Lung Ultrasound Image Classification Using Deep Learning and Histogram of Oriented Gradients Features for COVID-19 Detection
Bibliographic record
Abstract
Features derived by deep learning models are useful in challenging classification tasks such as the detection of COVID-19 in ultrasound lung images. However, in this process, knowledge-based hand-crafted features engineered by humans are totally neglected. Hand-crafted features do have a significant role in performance enhancement in complicated classification tasks. This paper proposes a fusion of hand-crafted features with abstract features produced by deep learning in the later stages of the classification process for COVID-19 detection. Histogram of Oriented Gradients (HOG) features are used as a hand-crafted feature for fusion with abstract features produced by VGG 16 and Vision transformer (ViT). The HOG and abstract features are fused later to improve the classification model's performance. A public COVID-19 dataset is used to demonstrate the improved performance of the proposed classification model. Results show that the proposed fusion technique improves the accuracy achieved by ViT for normal vs abnormal classification by 1.75% and for COVID-19 vs bacterial pneumonia classification by 1.04% when compared with the traditional ViT classification results. Similarly, when abstract features produced by VGG 16 were fused with HOG features, the classification accuracy achieved an improvement of approximately 5.81% and 4.94% for normal vs abnormal and COVID-19 vs bacterial pneumonia classification, respectively.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".