TVFx – CoVID-19 X-Ray images classification approach using neural networks based feature thresholding technique
Abstract COVID-19, the global pandemic of twenty-first century, has caused major challenges and setbacks for researchers and medical infrastructure worldwide. The CoVID-19 influences on the patients respiratory system cause flooding of airways in the lungs. Multiple techniques have been proposed since the outbreak each of which is interdepended on features and larger training datasets. It is challenging scenario to consolidate larger datasets for accurate and reliable decision support. This research article proposes a chest X-Ray images classification approach based on feature thresholding in categorizing the CoVID-19 samples. The proposed approach uses the threshold value-based Feature Extraction (TVFx) technique and has been validated on 661-CoVID-19 X-Ray datasets in providing decision support for medical experts. The model has three layers of training datasets to attain a sequential pattern based on various learning features. The aligned feature-set of the proposed technique has successfully categorized CoVID-19 active samples into mild, serious, and extreme categories as per medical standards. The proposed technique has achieved an accuracy of 97.42% in categorizing and classifying given samples sets..
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:23 |
|---|---|
| Enthalten in: |
BMC medical imaging - 23(2023), 1 vom: 02. Okt. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Ahmed, Syed Thouheed [VerfasserIn] |
|---|
| Links: |
Volltext [kostenfrei] |
|---|
| Themen: |
COVID-19 |
|---|
| Anmerkungen: |
© The Author(s) 2023 |
|---|
| doi: |
10.1186/s12880-023-01100-8 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
SPR05328500X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR05328500X | ||
| 003 | DE-627 | ||
| 005 | 20231120064728.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231005s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s12880-023-01100-8 |2 doi | |
| 035 | |a (DE-627)SPR05328500X | ||
| 035 | |a (SPR)s12880-023-01100-8-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Ahmed, Syed Thouheed |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a TVFx – CoVID-19 X-Ray images classification approach using neural networks based feature thresholding technique |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a © The Author(s) 2023 | ||
| 520 | |a Abstract COVID-19, the global pandemic of twenty-first century, has caused major challenges and setbacks for researchers and medical infrastructure worldwide. The CoVID-19 influences on the patients respiratory system cause flooding of airways in the lungs. Multiple techniques have been proposed since the outbreak each of which is interdepended on features and larger training datasets. It is challenging scenario to consolidate larger datasets for accurate and reliable decision support. This research article proposes a chest X-Ray images classification approach based on feature thresholding in categorizing the CoVID-19 samples. The proposed approach uses the threshold value-based Feature Extraction (TVFx) technique and has been validated on 661-CoVID-19 X-Ray datasets in providing decision support for medical experts. The model has three layers of training datasets to attain a sequential pattern based on various learning features. The aligned feature-set of the proposed technique has successfully categorized CoVID-19 active samples into mild, serious, and extreme categories as per medical standards. The proposed technique has achieved an accuracy of 97.42% in categorizing and classifying given samples sets. | ||
| 650 | 4 | |a COVID-19 |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a X-Ray image classification |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Feature-alignment |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Corona virus classification |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a COVID-19 detection |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Basha, Syed Muzamil |4 aut | |
| 700 | 1 | |a Venkatesan, Muthukumaran |4 aut | |
| 700 | 1 | |a Mathivanan, Sandeep Kumar |4 aut | |
| 700 | 1 | |a Mallik, Saurav |4 aut | |
| 700 | 1 | |a Alsubaie, Najah |4 aut | |
| 700 | 1 | |a Alqahtani, Mohammed S. |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t BMC medical imaging |d London : BioMed Central, 2001 |g 23(2023), 1 vom: 02. Okt. |w (DE-627)SPR027472574 |w (DE-600)2061975-3 |x 1471-2342 |7 nnns |
| 773 | 1 | 8 | |g volume:23 |g year:2023 |g number:1 |g day:02 |g month:10 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1186/s12880-023-01100-8 |z kostenfrei |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 951 | |a AR | ||
| 952 | |d 23 |j 2023 |e 1 |b 02 |c 10 | ||