An evaluation of lightweight deep learning techniques in medical imaging for high precision COVID-19 diagnostics

Ogechukwu, Ukwandu,; Hindy, Hanan; Ukwandu, Elochukwu

doi:10.1016/j.health.2022.100096

Cited by 12 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Reference Method Data Size Accuracy (%) Trainable Parameters COVID-19 Normal (Anunay Gupta et al, 2021 ) Inception-V3 361 365 97.00 24,000,000 ( George et al, 2023 ) GrayVIC model 2,250 2,250 98.06 2,684,650 ( Hussain et al, 2021 ) CoroDet 500 800 99.10 2,873,609 ( Jyoti et al, 2023 ) ResNet50 2409 2866 95.67 23,591,810 (A. I. Khan et al, 2020 ) CoroNet 284 310 99.00 33,969,964 ( Malik et al, 2022 ) Vgg16 4630 1583 93.00 14,715,714 ( Nayak et al, 2021 ) ResNet-34 775 775 98.33 21,800,000 ( Nayak et al, 2023 ) LW-CORONet 2358 8066 96.25 680,000 ( Sahin, 2022 ) CNN_Model 3,626 10,198 96.71 667,458 ( Ukwandu et al, 2022 ) MobileNet-V2 1,200 1,341 99.60 3,538,984 Proposed Model Lightweight CNN Model 3,616 10,192 98.55 ...…”

Section: Resultsmentioning

confidence: 99%

“… Reference Method Data Size Accuracy (%) Trainable Parameters COVID-19 Normal Pneumonia ( Apostolopoulos & Mpesiana, 2020 ) VGG19 224 504 714 93.48 143,667,240 (Anunay Gupta et al, 2021 ) Inception-V3 361 365 362 97.00 24,000,000 ( George et al, 2023 ) GrayVIC model 2,250 2,250 2,250 97.41 2,684,650 ( Hussain et al, 2021 ) CoroDet 500 800 800 94.20 2,874,635 ( Heidari et al, 2020 ) VGG16 445 2,880 5,179 94.50 138,000,000 (A. I. Khan et al, 2020 ) CoroNet 284 310 657 95.00 33,969,964 ( Nayak et al, 2023 ) LW-CORONet 2358 8066 5575 95.67 680,000 ( Ukwandu et al, 2022 ) MobileNet-V2 1,200 1,341 1,345 94.50 3,538,984 (L. Wang et al, 2020 ) COVID-Net 358 8,066 5,538 93.30 11,750,000 ( Zebin & Rezvy, 2021 ) EfficientNetB0 ...…”

Section: Resultsmentioning

confidence: 99%

“…( Ukwandu et al, 2022 ) proposed three lightweight CNN models through fine-tuning MobileNetV2 architecture to detect COVID-19 infection using chest X-ray images. The first model was designed for 3-class categorization (COVID-19, Normal, Viral Pneumonia infection).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Lightweight deep CNN-based models for early detection of COVID-19 patients from chest X-ray images

Hussein¹,

Mohammed²,

Hassan³

et al. 2023

Expert Systems with Applications

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Lightweight deep CNN-based models for early detection of COVID-19 patients from chest X-ray images

Hussein¹,

Mohammed²,

Hassan³

et al. 2023

Expert Systems with Applications

View full text Add to dashboard Cite

“…Ukwandu et al [ 17 ] developed three lightweight architectures by fine-tuning the MobileNetV2 algorithm for diagnosing COVID-19 patients by using CXR images. These models were introduced for three classification and two classification tasks.…”

Section: Related Workmentioning

confidence: 99%

A high-accuracy lightweight network model for X-ray image diagnosis: A case study of COVID detection

Wang,

Ren,

Guo

2024

PLoS ONE

View full text Add to dashboard Cite

The Coronavirus Disease 2019(COVID-19) has caused widespread and significant harm globally. In order to address the urgent demand for a rapid and reliable diagnostic approach to mitigate transmission, the application of deep learning stands as a viable solution. The impracticality of many existing models is attributed to excessively large parameters, significantly limiting their utility. Additionally, the classification accuracy of the model with few parameters falls short of desirable levels. Motivated by this observation, the present study employs the lightweight network MobileNetV3 as the underlying architecture. This paper incorporates the dense block to capture intricate spatial information in images, as well as the transition layer designed to reduce the size and channel number of the feature map. Furthermore, this paper employs label smoothing loss to address the inter-class similarity effects and uses class weighting to tackle the problem of data imbalance. Additionally, this study applies the pruning technique to eliminate unnecessary structures and further reduce the number of parameters. As a result, this improved model achieves an impressive 98.71% accuracy on an openly accessible database, while utilizing only 5.94 million parameters. Compared to the previous method, this maximum improvement reaches 5.41%. Moreover, this research successfully reduces the parameter count by up to 24 times, showcasing the efficacy of our approach. This demonstrates the significant benefits in regions with limited availability of medical resources.

show abstract

$$\mathrm SRC_{2}$$: a novel deep learning based technique for identifying COVID-19 using images of chest x-ray

Acharya,

Banerjea,

2023

Multimed Tools Appl

View full text Add to dashboard Cite

An evaluation of lightweight deep learning techniques in medical imaging for high precision COVID-19 diagnostics

Cited by 12 publications

References 43 publications

Lightweight deep CNN-based models for early detection of COVID-19 patients from chest X-ray images

Lightweight deep CNN-based models for early detection of COVID-19 patients from chest X-ray images

A high-accuracy lightweight network model for X-ray image diagnosis: A case study of COVID detection

$$\mathrm SRC_{2}$$: a novel deep learning based technique for identifying COVID-19 using images of chest x-ray

Contact Info

Product

Resources

About