CT image feature analysis in distinguishing radiation fibrosis from tumour recurrence after stereotactic ablative radiotherapy (SABR) for lung cancer: a preliminary study
Bibliographic record
Abstract
Radiation induced lung injury (RILI) is a common finding following lung radiotherapy and results in radiographic changes on computed tomography (CT). Stereotactic ablative radiotherapy (SABR) treats the tumour to a highly conformal dose with large doses/fraction, which can result in benign, tumour-mimicking radiographic changes. Our purpose was to determine the ability of quantitative measures of post-SABR radiographic changes to distinguish the subject groups (recurrence vs. RILI) at several time points. Two regions were manually contoured on each follow-up CT: consolidative changes and ground glass opacity (GGO). A peri-tumoural region of GGO was also taken around the consolidative changes. At 9 months, patients with recurrence had significantly denser consolidative areas compared to patients with RILI (p=.046) and significantly increased variability of CT densities in the GGO areas (p=.0078). The variability of CT density in a peri-tumoural region of 4 mm thickness was also significant at 9 months post-treatment (p=.0499). Our preliminary study of classification accuracy based on these measures showed that variability of the GGO CT density was the best predictor with a cross validation error of 26.1%, demonstrating that further refinement of the features and classifier may soon lead to a clinically useful computer-aided diagnosis tool. These results suggest the future potential to distinguish patients with recurrence from those RILI at 9 months post-SABR based on appearance characteristics within the consolidative, GGO, and peri-tumoural regions. This could potentially allow for earlier salvage of patients with recurrence, and result in fewer investigations of benign RILI.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 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 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".