on human health and life expectancy. An early warning system where people are alerted well before an adverse air quality episode can go a long way in preventing exposure to harmful air conditions. Having such system can also help the government to take better mitigation and preventive measures. Forecasting systems based on machine learning are gaining importance due to their cost-effectiveness and applicability to small towns and villages, where most complex models are not feasible due to resource constraints and limited data availability. This paper presents a study of air quality forecasting by application of statistical models. Three statistical models based on autoregression (AR), moving average (MA), and autoregressive integrated moving average (ARIMA) models were applied to the datasets of PM2.5 concentrations of Delhi and Bengaluru, and forecasting was done for 1-day-ahead and 7-day-ahead time frames. All three models forecasted the PM2.5 reasonably well for Bengaluru, but the model performance deteriorated for the Delhi region. The AR, MA, and ARIMA models achieved mean absolute percentage error (MAPE) of 10.82%, 7.94%, and 8.17% respectively for forecast of 7 days and MAPE of 7.35%, 5.62%, and 5.87% for 1-day-ahead forecasts for Bengaluru. For the Delhi region, the model gave an MAPE of 27.82%, 24.62%, and 27.32% for the AR, MA, and ARIMA models respectively in the 7-day-ahead forecast, and 24.48%, 23.53%, and 23.72% respectively for 1-day-ahead forecast. The analysis showed that ARIMA model performs better in comparison to the other models but performance varies with varying concentration regimes. Study indicates that other topographical and meteorological parameters need to be incorporated to develop better models and account for the effects of these parameters in the study.

Agarwal Akash, Sahu Manoranjan

2023-Mar-23

ARIMA, Air quality forecasting, Data analytics, Machine learning

General General

Ranking parameters driving siring success during sperm competition in the North African houbara bustard.

In Communications biology

Sperm competition is a powerful force driving the evolution of ejaculate and sperm traits. However, the outcome of sperm competition depends on many traits that extend beyond ejaculate quality. Here, we study male North African houbara bustards (Chlamydotis undulata undulata) competing for egg fertilization, after artificial insemination, with the aim to rank the importance of 14 parameters as drivers of siring success. Using a machine learning approach, we show that traits independent of male quality (i.e., insemination order, delay between insemination and egg laying) are the most important predictors of siring success. Traits describing intrinsic male quality (i.e., number of sperm in the ejaculate, mass motility index) are also positively associated with siring success, but their contribution to explaining the outcome of sperm competition is much lower than for insemination order. Overall, this analysis shows that males mating at the last position in the mating sequence have the best chance to win the competition for egg fertilization. This raises the question of the importance of female behavior as determinant of mating order.

Sorci Gabriele, Hussein Hiba Abi, Levêque Gwènaëlle, Saint Jalme Michel, Lacroix Frédéric, Hingrat Yves, Lesobre Loïc

2023-Mar-22

General General

Establishing a prediction model of severe acute mountain sickness using machine learning of support vector machine recursive feature elimination.

In Scientific reports ; h5-index 158.0

Severe acute mountain sickness (sAMS) can be life-threatening, but little is known about its genetic basis. The study was aimed to explore the genetic susceptibility of sAMS for the purpose of prediction, using microarray data from 112 peripheral blood mononuclear cell (PBMC) samples of 21 subjects, who were exposed to very high altitude (5260 m), low barometric pressure (406 mmHg), and hypobaric hypoxia (VLH) at various timepoints. We found that exposure to VLH activated gene expression in leukocytes, resulting in an inverted CD4/CD8 ratio that interacted with other phenotypic risk factors at the genetic level. A total of 2286 underlying risk genes were input into the support vector machine recursive feature elimination (SVM-RFE) system for machine learning, and a model with satisfactory predictive accuracy and clinical applicability was established for sAMS screening using ten featured genes with significant predictive power. Five featured genes (EPHB3, DIP2B, RHEBL1, GALNT13, and SLC8A2) were identified upstream of hypoxia- and/or inflammation-related pathways mediated by microRNAs as potential biomarkers for sAMS. The established prediction model of sAMS holds promise for clinical application as a genetic screening tool for sAMS.

Yang Min, Wu Yang, Yang Xing-Biao, Liu Tao, Zhang Ya, Zhuo Yue, Luo Yong, Zhang Nan

2023-Mar-21