Potential diagnosis of COVID-19 from chest X-ray and CT findings using semi-supervised learning

Sahoo, Pracheta; Roy, Indranil; Ahlawat, Randeep; Irtiza, Saquib; Khan, Latifur

doi:10.1007/s13246-021-01075-2

Cited by 13 publications

(6 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Seven of them used only Kaggle dataset to collect their data for training or testing purpose of developed model [35,38,42,44,46,49,51]. Three of them used only GitHub repository which was developed by Dr. Joseph Cohen [33,43,48], other four of them used both of the Kaggle and GitHub database [34,47,50,54]. One used all of the GitHub, Covid-19 radiography database, Kaggle Covid-19 image data collection, and Actual Med Covid-19 Chest X-ray Dataset [36].…”

Section: Exploration Of Used Datamentioning

confidence: 99%

“…Data Source Data Volume [42] Kaggle 2482 CT scans image and 31 Covid positive along with 10,192 normal X-ray image [48] GitHub 108,948 images [49] Kaggle 3829 X-rays and 3829 X-rays [43] GitHub 535 CT and X-ray images and 485 clinical notes related with them [37] Mendeley Data 17,599 images [44] Kaggle 2481 images [46] Kaggle 2357 CT scan data, 2515 chest X-ray data and 2400 CT and chest X-ray hybrid data [34] Kaggle, GitHub 5856 chest X-ray & CT dataset [54] Kaggle, GitHub 2905 unique images for X-ray 617,775 images from 4154 patients [41] Mendeley Data 8,055 CT scan and 9,544 X-ray images [51] Kaggle 2591 mixed data [33] GitHub 17100 X−ray and CT images [47] Kaggle, GitHub 168 Covid and 168 normal cases for the both Xray and CT scan images [36] GitHub Kaggle and Git Hub 723 X-ray and 3228 CT scans images [38] Kaggle 400 chest X-ray images, and 400 CT scan images [39] Wonkwang University Hospital(WKUH) and Chonnam National University Hospital (CNUH), Italian Society of Medical and Interventional Radiology(SIRM) public database.…”

Section: Literaturementioning

confidence: 99%

“…A total of 6 papers worked on different CNN procedures like VGG19 [62], VGG16 [63], InceptionResNetV2 [64], MobileNetV2 [65], Densenet121 [66], InceptionV3 [67], Xception [68], and Resnet50 [68] [37] and InceptionResNetV2 [54] are two different architecture, are also developed to detect Covid, these were pre-trained by VGGNet-19, ResNet50, InceptionResNetV2 and MobileNet etc. SCoVNet architecture shows 99% accuracy on CT scan and 98% on X-ray data set.…”

Section: Exploring the Ai Techniquesmentioning

confidence: 99%

See 2 more Smart Citations

Comparative Analysis on Available Technique for the Detection of Covid-19 through CT-Scan and X-Ray using Machine Learning: A Systematic Review

Majhi¹,

Sauseng²

2023

Preprint

View full text Add to dashboard Cite

(1) Background: In the year of 2020 Covid-19 was declared epidemic by WHO. From that time millions of people were affected and died by this disease. The main detection process for this epidemic is RT-PCR test or reverse polymerase transcription chain reaction test. One of the reason of spreading of this disease so much is lack of efficiency in RT-PCR test. Sampling error and low viral load were two main reasons for what the testing process faced such problems. Lung infection is a very common symptom for covid-19 patients, so, CT scan and chest X-ray imaging technique can be applied to detect patient at a very early stage of infection. Which will be very effective and also can be a better option to RT-PCR test; (2) Methods: We searched data in Scopus for articles published between 2020 and 2023. The initial set of articles was 189, from which 21 articles will eventually be selected by exclusion criteria; (3) Results: A total of thirteen (61.90%) articles were found working on detecting Covid-19 by extracting the X-ray and CT scan data individually. Three (14.28%) of those articles focused on a hybrid model of CT scan and X-ray Image Data. Another four articles made a comparison between Covid-19, pneumonia and a normal person to identify a Covid-19 patient. Where others have worked on unsupervised learning methods or SVM to detect Covid-19.; (4) Conclusions: We have conducted a systematic review of the studies that have been published up to this time, with the purpose to present a summary of the evidence about the detection of COVID-19. In this article, we have summarized and critically reviewed literatures which worked on development or application or both of different AI or ML technique from chest CT and X-ray images to find a solution to detect covid-19.

