A Sustainable Deep Learning-Based Framework for Automated Segmentation of COVID-19 Infected Regions: Using U-Net with an Attention Mechanism and Boundary Loss Function
Bibliographic record
Abstract
COVID-19 has been spreading rapidly, affecting billions of people globally, with significant public health impacts. Biomedical imaging, such as computed tomography (CT), has significant potential as a possible substitute for the screening process. Because of this, automatic segmentation of images is highly desirable as clinical decision support for an extensive evaluation of disease control and monitoring. It is a dynamic tool and performs a central role in precise or accurate segmentation of infected areas or regions in CT scans, thus helping in screening, diagnosing, and disease monitoring. For this purpose, we introduced a deep learning framework for automated segmentation of COVID-19 infected lesions/regions in lung CT scan images. Specifically, we adopted a segmentation model, i.e., U-Net, and utilized an attention mechanism to enhance the framework’s ability for the segmentation of virus-infected regions. Since all of the features extracted or obtained from the encoders are not valuable for segmentation; thus, we applied the U-Net architecture with a mechanism of attention for a better representation of the features. Moreover, we applied a boundary loss function to deal with small and unbalanced lesion segmentation’s. Using different public CT scan image data sets, we validated the framework’s effectiveness in contrast with other segmentation techniques. The experimental outcomes showed the improved performance of the presented framework for the automated segmentation of lungs and infected areas in CT scan images. We also considered both boundary loss and weighted binary cross-entropy dice loss function. The overall dice accuracies of the framework are 0.93 and 0.76 for lungs and COVID-19 infected areas/regions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".