A computer-aided diagnosis system for lung nodule detection in pulmonary CT images based on LS-SVM and wavelet transformation
Bibliographic record
Abstract
One of the most important areas of biomedical engineering is medical imaging. Fully automated schemes are currently being explored as Computer-Aided Diagnosis (CAD) systems to provide a second opinion to medical professionals; of these systems, abnormal region detector in medical images is one of the most critical CAD systems in development. The primary motivation in using these systems is due to the fact that reading an enormous number of images is a time-consuming task for the radiologist. This task can be sped up by using a CAD system which highlights abnormal regions of interest. Low false positive rates and high sensitivity are essential requirement[s] of such a system. The initial requirement of processing any organ is an accurate segmentation of the target of interest in the images. A segmentation method based on the wavelet transformation is proposed which accurately extracts lung regions in the thoracic CT images. After this step, an Aritifical Intelligence system, known as Least Squares Support Vector Machine (LS-SVM), is employed to classify nodules within the regions of interest. It is a well known fact that the lung nodules, except the pleural nodules, are mostly spherical structures whereas other structures including blood vessels are shaped as other structures such as tubular. Therfore, an enhancment filter is developed in which spherical structures are accentuated. Processing three different real databases revealed that the proposed system has reached the objective of a CAD system to provide reliable opinion for the doctors in the diagnosis fashion.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".