show abstract

Section: Exploration Of Used Datamentioning

confidence: 99%

Section: Literaturementioning

confidence: 99%

Section: Exploring the Ai Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Analysis on Available Technique for the Detection of Covid-19 through CT-Scan and X-Ray using Machine Learning: A Systematic Review

Majhi¹,

Sauseng²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Using machine learning algorithm to complete the classification of data flow, the classifier has low generalization ability, which can effectively improve the effectiveness of data flow processing. The method of semi supervised learning and semi cluster analysis [22,23] is used to construct the corresponding classifier. Semi-supervised aggregation techniques are those that can be used with partly labelled information or data with different kinds of outcomes metrics.…”

Section: Adaptive Classification Of Text Data Streammentioning

confidence: 99%

Clustering Mining Algorithm of Internet of Things Database Based on Python Language

Wan,

Liu

2023

cai

View full text Add to dashboard Cite

In order to solve the problems of reading delay in data mining of the Internet of Things database, a clustering mining algorithm of the Internet of Things database based on Python language is proposed. We designed an improved crawler algorithm based on the open-source structure of scratch through Python language, judge the similarity of recruitment data topics in the Internet of Things database through Bayesian classifier, and crawl the recruitment data in the Internet of Things database: the number of keywords in the text space, the degree of keyword extraction, and the number of keyword data in the text space. The time series model is used to eliminate the delay of text features. On this basis, the semi-supervised learning and semi-cluster analysis method is used to construct the corresponding classifier, complete the adaptive classification process of the text data stream and realize the clustering mining of the Internet of Things database based on Python language. The experimental results show that this method has a low reading delay, and can mine the attention, number of posts and click time frequency of the Internet of Things database from which the recruitment data are obtained.

show abstract

“…Data quantities are increasing as a result of numerous causes, including diagnostic products and technologies, medical studies, or patient registries, that mention insufficient, like in the medical field transforms entering the age of the computer [11,12] These sources generate information in a variety of formats, and their integration is becoming increasingly required, because of decentralized structure of the situation applications and the manufacturing's then multidisciplinary research activities' compatibility needs [13]Relational databases are no longer able to match the availability and solubility demands of online and mobile applications in this new environment. Furthermore, the relational data model's strict restrictions and limitations appear to be constraining big data analytics [14] The structure of the No-SQL database, which turns expanding The storage level's efficiency storage requirements, is gaining traction between the research world and the business world as unstructured data continues to grow due to the heterogeneous nature of its sources.…”

Section: Overview Of Healthcare Data Manipulationmentioning

confidence: 99%

The Signiﬁcance of IoT: A Healthcare Systems Perspective

Rasheed,

Murtaza,

Awan

et al. 2022

VAWKUM trans. comput. sci.

View full text Add to dashboard Cite

In the current era of modern technologies, the health of the patient demands real time monitoring system. This dynamic system can be developed by using efficient sensors, network and internet cloud either wire or wireless. For example, for heart patient blood pressure and pulse must be measure constantly, in case if the patient is in moving and changing his position. For this purpose, an efficient system is required. In future there will be many other problems such as viruses attach detection, dingy fever detection, and sugar problems. For all these problems there will be multiple parameters of patient must me monitor and control. In this paper a method will be device to monitor all these parameters in real time. Moreover, we are concentrating on using mobile agents to provide patient assistance and healthcare services in order to help with the diagnosis of patient’s illnesses Furthermore, platform-agnostic solutions for healthcare data collection and dissemination over NoSQL are being studied. The Apache Jena Fuseki NoSQL database with the JAVA Example Application Framework -JADE client platform was used in testing environment. The consequences show that No Structure Query Language version beats the rel-database implementation.

show abstract

Potential diagnosis of COVID-19 from chest X-ray and CT findings using semi-supervised learning

Cited by 13 publications

References 56 publications

Comparative Analysis on Available Technique for the Detection of Covid-19 through CT-Scan and X-Ray using Machine Learning: A Systematic Review

Comparative Analysis on Available Technique for the Detection of Covid-19 through CT-Scan and X-Ray using Machine Learning: A Systematic Review

Clustering Mining Algorithm of Internet of Things Database Based on Python Language

The Signiﬁcance of IoT: A Healthcare Systems Perspective

Contact Info

Product

Resources

About