More Like this

1. Calibrated bagging deep learning for image semantic segmentation: A case study on COVID-19 chest X-ray image

   https://doi.org/10.1371/journal.pone.0276250  

   Nwosu, Lucy ; Li, Xiangfang ; Qian, Lijun ; Kim, Seungchan ; Dong, Xishuang ( November 2022 , PLOS ONE)

   Hemanth, Jude (Ed.)

   Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes coronavirus disease 2019 (COVID-19). Imaging tests such as chest X-ray (CXR) and computed tomography (CT) can provide useful information to clinical staff for facilitating a diagnosis of COVID-19 in a more efficient and comprehensive manner. As a breakthrough of artificial intelligence (AI), deep learning has been applied to perform COVID-19 infection region segmentation and disease classification by analyzing CXR and CT data. However, prediction uncertainty of deep learning models for these tasks, which is very important to safety-critical applications like medical image processing, has not been comprehensively investigated. In this work, we propose a novel ensemble deep learning model through integrating bagging deep learning and model calibration to not only enhance segmentation performance, but also reduce prediction uncertainty. The proposed method has been validated on a large dataset that is associated with CXR image segmentation. Experimental results demonstrate that the proposed method can improve the segmentation performance, as well as decrease prediction uncertainty.
2. Event-Driven Deep Learning for Edge Intelligence (EDL-EI) †

   https://doi.org/10.3390/s21186023  

   Shah, Sayed Khushal ; Tariq, Zeenat ; Lee, Jeehwan ; Lee, Yugyung ( September 2021 , Sensors)

   null (Ed.)

   Edge intelligence (EI) has received a lot of interest because it can reduce latency, increase efficiency, and preserve privacy. More significantly, as the Internet of Things (IoT) has proliferated, billions of portable and embedded devices have been interconnected, producing zillions of gigabytes on edge networks. Thus, there is an immediate need to push AI (artificial intelligence) breakthroughs within edge networks to achieve the full promise of edge data analytics. EI solutions have supported digital technology workloads and applications from the infrastructure level to edge networks; however, there are still many challenges with the heterogeneity of computational capabilities and the spread of information sources. We propose a novel event-driven deep-learning framework, called EDL-EI (event-driven deep learning for edge intelligence), via the design of a novel event model by defining events using correlation analysis with multiple sensors in real-world settings and incorporating multi-sensor fusion techniques, a transformation method for sensor streams into images, and lightweight 2-dimensional convolutional neural network (CNN) models. To demonstrate the feasibility of the EDL-EI framework, we presented an IoT-based prototype system that we developed with multiple sensors and edge devices. To verify the proposed framework, we have a case study of air-quality scenarios based on the benchmark datamore »provided by the USA Environmental Protection Agency for the most polluted cities in South Korea and China. We have obtained outstanding predictive accuracy (97.65% and 97.19%) from two deep-learning models on the cities’ air-quality patterns. Furthermore, the air-quality changes from 2019 to 2020 have been analyzed to check the effects of the COVID-19 pandemic lockdown.« less
3. ComputeCOVID19+: Accelerating COVID-19 Diagnosis and Monitoring via High-Performance Deep Learning on CT Images

   https://doi.org/10.1145/3472456.3473523  

   Goel, Garvit ; Gondhalekar, Atharva ; Qi, Jingyuan ; Zhang, Zhicheng ; Cao, Guohua ; Feng, Wu-chun ( August 2021 , 50th International Conference on Parallel Processing)

   The COVID-19 pandemic has highlighted the importance of diagnosis and monitoring as early and accurately as possible. However, the reverse-transcription polymerase chain reaction (RT-PCR) test results in two issues: (1) protracted turnaround time from sample collection to testing result and (2) compromised test accuracy, as low as 67%, due to when the test is administered and due to how the samples are collected, handled, and delivered to the lab to conduct the RT-PCR test. Thus, we present ComputeCOVID19+, our computed tomography-based framework to improve the testing speed and accuracy of COVID-19 (plus its variants) via a deep learning-based network for CT image enhancement called DDnet. To demonstrate its speed and accuracy, we evaluate ComputeCOVID19+ across many sources of computed tomography (CT) images and on many heterogeneous platforms, including multi-core CPU, many-core GPU, and even FPGA. Our results show that ComputeCOVID19+ can significantly shorten the turnaround time from days to minutes and improve the testing accuracy to 91%.
4. Classifying Small Volumes of Tissue for Real-Time Monitoring Radiofrequency Ablation

   https://doi.org/10.1007/978-3-030-21642-9_26  

   Besler, Emre ; Wang, Yearnchee Curtis ; Chan, Terence ; Sahakian, Alan Varteres ( May 2019 , Conference on Artificial Intelligence in Medicine in Europe)

   An increasingly-popular treatment for ablation of cancerous and non-cancerous masses is thermal ablation by radiofrequency joule heating. Real-time monitoring of the thermal tissue ablation process is essential in order to maintain the reliability of the treatment technique. Common methods for monitoring the extent of ablation have proven to be accurate, though they are time-consuming and often require powerful computers to run on, which makes the clinical ablation process more cumbersome and expensive due to the time-dependent nature of the clinical procedure. In this study, a Machine Learning (ML) approach is presented to reduce the time to calculate the progress of ablation while keeping the accuracy of the conventional methods. Different setups were used to perform the ablation and collect impedance data at the same time and different ML algorithms were tested to predict the ablation depth in three dimensions, based on the collected data. In the end, it is shown that an optimal pair of hardware setup and ML algorithm were able to control the ablation by estimating the lesion depth within an average of micrometer-magnitude error range while keeping the estimation time within 5.5 s on conventional x86-64 computing hardware.
5. The Existence of at Least Three Genomic Signature Patterns and at Least Seven Subtypes of COVID-19 and the End of the Disease

   https://doi.org/10.3390/vaccines10050761  

   Zhang, Zhengjun ( May 2022 , Vaccines)

   Hoping to find genomic clues linked to COVID-19 and end the pandemic has driven scientists’ tremendous efforts to try all kinds of research. Signs of progress have been achieved but are still limited. This paper intends to prove the existence of at least three genomic signature patterns and at least seven subtypes of COVID-19 driven by five critical genes (the smallest subset of genes) using three blood-sampled datasets. These signatures and subtypes provide crucial genomic information in COVID-19 diagnosis (including ICU patients), research focuses, and treatment methods. Unlike existing approaches focused on gene fold-changes and pathways, gene-gene nonlinear and competing interactions are the driving forces in finding the signature patterns and subtypes. Furthermore, the method leads to high accuracy with hospitalized patients, showing biological and mathematical equivalences between COVID-19 status and the signature patterns and a methodological advantage over other methods that cannot lead to high accuracy. As a result, as new biomarkers, the new findings and genomic clues can be much more informative than other findings for interpreting biological mechanisms, developing the second (third) generation of vaccines, antiviral drugs, and treatment methods, and eventually bringing new hopes of an end to the pandemic.