Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Periodicals of Engineering and Natural Sciences (PEN)Open Access

Segmentation and measurement of lung pathological changes for COVID-19 diagnosis based on computed tomography

View Full Paper
Ask AI
Bookmark
Share

Authors

YHYousif A. HamadUniversity of KirkukMSMohammed E. SenoUniversity of Al MaarifMAMohannad Al-KubaisiUniversity of Al Maarif

Discussion

Loading...

Member takes

Implication

Automated detection reveals significant lung abnormalities in COVID-19 patients, implying improved diagnostic accuracy.

Key Points

  • The proposed system achieved a 97.64% average coefficient for infection segment detection and accuracy.
  • Utilizing wavelet and Shearlet transforms, the study effectively improved the visualization of pathological lung changes.
  • The Jaccard similarity coefficient was 96.73%, demonstrating robust segmentation of tumors and COVID-infected areas.
  • By applying pre-processing methods to dynamic CT images, the detection of lung abnormalities was significantly enhanced.

Cite This Study

Hamad et al. (2021) studied this question.

synapsesocial.com/papers/68c19ab49b7b07f3a061c822https://doi.org/10.21533/pen.v9.i3.819
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1CT-Based Auto Lung Damage Assessment COVID-192025
  2. 2PSACOVID: Parallel Segmentation Architecture for Localization and Contagion Quantification of Covid-19 Pneumonia in Chest Computed Tomography Imaging2025
  3. 3COVID Pneumonia Severity Detection of Chest CT-Scan Images based on Robust Semantic Segmentation2024 · 1 citations
  4. 4Enhancing COVID-19 diagnosis and severity evaluation through machine learning algorithms applied to ct images2024 · 76 citations
  5. 5Lung Infection Detection via CT Images and Transfer Learning Techniques in Deep Learning2024 · 2 citations