Pulmonary Medical Image Recognition Based on Deep Learning
Bibliographic record
Abstract
Pulmonary nodules are important indicators for the early diagnosis of lung can- cer, and their identification and classification are of great significance. At present, there exist significant domain discrepancies between source and target datasets when using transfer learning-based recognition algorithms, which leads to poor feature extraction of pulmonary nodules and thus unsatisfactory results. Therefore, this paper proposes an improved convolutional neural network model based on a mod- ified neural network architecture. The model integrates features extracted by the pre-trained GoogLeNet Inception V3 network to enhance its ability to extract relev- ant features. In order to determine the optimal combination, different groups were tested using accuracy as the evaluation metric. Experiments were conducted on the LUNA16 lung nodule dataset. The results from cross-validation testing show that the improved network achieves an accuracy of 88.80% and a sensitivity of 87.15%. In terms of recognition accuracy and sensitivity, the proposed method outperforms GoogLeNet Inception V3, with improvements of 2.72 and 2.19 percentage points, respectively. Even when tested on small-scale datasets, the model demonstrates bet- ter generalization capability. This method can provide objective reference indicators for clinical diagnosis.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| 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".