Comparison of COVID-19 Classification via Imagenet-Based and RadImagenet-Based Transfer Learning Models with Random Frame Selection
Bibliographic record
Abstract
Transfer learning methods are used in lung ultrasound (US) video classification as the training data for learning is generally limited. However, transfer learning models trained on the ImageNet dataset have been considered in the literature. Recently, the RadImageNet dataset, which contains medical images, was made available with four pre-trained models. In this work, pretrained models from both of these datasets are used as the backbone network, and models are developed for COVID-19 classification based on frames and videos. Random frame selection method is proposed and compared with the commonly used constant and non-adjacent frame selections. Video classification based on selected frames (VCBSF), and video classification based on the whole video (VCBWV) using voting are studied as part of video classification approach. A publicly available COVID-19 dataset is used to do this comparative study. The pre-trained models using the ImageNet dataset outperformed those using the RadImageNet dataset for frame classification. The ResNet50 and DenseNet121 models using ImageNet outperformed their counterparts using RadImageNet for VCBSF classification, while the Inception_ResNet_V2 and Inception_V3 models using RadImageNet performed better for VCBWV classification. These findings provide insight into improving the accuracy of COVID-19 detection using deep learning techniques and random frame selection.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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".