Pneumonia and COVID-19 Detection in Chest X-rays Using Faster Region-Based Convolutional Neural Networks (Faster R-CNN)
Bibliographic record
Abstract
The arising of SARS-CoV-2 or 2019 novel coron-avirus in December 2019 have prioritized research on pulmonary diseases diagnosis and prognosis, especially using artificial intelligence (AI) and Deep Learning (DL). Polymerase Chain Reaction (PCR) is the most widely used technique to detect SARS-CoV-2, with a 0.12% false negative rate. While 75% of the hospitalized cases develop pneumonia caused by the virus, patients can still develop bacterial pneumonia. COVID-19 pneumonia can be diagnosed based on clinical data and Computed Tomography (CT scan). However, Chest X-rays are faster, cheaper, emit less radiations, and can be performed on bed-side. In this article, we extend the application of VGG-16 based Faster Region-Based Convolutional Neural Network (Faster R-CNN) to the detection of Pneumonia and COVID-19 in Chest X-ray images using several public datasets of total images count ranging from 2122 to 18455 Chest X-rays, and study the impact of several hyper-parameters such as objectness threshold and epochs count and length, to optimize the model's performance. Our results comply with the state of the art of Faster R-CNN in pneumonia detection as the best accuracy achieved is 65%. For COVID-19 detection, Faster R-CNN achieves a 90% validation accuracy.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.002 | 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".