A Multi-Agent Deep Reinforcement Learning Approach for Enhancement of COVID-19 CT Image Segmentation

Allioui, Hanane; Mohammed, Mazin Abed; Benameur, Narjes; Al‐Khateeb, Belal; Abdulkareem, Karrar Hameed; Garcia-Zapirain, Begonya; Damaševičius, Robertas; Maskeliūnas, Rytis

doi:10.3390/jpm12020309

Cited by 58 publications

(41 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most common COVID-19 symptoms include respiratory ailment, cough, flu, and fever, while for its part, computer tomography (CT) is a far better form of technology in terms of reliability, speed, and usefulness. As the virus broke out rapidly, assessment of COVID-19 needed to be automatic in the case of this particular pandemic [ 5 ]. Assessment and classification of COVID-19 are quicker using CT scans, insofar as its early detection is possible using CT images, although classification takes a lot of valuable time as this is done manually by expert radiologists.…”

Section: Introductionmentioning

confidence: 99%

Automatic COVID-19 Lung Infection Segmentation through Modified Unet Model

Shamim

Awan

Zain

et al. 2022

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

The coronavirus (COVID-19) pandemic has had a terrible impact on human lives globally, with far-reaching consequences for the health and well-being of many people around the world. Statistically, 305.9 million people worldwide tested positive for COVID-19, and 5.48 million people died due to COVID-19 up to 10 January 2022. CT scans can be used as an alternative to time-consuming RT-PCR testing for COVID-19. This research work proposes a segmentation approach to identifying ground glass opacity or ROI in CT images developed by coronavirus, with a modified structure of the Unet model having been used to classify the region of interest at the pixel level. The problem with segmentation is that the GGO often appears indistinguishable from a healthy lung in the initial stages of COVID-19, and so, to cope with this, the increased set of weights in contracting and expanding the Unet path and an improved convolutional module is added in order to establish the connection between the encoder and decoder pipeline. This has a major capacity to segment the GGO in the case of COVID-19, with the proposed model being referred to as “convUnet.” The experiment was performed on the Medseg1 dataset, and the addition of a set of weights at each layer of the model and modification in the connected module in Unet led to an improvement in overall segmentation results. The quantitative results obtained using accuracy, recall, precision, dice-coefficient, F1score, and IOU were 93.29%, 93.01%, 93.67%, 92.46%, 93.34%, 86.96%, respectively, which is better than that obtained using Unet and other state-of-the-art models. Therefore, this segmentation approach proved to be more accurate, fast, and reliable in helping doctors to diagnose COVID-19 quickly and efficiently.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic COVID-19 Lung Infection Segmentation through Modified Unet Model

Shamim

Awan

Zain

et al. 2022

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Whether someone is exposed to COVID-19 disease could be detected by analyzing his/her medical chest image [40], [50], [51]. This image-based analysis was used for screening the type of patients' respiratory disease and their severity.…”

Section: Topic Hotspotsmentioning

confidence: 99%

“…To extract CT masks to improve the diagnosis of COVID-19 [51] Computed tomography (CT) images Multi-agent deep reinforcement learning 22.…”

Section: Super Learner Ensemblementioning

confidence: 99%

Machine learning in handling disease outbreaks: a comprehensive review

Riswantini

Nugraheni

2022

Bulletin EEI

View full text Add to dashboard Cite

The changes in the global environment have made impact on the evolution of infectious diseases, virus mutations, or new diseases which are challenging to be tackled with new technological advances. This work aims to identify and analyze previous studies on machine learning applications in handling disease outbreaks. Bibliometric analysis was conducted on 3,447 scientific articles selected from the Scopus database. Further, latent dirichlet analysis (LDA) method was applied to identify the topic hotspots in attempting to deepen the analysis. The LDA results identified twelve topic hotspots that can be classified into three themes: COVID-19 disease, miscellaneous diseases, and public opinion on disease outbreaks for discussion. The study reveals that the scientific structure of this domain is dominated by machine learning research on COVID-19 diseases and miscellaneous diseases caused by pathogens or some genetic factors. A huge amount of multimodal medical data was used by previous studies for prediction, forecasting, classification, or screening purposes to resolve many problems of diseases, including epidemiological surveillance, diagnosis, treatment, health monitoring, epidemic management, viral infection, and pathogenesis. Public opinions toward new diseases are also an interesting topic in addition to the public perceptions in response to the health protocol and policies.

show abstract

“…Machine learning and deep learning methods are widely used for COVID-19 diagnostics (see, for example, [4][5][6]), severity prediction [7], and spread prediction [8,9]. The overview of these methods can be found in review papers [10,11].…”

Section: Introductionmentioning

confidence: 99%

An Optimized Decision Support Model for COVID-19 Diagnostics Based on Complex Fuzzy Hypersoft Mapping

et al. 2022

Self Cite

View full text Add to dashboard Cite

COVID-19 has shaken the entire world economy and affected millions of people in a brief period. COVID-19 has numerous overlapping symptoms with other upper respiratory conditions, making it hard for diagnosticians to diagnose correctly. Several mathematical models have been presented for its diagnosis and treatment. This article delivers a mathematical framework based on a novel agile fuzzy-like arrangement, namely, the complex fuzzy hypersoft (CFHS) set, which is a formation of the complex fuzzy (CF) set and the hypersoft set (an extension of soft set). First, the elementary theory of CFHS is developed, which considers the amplitude term (A-term) and the phase term (P-term) of the complex numbers simultaneously to tackle uncertainty, ambivalence, and mediocrity of data. In two components, this new fuzzy-like hybrid theory is versatile. First, it provides access to a broad spectrum of membership function values by broadening them to the unit circle on an Argand plane and incorporating an additional term, the P-term, to accommodate the data’s periodic nature. Second, it categorizes the distinct attribute into corresponding sub-valued sets for better understanding. The CFHS set and CFHS-mapping with its inverse mapping (INM) can manage such issues. Our proposed framework is validated by a study establishing a link between COVID-19 symptoms and medicines. For the COVID-19 types, a table is constructed relying on the fuzzy interval of [0,1]. The computation is based on CFHS-mapping, which identifies the disease and selects the optimum medication correctly. Furthermore, a generalized CFHS-mapping is provided, which can help a specialist extract the patient’s health record and predict how long it will take to overcome the infection.

show abstract

A Multi-Agent Deep Reinforcement Learning Approach for Enhancement of COVID-19 CT Image Segmentation

Cited by 58 publications

References 59 publications

Automatic COVID-19 Lung Infection Segmentation through Modified Unet Model

Automatic COVID-19 Lung Infection Segmentation through Modified Unet Model

Machine learning in handling disease outbreaks: a comprehensive review

An Optimized Decision Support Model for COVID-19 Diagnostics Based on Complex Fuzzy Hypersoft Mapping

Contact Info

Product

Resources

About