A modified deep learning model in the classification of post-COVID-19 lung disease and a comparative study on Iranian and international databases
Bibliographic record
Abstract
Background:We introduced Mask R-CNN+CNN as a deep learning model to classify COVID-19 and non-COVID-19 cases.Radiomic features relevant to COVID-19 was presented for Iranian and other nationalities.Materials and Methods: Chest CT images from 800 COVID-19 positive and negative patients were studied.The automated volume of the lung and segmentation of COVID-19 lung lesions were implemented using 3D U-net, Capsule network, and Mask R-CNN on annotated CT images.Deep learning models designed were based on Mask R-CNN, CNN, and Mask R -CNN+CNN algorithms to classify COVID-19 cases.We also explored radiomic features relevant to the COVID-19 pandemic in the lungs for chest CT images and implemented random forest (RF), decision tree (DT), and gradient boosting decision tree (GBDT) algorithms on two datasets.Results: The Mask R-CNN+CNN model demonstrated a higher classification accuracy (96.39 ± 2.94) compared to the Mask R-CNN and CNN models.The RF algorithm had greater power in differentiating relevant COVID-19 radiomic features compared to DT and GBDT, with an accuracy of at least 91 and an AUC of at least 985 in both datasets.We identified six radiomic features that were relevant to the pathological characteristics of COVID-19 positive/negative patients and were common across all datasets.Conclusion: This study emphasizes the power of Mask R-CNN+CNN with a ResNet-101 backbone as a CNN algorithm that utilizes bounding box offsets output from Mask R-CNN as the input for classifying COVID-19 cases.Radiomic features extracted from lung CT images might aid the diagnosis of COVID-19 in patients at various stages of the disease.
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 | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| 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 | 0.000 |
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".