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

General General

A Review on Deep Learning Architecture and Methods for MRI Brain Tumour Segmentation.

In Current medical imaging

BACKGROUND : The automatic segmentation of brain tumour from MRI medical images is mainly covered in this review. Recently, state-of-the-art performance is provided by deep learning-based approaches in the field of image classification, segmentation, object detection, and tracking tasks.

INTRODUCTION : The core feature deep learning approach is the hierarchical representation of features from images and thus avoiding domain-specific handcrafted features.

METHODS : In this review paper, we have dealt with a Review of Deep Learning Architecture and Methods for MRI Brain Tumour Segmentation. First, we have discussed basic architecture and approaches for deep learning methods. Secondly, we have discussed the literature survey of MRI brain tumour segmentation using deep learning methods and its multimodality fusion. Then, the advantages and disadvantages of each method analyzed and finally concluded the discussion with the merits and challenges of deep learning techniques.

RESULTS AND CONCLUSION : The review of brain tumour identification using deep learning Techniques may help the research to have a better focus on it.

Angulakshmi M Deepa M

2021-Jan-08

Architecture, Brain Tumour, Classification, Deep Learning, MRI, challenges.

General General

Designing a hybrid reinforcement learning based algorithm with application in prediction of the COVID-19 pandemic in Quebec.

In Annals of operations research

World Health Organization (WHO) stated COVID-19 as a pandemic in March 2020. Since then, 26,795,847 cases have been reported worldwide, and 878,963 lost their lives due to the illness by September 3, 2020. Prediction of the COVID-19 pandemic will enable policymakers to optimize the use of healthcare system capacity and resource allocation to minimize the fatality rate. In this research, we design a novel hybrid reinforcement learning-based algorithm capable of solving complex optimization problems. We apply our algorithm to several well-known benchmarks and show that the proposed methodology provides quality solutions for most complex benchmarks. Besides, we show the dominance of the offered method over state-of-the-art methods through several measures. Moreover, to demonstrate the suggested method's efficiency in optimizing real-world problems, we implement our approach to the most recent data from Quebec, Canada, to predict the COVID-19 outbreak. Our algorithm, combined with the most recent mathematical model for COVID-19 pandemic prediction, accurately reflected the future trend of the pandemic with a mean square error of 6.29E-06. Furthermore, we generate several scenarios for deepening our insight into pandemic growth. We determine essential factors and deliver various managerial insights to help policymakers making decisions regarding future social measures.

Khalilpourazari Soheyl, Hashemi Doulabi Hossein

2021-Jan-03

COVID-19 pandemic, Machine learning, Reinforcement learning, SARS-Cov-2, SIDARTHE

General General

Deep Learning for Discussion-Based Cross-Domain Performance Prediction of MOOC Learners Grouped by Language on FutureLearn.

In Arabian journal for science and engineering

Analysing learners' behaviours in MOOCs has been used to identify predictive features associated with positive outcomes in engagement and learning success. Early methods predominantly analysed numerical features of behaviours such as the page views, video views, and assessment grades. Analysing extracted numeric features using baseline machine learning algorithms performed well to predict the learners' future performance in MOOCs. We propose categorising learners by likely English language proficiency and extending the range of data to include the content of comment texts. We compare results to a model trained with a combined set of extracted features. Not all platforms provide this rich variety of data. We analysed a series of a FutureLearn language focused MOOCs. Our data were from discussions embedded into each lesson's content. Analysing whether we gained any additional insights, over 420,000 comments were used to train the algorithm. We created a method for identifying one's possible first language from their country. We found that using comments alone is a weaker predictive approach than using a combination including extracted features from learners' activities. Our study contributes to research on generalisability of learning algorithms. We replicated the method across different MOOCs-the performance varies on the model though it always remained over 50%. One of the deep learning architecture, Bidirectional LSTM, trained with discussions on the language learning 73% successfully predicted learners' performance on a different MOOC.

Duru Ismail, Sunar Ayse Saliha, White Su, Diri Banu

2021-Jan-06

Deep learning, English as a second language, FutureLearn, MOOCs, Natural language processing, Predictive models

Surgery Surgery

Computed Tomography Image Analysis in Abdominal Wall Reconstruction: A Systematic Review.

In Plastic and reconstructive surgery. Global open ; h5-index 27.0

** : Ventral hernias are a complex and costly burden to the health care system. Although preoperative radiologic imaging is commonly performed, the plethora of anatomic features present and available in routine imaging are seldomly quantified and integrated into patient selection, preoperative risk stratification, and perioperative planning. We herein aimed to critically examine the current state of computed tomography feature application in predicting surgical outcomes.

Methods : A systematic review was conducted in accordance with the Preferred Reporting Items for a Systematic Review and Meta-Analysis (PRISMA) checklist. PubMed, MEDLINE, and Embase databases were reviewed under search syntax "computed tomography imaging" and "abdominal hernia" for papers published between 2000 and 2020.

