COVID-19 Classification Using Pre-Trained Models and Disease Severity Score Masks
Bibliographic record
Abstract
The significance of early detection of COVID-19 has been widely acknowledged as a means of reducing its spread and mortality rates among patients. Deep learning techniques for COVID-19 classification based on ultrasound (US) data have been extensively employed. However, detecting COVID-19 based on US images continues to be challenging primarily due to limited datasets with noisy and low-resolution images. This study investigates methods to enhance classification performance by incorporating disease severity score masks while training pretrained models enhanced with self-attention mechanisms. The disease severity scores range from 0 for healthy lung tissue to 1 for initial signs of abnormality, and 2 and 3 for advanced pathological artifacts. These masks and their corresponding US images are employed as inputs to pre-trained models for feature extraction. Subsequently, features extracted from the masks are utilized to recalibrate features obtained from US images using self-attention mechanisms. The proposed method achieves classification accuracy of 95.4, 90.4, 95%, 83%, and 92% when using pre-trained models VGG16, NASNet-Mobile, MobileNet_V2, ResNet50, and Xception, respectively. Further, all pre-trained models yield a low standard deviation of less than 5%. The results demonstrate that incorporating disease severity masks improves the classification performance, thus offering promising techniques for enhancing COVID-19 detection using ultrasound imaging.
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) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".