Improving Lung Disease Classification from Chest X-ray Images using an Efficient Clustering Approach
Bibliographic record
Abstract
Lung diseases are a major health problem and one of the leading causes of death worldwide.Chest X-ray (CXR) is one of the most common radiological examinations for screening thoracic diseases.Despite the existing methods that have achieved significant progress in the classification of thoracic diseases, none of the studies take into account the presence of artifacts such as wires or objects in the images.Based on the above problem, in this paper we present a novel methodology for clustering sharp images from images containing artifacts, and then perform the classification exclusively to the cluster containing sharp images without artifacts.We selected CXR of pneumonia and normal cases from the ChestX-Ray14 dataset and performed histogram equalization as preprocessing technique.By applying the DenseNet-121 model exclusively to the cluster containing images without artifacts, we achieved a higher area under the curve (AUC) than the model applied to all images.Our approach thus achieved an AUC of 79.58% for pneumonia and normal images classification.To evaluate the effectiveness of our method, we conducted experiments on another disease, namely consolidation.The results demonstrated that our method is promising, highlighting its potential for broader applications in lung disease classification.This research highlights the importance of considering the presence of artifacts when diagnosing lung diseases from radiographic images.The code will be available upon request.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 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 | 0.002 |
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".