Results : Of the initial 1922 studies, 12 papers met inclusion and exclusion criteria. The most frequently used radiologic features were hernia volume (n = 9), subcutaneous fat volume (n = 5), and defect size (n = 8). Outcomes included both complications and need for surgical intervention. Median area under the curve (AUC) and odds ratio were 0.68 (±0.16) and 1.12 (±0.39), respectively. The best predictive feature was hernia neck ratio > 2.5 (AUC 0.903).

Conclusions : Computed tomography feature selection offers hernia surgeons an opportunity to identify, quantify, and integrate routinely available morphologic tissue features into preoperative decision-making. Despite being in its early stages, future surgeons and researchers will soon be able to integrate 3D volumetric analysis and complex machine learning and neural network models to improvement patient care.

Elfanagely Omar, Mellia Joseph A, Othman Sammy, Basta Marten N, Mauch Jaclyn T, Fischer John P

2020-Dec

General General

3D printing of tissue engineering scaffolds: a focus on vascular regeneration.

In Bio-design and manufacturing

Tissue engineering is an emerging means for resolving the problems of tissue repair and organ replacement in regenerative medicine. Insufficient supply of nutrients and oxygen to cells in large-scale tissues has led to the demand to prepare blood vessels. Scaffold-based tissue engineering approaches are effective methods to form new blood vessel tissues. The demand for blood vessels prompts systematic research on fabrication strategies of vascular scaffolds for tissue engineering. Recent advances in 3D printing have facilitated fabrication of vascular scaffolds, contributing to broad prospects for tissue vascularization. This review presents state of the art on modeling methods, print materials and preparation processes for fabrication of vascular scaffolds, and discusses the advantages and application fields of each method. Specially, significance and importance of scaffold-based tissue engineering for vascular regeneration are emphasized. Print materials and preparation processes are discussed in detail. And a focus is placed on preparation processes based on 3D printing technologies and traditional manufacturing technologies including casting, electrospinning, and Lego-like construction. And related studies are exemplified. Transformation of vascular scaffolds to clinical application is discussed. Also, four trends of 3D printing of tissue engineering vascular scaffolds are presented, including machine learning, near-infrared photopolymerization, 4D printing, and combination of self-assembly and 3D printing-based methods.

Wang Pengju, Sun Yazhou, Shi Xiaoquan, Shen Huixing, Ning Haohao, Liu Haitao

2021-Jan-04

3D printing, Modeling methods, Print materials, Tissue engineering, Vascular scaffolds

General General

Explainable artificial intelligence for heart rate variability in ECG signal.

In Healthcare technology letters

Electrocardiogram (ECG) signal is one of the most reliable methods to analyse the cardiovascular system. In the literature, there are different deep learning architectures proposed to detect various types of tachycardia diseases, such as atrial fibrillation, ventricular fibrillation, and sinus tachycardia. Even though all types of tachycardia diseases have fast beat rhythm as the common characteristic feature, existing deep learning architectures are trained with the corresponding disease-specific features. Most of the proposed works lack the interpretation and understanding of the results obtained. Hence, the objective of this letter is to explore the features learned by the deep learning models. For the detection of the different types of tachycardia diseases, the authors used a transfer learning approach. In this method, the model is trained with one of the tachycardia diseases called atrial fibrillation and tested with other tachycardia diseases, such as ventricular fibrillation and sinus tachycardia. The analysis was done using different deep learning models, such as RNN, LSTM, GRU, CNN, and RSCNN. RNN achieved an accuracy of 96.47% for atrial fibrillation data set, 90.88% accuracy for CU-ventricular tachycardia data set, and also achieved an accuracy of 94.71, and 94.18% for MIT-BIH malignant ventricular ectopy database for ECG lead I and lead II, respectively. The RNN model could only achieve an accuracy of 23.73% for the sinus tachycardia data set. A similar trend is shown by other models. From the analysis, it was evident that even though tachycardia diseases have fast beat rhythm as their common feature, the model was not able to detect different types of tachycardia diseases. The deep learning model could only detect atrial fibrillation and ventricular fibrillation and failed in the case of sinus tachycardia. From the analysis, they were able to interpret that, along with the fast beat rhythm, the model has learned the absence of P-wave which is a common feature for ventricular fibrillation and atrial fibrillation but sinus tachycardia disease has an upright positive P-wave. The time-based analysis is conducted to find the time complexity of the models. The analysis conveyed that RNN and RSCNN models could achieve better performance with lesser time complexity.

K Sanjana, V Sowmya, E A Gopalakrishnan, K P Soman

2020-Dec

CU-ventricular tachycardia data, ECG signal, MIT-BIH malignant ventricular ectopy database, RCNN model, atrial fibrillation, cardiac diseases, cardiovascular system, convolutional neural nets, deep learning architectures, deep learning model, deep learning models, diseases, electrocardiogram signal, electrocardiography, learning (artificial intelligence), medical signal processing, signal classification, sinus tachycardia, tachycardia disease, ventricular fibrillation